Initial commit
This commit is contained in:
File diff suppressed because one or more lines are too long
@@ -0,0 +1,169 @@
|
||||
from __future__ import print_function, division
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.optim as optim
|
||||
from torch.optim import lr_scheduler
|
||||
import torch.backends.cudnn as cudnn
|
||||
import numpy as np
|
||||
import torchvision
|
||||
from torchvision import datasets, models, transforms
|
||||
import matplotlib.pyplot as plt
|
||||
import time
|
||||
import os
|
||||
import copy
|
||||
|
||||
cudnn.benchmark = True
|
||||
plt.ion() # interactive mode
|
||||
|
||||
data_transforms = {
|
||||
'train': transforms.Compose([
|
||||
transforms.RandomResizedCrop(224),
|
||||
transforms.RandomHorizontalFlip(),
|
||||
transforms.ToTensor(),
|
||||
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
|
||||
]),
|
||||
'val': transforms.Compose([
|
||||
transforms.Resize(256),
|
||||
transforms.CenterCrop(224),
|
||||
transforms.ToTensor(),
|
||||
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
|
||||
]),
|
||||
}
|
||||
|
||||
data_dir = 'hymenoptera_data'
|
||||
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
|
||||
data_transforms[x])
|
||||
for x in ['train', 'val']}
|
||||
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
|
||||
shuffle=True, num_workers=4)
|
||||
for x in ['train', 'val']}
|
||||
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
|
||||
class_names = image_datasets['train'].classes
|
||||
|
||||
device = torch.device("cpu")
|
||||
|
||||
def imshow(inp, title=None):
|
||||
"""Imshow for Tensor."""
|
||||
inp = inp.numpy().transpose((1, 2, 0))
|
||||
mean = np.array([0.485, 0.456, 0.406])
|
||||
std = np.array([0.229, 0.224, 0.225])
|
||||
inp = std * inp + mean
|
||||
inp = np.clip(inp, 0, 1)
|
||||
plt.imshow(inp)
|
||||
if title is not None:
|
||||
plt.title(title)
|
||||
plt.pause(0.001) # pause a bit so that plots are updated
|
||||
|
||||
def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
|
||||
since = time.time()
|
||||
|
||||
best_model_wts = copy.deepcopy(model.state_dict())
|
||||
best_acc = 0.0
|
||||
|
||||
for epoch in range(num_epochs):
|
||||
print(f'Epoch {epoch}/{num_epochs - 1}')
|
||||
print('-' * 10)
|
||||
|
||||
# Each epoch has a training and validation phase
|
||||
for phase in ['train', 'val']:
|
||||
if phase == 'train':
|
||||
model.train() # Set model to training mode
|
||||
else:
|
||||
model.eval() # Set model to evaluate mode
|
||||
|
||||
running_loss = 0.0
|
||||
running_corrects = 0
|
||||
|
||||
# Iterate over data.
|
||||
for inputs, labels in dataloaders[phase]:
|
||||
inputs = inputs.to(device)
|
||||
labels = labels.to(device)
|
||||
|
||||
# zero the parameter gradients
|
||||
optimizer.zero_grad()
|
||||
|
||||
# forward
|
||||
# track history if only in train
|
||||
with torch.set_grad_enabled(phase == 'train'):
|
||||
outputs = model(inputs)
|
||||
_, preds = torch.max(outputs, 1)
|
||||
loss = criterion(outputs, labels)
|
||||
|
||||
# backward + optimize only if in training phase
|
||||
if phase == 'train':
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
# statistics
|
||||
running_loss += loss.item() * inputs.size(0)
|
||||
running_corrects += torch.sum(preds == labels.data)
|
||||
if phase == 'train':
|
||||
scheduler.step()
|
||||
|
||||
epoch_loss = running_loss / dataset_sizes[phase]
|
||||
epoch_acc = running_corrects.double() / dataset_sizes[phase]
|
||||
|
||||
print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')
|
||||
|
||||
# deep copy the model
|
||||
if phase == 'val' and epoch_acc > best_acc:
|
||||
best_acc = epoch_acc
|
||||
best_model_wts = copy.deepcopy(model.state_dict())
|
||||
|
||||
print()
|
||||
|
||||
time_elapsed = time.time() - since
|
||||
print(f'Training complete in {time_elapsed // 60:.0f}m {time_elapsed % 60:.0f}s')
|
||||
print(f'Best val Acc: {best_acc:4f}')
|
||||
|
||||
# load best model weights
|
||||
model.load_state_dict(best_model_wts)
|
||||
return model
|
||||
|
||||
def visualize_model(model, num_images=6):
|
||||
was_training = model.training
|
||||
model.eval()
|
||||
images_so_far = 0
|
||||
fig = plt.figure()
|
||||
|
||||
with torch.no_grad():
|
||||
for i, (inputs, labels) in enumerate(dataloaders['val']):
|
||||
inputs = inputs.to(device)
|
||||
labels = labels.to(device)
|
||||
|
||||
outputs = model(inputs)
|
||||
_, preds = torch.max(outputs, 1)
|
||||
|
||||
for j in range(inputs.size()[0]):
|
||||
images_so_far += 1
|
||||
ax = plt.subplot(num_images//2, 2, images_so_far)
|
||||
ax.axis('off')
|
||||
ax.set_title(f'predicted: {class_names[preds[j]]}')
|
||||
imshow(inputs.cpu().data[j])
|
||||
|
||||
if images_so_far == num_images:
|
||||
model.train(mode=was_training)
|
||||
return
|
||||
model.train(mode=was_training)
|
||||
|
||||
model_ft = models.resnet18(pretrained=True)
|
||||
num_ftrs = model_ft.fc.in_features
|
||||
# Here the size of each output sample is set to 2.
|
||||
# Alternatively, it can be generalized to nn.Linear(num_ftrs, len(class_names)).
|
||||
model_ft.fc = nn.Linear(num_ftrs, 2)
|
||||
|
||||
model_ft = model_ft.to(device)
|
||||
|
||||
criterion = nn.CrossEntropyLoss()
|
||||
|
||||
# Observe that all parameters are being optimized
|
||||
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)
|
||||
|
||||
# Decay LR by a factor of 0.1 every 7 epochs
|
||||
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
|
||||
|
||||
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
|
||||
num_epochs=25)
|
||||
|
||||
visualize_model(model_ft)
|
||||
@@ -0,0 +1,263 @@
|
||||
# Repo-specific GitIgnore ----------------------------------------------------------------------------------------------
|
||||
*.jpg
|
||||
*.jpeg
|
||||
*.png
|
||||
*.bmp
|
||||
*.tif
|
||||
*.tiff
|
||||
*.heic
|
||||
*.JPG
|
||||
*.JPEG
|
||||
*.PNG
|
||||
*.BMP
|
||||
*.TIF
|
||||
*.TIFF
|
||||
*.HEIC
|
||||
*.mp4
|
||||
*.mov
|
||||
*.MOV
|
||||
*.avi
|
||||
*.data
|
||||
*.json
|
||||
*.cfg
|
||||
!setup.cfg
|
||||
!cfg/yolov3*.cfg
|
||||
|
||||
storage.googleapis.com
|
||||
runs/*
|
||||
data/*
|
||||
data/images/*
|
||||
!data/*.yaml
|
||||
!data/hyps
|
||||
!data/scripts
|
||||
!data/images
|
||||
!data/images/zidane.jpg
|
||||
!data/images/bus.jpg
|
||||
!data/*.sh
|
||||
|
||||
results*.csv
|
||||
|
||||
# Datasets -------------------------------------------------------------------------------------------------------------
|
||||
coco/
|
||||
coco128/
|
||||
VOC/
|
||||
|
||||
coco2017labels-segments.zip
|
||||
test2017.zip
|
||||
train2017.zip
|
||||
val2017.zip
|
||||
|
||||
# MATLAB GitIgnore -----------------------------------------------------------------------------------------------------
|
||||
*.m~
|
||||
*.mat
|
||||
!targets*.mat
|
||||
|
||||
# Neural Network weights -----------------------------------------------------------------------------------------------
|
||||
*.weights
|
||||
*.pt
|
||||
*.pb
|
||||
*.onnx
|
||||
*.engine
|
||||
*.mlmodel
|
||||
*.torchscript
|
||||
*.tflite
|
||||
*.h5
|
||||
*_saved_model/
|
||||
*_web_model/
|
||||
*_openvino_model/
|
||||
darknet53.conv.74
|
||||
yolov3-tiny.conv.15
|
||||
*.ptl
|
||||
*.trt
|
||||
|
||||
# GitHub Python GitIgnore ----------------------------------------------------------------------------------------------
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
env/
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
*.egg-info/
|
||||
/wandb/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
.hypothesis/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# pyenv
|
||||
.python-version
|
||||
|
||||
# celery beat schedule file
|
||||
celerybeat-schedule
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# dotenv
|
||||
.env
|
||||
|
||||
# virtualenv
|
||||
.venv*
|
||||
venv*/
|
||||
ENV*/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
|
||||
|
||||
# https://github.com/github/gitignore/blob/master/Global/macOS.gitignore -----------------------------------------------
|
||||
|
||||
# General
|
||||
.DS_Store
|
||||
.AppleDouble
|
||||
.LSOverride
|
||||
|
||||
# Icon must end with two \r
|
||||
Icon
|
||||
Icon?
|
||||
|
||||
# Thumbnails
|
||||
._*
|
||||
|
||||
# Files that might appear in the root of a volume
|
||||
.DocumentRevisions-V100
|
||||
.fseventsd
|
||||
.Spotlight-V100
|
||||
.TemporaryItems
|
||||
.Trashes
|
||||
.VolumeIcon.icns
|
||||
.com.apple.timemachine.donotpresent
|
||||
|
||||
# Directories potentially created on remote AFP share
|
||||
.AppleDB
|
||||
.AppleDesktop
|
||||
Network Trash Folder
|
||||
Temporary Items
|
||||
.apdisk
|
||||
|
||||
|
||||
# https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore
|
||||
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
|
||||
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
|
||||
|
||||
# User-specific stuff:
|
||||
.idea/*
|
||||
.idea/**/workspace.xml
|
||||
.idea/**/tasks.xml
|
||||
.idea/dictionaries
|
||||
.html # Bokeh Plots
|
||||
.pg # TensorFlow Frozen Graphs
|
||||
.avi # videos
|
||||
|
||||
# Sensitive or high-churn files:
|
||||
.idea/**/dataSources/
|
||||
.idea/**/dataSources.ids
|
||||
.idea/**/dataSources.local.xml
|
||||
.idea/**/sqlDataSources.xml
|
||||
.idea/**/dynamic.xml
|
||||
.idea/**/uiDesigner.xml
|
||||
|
||||
# Gradle:
|
||||
.idea/**/gradle.xml
|
||||
.idea/**/libraries
|
||||
|
||||
# CMake
|
||||
cmake-build-debug/
|
||||
cmake-build-release/
|
||||
|
||||
# Mongo Explorer plugin:
|
||||
.idea/**/mongoSettings.xml
|
||||
|
||||
## File-based project format:
|
||||
*.iws
|
||||
|
||||
## Plugin-specific files:
|
||||
|
||||
# IntelliJ
|
||||
out/
|
||||
|
||||
# mpeltonen/sbt-idea plugin
|
||||
.idea_modules/
|
||||
|
||||
# JIRA plugin
|
||||
atlassian-ide-plugin.xml
|
||||
|
||||
# Cursive Clojure plugin
|
||||
.idea/replstate.xml
|
||||
|
||||
# Crashlytics plugin (for Android Studio and IntelliJ)
|
||||
com_crashlytics_export_strings.xml
|
||||
crashlytics.properties
|
||||
crashlytics-build.properties
|
||||
fabric.properties
|
||||
@@ -0,0 +1,674 @@
|
||||
GNU GENERAL PUBLIC LICENSE
|
||||
Version 3, 29 June 2007
|
||||
|
||||
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
|
||||
Everyone is permitted to copy and distribute verbatim copies
|
||||
of this license document, but changing it is not allowed.
|
||||
|
||||
Preamble
|
||||
|
||||
The GNU General Public License is a free, copyleft license for
|
||||
software and other kinds of works.
|
||||
|
||||
The licenses for most software and other practical works are designed
|
||||
to take away your freedom to share and change the works. By contrast,
|
||||
the GNU General Public License is intended to guarantee your freedom to
|
||||
share and change all versions of a program--to make sure it remains free
|
||||
software for all its users. We, the Free Software Foundation, use the
|
||||
GNU General Public License for most of our software; it applies also to
|
||||
any other work released this way by its authors. You can apply it to
|
||||
your programs, too.
|
||||
|
||||
When we speak of free software, we are referring to freedom, not
|
||||
price. Our General Public Licenses are designed to make sure that you
|
||||
have the freedom to distribute copies of free software (and charge for
|
||||
them if you wish), that you receive source code or can get it if you
|
||||
want it, that you can change the software or use pieces of it in new
|
||||
free programs, and that you know you can do these things.
|
||||
|
||||
To protect your rights, we need to prevent others from denying you
|
||||
these rights or asking you to surrender the rights. Therefore, you have
|
||||
certain responsibilities if you distribute copies of the software, or if
|
||||
you modify it: responsibilities to respect the freedom of others.
|
||||
|
||||
For example, if you distribute copies of such a program, whether
|
||||
gratis or for a fee, you must pass on to the recipients the same
|
||||
freedoms that you received. You must make sure that they, too, receive
|
||||
or can get the source code. And you must show them these terms so they
|
||||
know their rights.
|
||||
|
||||
Developers that use the GNU GPL protect your rights with two steps:
|
||||
(1) assert copyright on the software, and (2) offer you this License
|
||||
giving you legal permission to copy, distribute and/or modify it.
|
||||
|
||||
For the developers' and authors' protection, the GPL clearly explains
|
||||
that there is no warranty for this free software. For both users' and
|
||||
authors' sake, the GPL requires that modified versions be marked as
|
||||
changed, so that their problems will not be attributed erroneously to
|
||||
authors of previous versions.
|
||||
|
||||
Some devices are designed to deny users access to install or run
|
||||
modified versions of the software inside them, although the manufacturer
|
||||
can do so. This is fundamentally incompatible with the aim of
|
||||
protecting users' freedom to change the software. The systematic
|
||||
pattern of such abuse occurs in the area of products for individuals to
|
||||
use, which is precisely where it is most unacceptable. Therefore, we
|
||||
have designed this version of the GPL to prohibit the practice for those
|
||||
products. If such problems arise substantially in other domains, we
|
||||
stand ready to extend this provision to those domains in future versions
|
||||
of the GPL, as needed to protect the freedom of users.
|
||||
|
||||
Finally, every program is threatened constantly by software patents.
|
||||
States should not allow patents to restrict development and use of
|
||||
software on general-purpose computers, but in those that do, we wish to
|
||||
avoid the special danger that patents applied to a free program could
|
||||
make it effectively proprietary. To prevent this, the GPL assures that
|
||||
patents cannot be used to render the program non-free.
|
||||
|
||||
The precise terms and conditions for copying, distribution and
|
||||
modification follow.
|
||||
|
||||
TERMS AND CONDITIONS
|
||||
|
||||
0. Definitions.
|
||||
|
||||
"This License" refers to version 3 of the GNU General Public License.
|
||||
|
||||
"Copyright" also means copyright-like laws that apply to other kinds of
|
||||
works, such as semiconductor masks.
|
||||
|
||||
"The Program" refers to any copyrightable work licensed under this
|
||||
License. Each licensee is addressed as "you". "Licensees" and
|
||||
"recipients" may be individuals or organizations.
|
||||
|
||||
To "modify" a work means to copy from or adapt all or part of the work
|
||||
in a fashion requiring copyright permission, other than the making of an
|
||||
exact copy. The resulting work is called a "modified version" of the
|
||||
earlier work or a work "based on" the earlier work.
|
||||
|
||||
A "covered work" means either the unmodified Program or a work based
|
||||
on the Program.
|
||||
|
||||
To "propagate" a work means to do anything with it that, without
|
||||
permission, would make you directly or secondarily liable for
|
||||
infringement under applicable copyright law, except executing it on a
|
||||
computer or modifying a private copy. Propagation includes copying,
|
||||
distribution (with or without modification), making available to the
|
||||
public, and in some countries other activities as well.
|
||||
|
||||
To "convey" a work means any kind of propagation that enables other
|
||||
parties to make or receive copies. Mere interaction with a user through
|
||||
a computer network, with no transfer of a copy, is not conveying.
|
||||
|
||||
An interactive user interface displays "Appropriate Legal Notices"
|
||||
to the extent that it includes a convenient and prominently visible
|
||||
feature that (1) displays an appropriate copyright notice, and (2)
|
||||
tells the user that there is no warranty for the work (except to the
|
||||
extent that warranties are provided), that licensees may convey the
|
||||
work under this License, and how to view a copy of this License. If
|
||||
the interface presents a list of user commands or options, such as a
|
||||
menu, a prominent item in the list meets this criterion.
|
||||
|
||||
1. Source Code.
|
||||
|
||||
The "source code" for a work means the preferred form of the work
|
||||
for making modifications to it. "Object code" means any non-source
|
||||
form of a work.
|
||||
|
||||
A "Standard Interface" means an interface that either is an official
|
||||
standard defined by a recognized standards body, or, in the case of
|
||||
interfaces specified for a particular programming language, one that
|
||||
is widely used among developers working in that language.
|
||||
|
||||
The "System Libraries" of an executable work include anything, other
|
||||
than the work as a whole, that (a) is included in the normal form of
|
||||
packaging a Major Component, but which is not part of that Major
|
||||
Component, and (b) serves only to enable use of the work with that
|
||||
Major Component, or to implement a Standard Interface for which an
|
||||
implementation is available to the public in source code form. A
|
||||
"Major Component", in this context, means a major essential component
|
||||
(kernel, window system, and so on) of the specific operating system
|
||||
(if any) on which the executable work runs, or a compiler used to
|
||||
produce the work, or an object code interpreter used to run it.
|
||||
|
||||
The "Corresponding Source" for a work in object code form means all
|
||||
the source code needed to generate, install, and (for an executable
|
||||
work) run the object code and to modify the work, including scripts to
|
||||
control those activities. However, it does not include the work's
|
||||
System Libraries, or general-purpose tools or generally available free
|
||||
programs which are used unmodified in performing those activities but
|
||||
which are not part of the work. For example, Corresponding Source
|
||||
includes interface definition files associated with source files for
|
||||
the work, and the source code for shared libraries and dynamically
|
||||
linked subprograms that the work is specifically designed to require,
|
||||
such as by intimate data communication or control flow between those
|
||||
subprograms and other parts of the work.
|
||||
|
||||
The Corresponding Source need not include anything that users
|
||||
can regenerate automatically from other parts of the Corresponding
|
||||
Source.
|
||||
|
||||
The Corresponding Source for a work in source code form is that
|
||||
same work.
|
||||
|
||||
2. Basic Permissions.
|
||||
|
||||
All rights granted under this License are granted for the term of
|
||||
copyright on the Program, and are irrevocable provided the stated
|
||||
conditions are met. This License explicitly affirms your unlimited
|
||||
permission to run the unmodified Program. The output from running a
|
||||
covered work is covered by this License only if the output, given its
|
||||
content, constitutes a covered work. This License acknowledges your
|
||||
rights of fair use or other equivalent, as provided by copyright law.
|
||||
|
||||
You may make, run and propagate covered works that you do not
|
||||
convey, without conditions so long as your license otherwise remains
|
||||
in force. You may convey covered works to others for the sole purpose
|
||||
of having them make modifications exclusively for you, or provide you
|
||||
with facilities for running those works, provided that you comply with
|
||||
the terms of this License in conveying all material for which you do
|
||||
not control copyright. Those thus making or running the covered works
|
||||
for you must do so exclusively on your behalf, under your direction
|
||||
and control, on terms that prohibit them from making any copies of
|
||||
your copyrighted material outside their relationship with you.
|
||||
|
||||
Conveying under any other circumstances is permitted solely under
|
||||
the conditions stated below. Sublicensing is not allowed; section 10
|
||||
makes it unnecessary.
|
||||
|
||||
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
|
||||
|
||||
No covered work shall be deemed part of an effective technological
|
||||
measure under any applicable law fulfilling obligations under article
|
||||
11 of the WIPO copyright treaty adopted on 20 December 1996, or
|
||||
similar laws prohibiting or restricting circumvention of such
|
||||
measures.
|
||||
|
||||
When you convey a covered work, you waive any legal power to forbid
|
||||
circumvention of technological measures to the extent such circumvention
|
||||
is effected by exercising rights under this License with respect to
|
||||
the covered work, and you disclaim any intention to limit operation or
|
||||
modification of the work as a means of enforcing, against the work's
|
||||
users, your or third parties' legal rights to forbid circumvention of
|
||||
technological measures.
|
||||
|
||||
4. Conveying Verbatim Copies.
|
||||
|
||||
You may convey verbatim copies of the Program's source code as you
|
||||
receive it, in any medium, provided that you conspicuously and
|
||||
appropriately publish on each copy an appropriate copyright notice;
|
||||
keep intact all notices stating that this License and any
|
||||
non-permissive terms added in accord with section 7 apply to the code;
|
||||
keep intact all notices of the absence of any warranty; and give all
|
||||
recipients a copy of this License along with the Program.
|
||||
|
||||
You may charge any price or no price for each copy that you convey,
|
||||
and you may offer support or warranty protection for a fee.
|
||||
|
||||
5. Conveying Modified Source Versions.
|
||||
|
||||
You may convey a work based on the Program, or the modifications to
|
||||
produce it from the Program, in the form of source code under the
|
||||
terms of section 4, provided that you also meet all of these conditions:
|
||||
|
||||
a) The work must carry prominent notices stating that you modified
|
||||
it, and giving a relevant date.
|
||||
|
||||
b) The work must carry prominent notices stating that it is
|
||||
released under this License and any conditions added under section
|
||||
7. This requirement modifies the requirement in section 4 to
|
||||
"keep intact all notices".
|
||||
|
||||
c) You must license the entire work, as a whole, under this
|
||||
License to anyone who comes into possession of a copy. This
|
||||
License will therefore apply, along with any applicable section 7
|
||||
additional terms, to the whole of the work, and all its parts,
|
||||
regardless of how they are packaged. This License gives no
|
||||
permission to license the work in any other way, but it does not
|
||||
invalidate such permission if you have separately received it.
|
||||
|
||||
d) If the work has interactive user interfaces, each must display
|
||||
Appropriate Legal Notices; however, if the Program has interactive
|
||||
interfaces that do not display Appropriate Legal Notices, your
|
||||
work need not make them do so.
|
||||
|
||||
A compilation of a covered work with other separate and independent
|
||||
works, which are not by their nature extensions of the covered work,
|
||||
and which are not combined with it such as to form a larger program,
|
||||
in or on a volume of a storage or distribution medium, is called an
|
||||
"aggregate" if the compilation and its resulting copyright are not
|
||||
used to limit the access or legal rights of the compilation's users
|
||||
beyond what the individual works permit. Inclusion of a covered work
|
||||
in an aggregate does not cause this License to apply to the other
|
||||
parts of the aggregate.
|
||||
|
||||
6. Conveying Non-Source Forms.
|
||||
|
||||
You may convey a covered work in object code form under the terms
|
||||
of sections 4 and 5, provided that you also convey the
|
||||
machine-readable Corresponding Source under the terms of this License,
|
||||
in one of these ways:
|
||||
|
||||
a) Convey the object code in, or embodied in, a physical product
|
||||
(including a physical distribution medium), accompanied by the
|
||||
Corresponding Source fixed on a durable physical medium
|
||||
customarily used for software interchange.
|
||||
|
||||
b) Convey the object code in, or embodied in, a physical product
|
||||
(including a physical distribution medium), accompanied by a
|
||||
written offer, valid for at least three years and valid for as
|
||||
long as you offer spare parts or customer support for that product
|
||||
model, to give anyone who possesses the object code either (1) a
|
||||
copy of the Corresponding Source for all the software in the
|
||||
product that is covered by this License, on a durable physical
|
||||
medium customarily used for software interchange, for a price no
|
||||
more than your reasonable cost of physically performing this
|
||||
conveying of source, or (2) access to copy the
|
||||
Corresponding Source from a network server at no charge.
|
||||
|
||||
c) Convey individual copies of the object code with a copy of the
|
||||
written offer to provide the Corresponding Source. This
|
||||
alternative is allowed only occasionally and noncommercially, and
|
||||
only if you received the object code with such an offer, in accord
|
||||
with subsection 6b.
|
||||
|
||||
d) Convey the object code by offering access from a designated
|
||||
place (gratis or for a charge), and offer equivalent access to the
|
||||
Corresponding Source in the same way through the same place at no
|
||||
further charge. You need not require recipients to copy the
|
||||
Corresponding Source along with the object code. If the place to
|
||||
copy the object code is a network server, the Corresponding Source
|
||||
may be on a different server (operated by you or a third party)
|
||||
that supports equivalent copying facilities, provided you maintain
|
||||
clear directions next to the object code saying where to find the
|
||||
Corresponding Source. Regardless of what server hosts the
|
||||
Corresponding Source, you remain obligated to ensure that it is
|
||||
available for as long as needed to satisfy these requirements.
|
||||
|
||||
e) Convey the object code using peer-to-peer transmission, provided
|
||||
you inform other peers where the object code and Corresponding
|
||||
Source of the work are being offered to the general public at no
|
||||
charge under subsection 6d.
|
||||
|
||||
A separable portion of the object code, whose source code is excluded
|
||||
from the Corresponding Source as a System Library, need not be
|
||||
included in conveying the object code work.
|
||||
|
||||
A "User Product" is either (1) a "consumer product", which means any
|
||||
tangible personal property which is normally used for personal, family,
|
||||
or household purposes, or (2) anything designed or sold for incorporation
|
||||
into a dwelling. In determining whether a product is a consumer product,
|
||||
doubtful cases shall be resolved in favor of coverage. For a particular
|
||||
product received by a particular user, "normally used" refers to a
|
||||
typical or common use of that class of product, regardless of the status
|
||||
of the particular user or of the way in which the particular user
|
||||
actually uses, or expects or is expected to use, the product. A product
|
||||
is a consumer product regardless of whether the product has substantial
|
||||
commercial, industrial or non-consumer uses, unless such uses represent
|
||||
the only significant mode of use of the product.
|
||||
|
||||
"Installation Information" for a User Product means any methods,
|
||||
procedures, authorization keys, or other information required to install
|
||||
and execute modified versions of a covered work in that User Product from
|
||||
a modified version of its Corresponding Source. The information must
|
||||
suffice to ensure that the continued functioning of the modified object
|
||||
code is in no case prevented or interfered with solely because
|
||||
modification has been made.
|
||||
|
||||
If you convey an object code work under this section in, or with, or
|
||||
specifically for use in, a User Product, and the conveying occurs as
|
||||
part of a transaction in which the right of possession and use of the
|
||||
User Product is transferred to the recipient in perpetuity or for a
|
||||
fixed term (regardless of how the transaction is characterized), the
|
||||
Corresponding Source conveyed under this section must be accompanied
|
||||
by the Installation Information. But this requirement does not apply
|
||||
if neither you nor any third party retains the ability to install
|
||||
modified object code on the User Product (for example, the work has
|
||||
been installed in ROM).
|
||||
|
||||
The requirement to provide Installation Information does not include a
|
||||
requirement to continue to provide support service, warranty, or updates
|
||||
for a work that has been modified or installed by the recipient, or for
|
||||
the User Product in which it has been modified or installed. Access to a
|
||||
network may be denied when the modification itself materially and
|
||||
adversely affects the operation of the network or violates the rules and
|
||||
protocols for communication across the network.
|
||||
|
||||
Corresponding Source conveyed, and Installation Information provided,
|
||||
in accord with this section must be in a format that is publicly
|
||||
documented (and with an implementation available to the public in
|
||||
source code form), and must require no special password or key for
|
||||
unpacking, reading or copying.
|
||||
|
||||
7. Additional Terms.
|
||||
|
||||
"Additional permissions" are terms that supplement the terms of this
|
||||
License by making exceptions from one or more of its conditions.
|
||||
Additional permissions that are applicable to the entire Program shall
|
||||
be treated as though they were included in this License, to the extent
|
||||
that they are valid under applicable law. If additional permissions
|
||||
apply only to part of the Program, that part may be used separately
|
||||
under those permissions, but the entire Program remains governed by
|
||||
this License without regard to the additional permissions.
|
||||
|
||||
When you convey a copy of a covered work, you may at your option
|
||||
remove any additional permissions from that copy, or from any part of
|
||||
it. (Additional permissions may be written to require their own
|
||||
removal in certain cases when you modify the work.) You may place
|
||||
additional permissions on material, added by you to a covered work,
|
||||
for which you have or can give appropriate copyright permission.
|
||||
|
||||
Notwithstanding any other provision of this License, for material you
|
||||
add to a covered work, you may (if authorized by the copyright holders of
|
||||
that material) supplement the terms of this License with terms:
|
||||
|
||||
a) Disclaiming warranty or limiting liability differently from the
|
||||
terms of sections 15 and 16 of this License; or
|
||||
|
||||
b) Requiring preservation of specified reasonable legal notices or
|
||||
author attributions in that material or in the Appropriate Legal
|
||||
Notices displayed by works containing it; or
|
||||
|
||||
c) Prohibiting misrepresentation of the origin of that material, or
|
||||
requiring that modified versions of such material be marked in
|
||||
reasonable ways as different from the original version; or
|
||||
|
||||
d) Limiting the use for publicity purposes of names of licensors or
|
||||
authors of the material; or
|
||||
|
||||
e) Declining to grant rights under trademark law for use of some
|
||||
trade names, trademarks, or service marks; or
|
||||
|
||||
f) Requiring indemnification of licensors and authors of that
|
||||
material by anyone who conveys the material (or modified versions of
|
||||
it) with contractual assumptions of liability to the recipient, for
|
||||
any liability that these contractual assumptions directly impose on
|
||||
those licensors and authors.
|
||||
|
||||
All other non-permissive additional terms are considered "further
|
||||
restrictions" within the meaning of section 10. If the Program as you
|
||||
received it, or any part of it, contains a notice stating that it is
|
||||
governed by this License along with a term that is a further
|
||||
restriction, you may remove that term. If a license document contains
|
||||
a further restriction but permits relicensing or conveying under this
|
||||
License, you may add to a covered work material governed by the terms
|
||||
of that license document, provided that the further restriction does
|
||||
not survive such relicensing or conveying.
|
||||
|
||||
If you add terms to a covered work in accord with this section, you
|
||||
must place, in the relevant source files, a statement of the
|
||||
additional terms that apply to those files, or a notice indicating
|
||||
where to find the applicable terms.
|
||||
|
||||
Additional terms, permissive or non-permissive, may be stated in the
|
||||
form of a separately written license, or stated as exceptions;
|
||||
the above requirements apply either way.
|
||||
|
||||
8. Termination.
|
||||
|
||||
You may not propagate or modify a covered work except as expressly
|
||||
provided under this License. Any attempt otherwise to propagate or
|
||||
modify it is void, and will automatically terminate your rights under
|
||||
this License (including any patent licenses granted under the third
|
||||
paragraph of section 11).
|
||||
|
||||
However, if you cease all violation of this License, then your
|
||||
license from a particular copyright holder is reinstated (a)
|
||||
provisionally, unless and until the copyright holder explicitly and
|
||||
finally terminates your license, and (b) permanently, if the copyright
|
||||
holder fails to notify you of the violation by some reasonable means
|
||||
prior to 60 days after the cessation.
|
||||
|
||||
Moreover, your license from a particular copyright holder is
|
||||
reinstated permanently if the copyright holder notifies you of the
|
||||
violation by some reasonable means, this is the first time you have
|
||||
received notice of violation of this License (for any work) from that
|
||||
copyright holder, and you cure the violation prior to 30 days after
|
||||
your receipt of the notice.
|
||||
|
||||
Termination of your rights under this section does not terminate the
|
||||
licenses of parties who have received copies or rights from you under
|
||||
this License. If your rights have been terminated and not permanently
|
||||
reinstated, you do not qualify to receive new licenses for the same
|
||||
material under section 10.
|
||||
|
||||
9. Acceptance Not Required for Having Copies.
|
||||
|
||||
You are not required to accept this License in order to receive or
|
||||
run a copy of the Program. Ancillary propagation of a covered work
|
||||
occurring solely as a consequence of using peer-to-peer transmission
|
||||
to receive a copy likewise does not require acceptance. However,
|
||||
nothing other than this License grants you permission to propagate or
|
||||
modify any covered work. These actions infringe copyright if you do
|
||||
not accept this License. Therefore, by modifying or propagating a
|
||||
covered work, you indicate your acceptance of this License to do so.
|
||||
|
||||
10. Automatic Licensing of Downstream Recipients.
|
||||
|
||||
Each time you convey a covered work, the recipient automatically
|
||||
receives a license from the original licensors, to run, modify and
|
||||
propagate that work, subject to this License. You are not responsible
|
||||
for enforcing compliance by third parties with this License.
|
||||
|
||||
An "entity transaction" is a transaction transferring control of an
|
||||
organization, or substantially all assets of one, or subdividing an
|
||||
organization, or merging organizations. If propagation of a covered
|
||||
work results from an entity transaction, each party to that
|
||||
transaction who receives a copy of the work also receives whatever
|
||||
licenses to the work the party's predecessor in interest had or could
|
||||
give under the previous paragraph, plus a right to possession of the
|
||||
Corresponding Source of the work from the predecessor in interest, if
|
||||
the predecessor has it or can get it with reasonable efforts.
|
||||
|
||||
You may not impose any further restrictions on the exercise of the
|
||||
rights granted or affirmed under this License. For example, you may
|
||||
not impose a license fee, royalty, or other charge for exercise of
|
||||
rights granted under this License, and you may not initiate litigation
|
||||
(including a cross-claim or counterclaim in a lawsuit) alleging that
|
||||
any patent claim is infringed by making, using, selling, offering for
|
||||
sale, or importing the Program or any portion of it.
|
||||
|
||||
11. Patents.
|
||||
|
||||
A "contributor" is a copyright holder who authorizes use under this
|
||||
License of the Program or a work on which the Program is based. The
|
||||
work thus licensed is called the contributor's "contributor version".
|
||||
|
||||
A contributor's "essential patent claims" are all patent claims
|
||||
owned or controlled by the contributor, whether already acquired or
|
||||
hereafter acquired, that would be infringed by some manner, permitted
|
||||
by this License, of making, using, or selling its contributor version,
|
||||
but do not include claims that would be infringed only as a
|
||||
consequence of further modification of the contributor version. For
|
||||
purposes of this definition, "control" includes the right to grant
|
||||
patent sublicenses in a manner consistent with the requirements of
|
||||
this License.
|
||||
|
||||
Each contributor grants you a non-exclusive, worldwide, royalty-free
|
||||
patent license under the contributor's essential patent claims, to
|
||||
make, use, sell, offer for sale, import and otherwise run, modify and
|
||||
propagate the contents of its contributor version.
|
||||
|
||||
In the following three paragraphs, a "patent license" is any express
|
||||
agreement or commitment, however denominated, not to enforce a patent
|
||||
(such as an express permission to practice a patent or covenant not to
|
||||
sue for patent infringement). To "grant" such a patent license to a
|
||||
party means to make such an agreement or commitment not to enforce a
|
||||
patent against the party.
|
||||
|
||||
If you convey a covered work, knowingly relying on a patent license,
|
||||
and the Corresponding Source of the work is not available for anyone
|
||||
to copy, free of charge and under the terms of this License, through a
|
||||
publicly available network server or other readily accessible means,
|
||||
then you must either (1) cause the Corresponding Source to be so
|
||||
available, or (2) arrange to deprive yourself of the benefit of the
|
||||
patent license for this particular work, or (3) arrange, in a manner
|
||||
consistent with the requirements of this License, to extend the patent
|
||||
license to downstream recipients. "Knowingly relying" means you have
|
||||
actual knowledge that, but for the patent license, your conveying the
|
||||
covered work in a country, or your recipient's use of the covered work
|
||||
in a country, would infringe one or more identifiable patents in that
|
||||
country that you have reason to believe are valid.
|
||||
|
||||
If, pursuant to or in connection with a single transaction or
|
||||
arrangement, you convey, or propagate by procuring conveyance of, a
|
||||
covered work, and grant a patent license to some of the parties
|
||||
receiving the covered work authorizing them to use, propagate, modify
|
||||
or convey a specific copy of the covered work, then the patent license
|
||||
you grant is automatically extended to all recipients of the covered
|
||||
work and works based on it.
|
||||
|
||||
A patent license is "discriminatory" if it does not include within
|
||||
the scope of its coverage, prohibits the exercise of, or is
|
||||
conditioned on the non-exercise of one or more of the rights that are
|
||||
specifically granted under this License. You may not convey a covered
|
||||
work if you are a party to an arrangement with a third party that is
|
||||
in the business of distributing software, under which you make payment
|
||||
to the third party based on the extent of your activity of conveying
|
||||
the work, and under which the third party grants, to any of the
|
||||
parties who would receive the covered work from you, a discriminatory
|
||||
patent license (a) in connection with copies of the covered work
|
||||
conveyed by you (or copies made from those copies), or (b) primarily
|
||||
for and in connection with specific products or compilations that
|
||||
contain the covered work, unless you entered into that arrangement,
|
||||
or that patent license was granted, prior to 28 March 2007.
|
||||
|
||||
Nothing in this License shall be construed as excluding or limiting
|
||||
any implied license or other defenses to infringement that may
|
||||
otherwise be available to you under applicable patent law.
|
||||
|
||||
12. No Surrender of Others' Freedom.
|
||||
|
||||
If conditions are imposed on you (whether by court order, agreement or
|
||||
otherwise) that contradict the conditions of this License, they do not
|
||||
excuse you from the conditions of this License. If you cannot convey a
|
||||
covered work so as to satisfy simultaneously your obligations under this
|
||||
License and any other pertinent obligations, then as a consequence you may
|
||||
not convey it at all. For example, if you agree to terms that obligate you
|
||||
to collect a royalty for further conveying from those to whom you convey
|
||||
the Program, the only way you could satisfy both those terms and this
|
||||
License would be to refrain entirely from conveying the Program.
|
||||
|
||||
13. Use with the GNU Affero General Public License.
|
||||
|
||||
Notwithstanding any other provision of this License, you have
|
||||
permission to link or combine any covered work with a work licensed
|
||||
under version 3 of the GNU Affero General Public License into a single
|
||||
combined work, and to convey the resulting work. The terms of this
|
||||
License will continue to apply to the part which is the covered work,
|
||||
but the special requirements of the GNU Affero General Public License,
|
||||
section 13, concerning interaction through a network will apply to the
|
||||
combination as such.
|
||||
|
||||
14. Revised Versions of this License.
|
||||
|
||||
The Free Software Foundation may publish revised and/or new versions of
|
||||
the GNU General Public License from time to time. Such new versions will
|
||||
be similar in spirit to the present version, but may differ in detail to
|
||||
address new problems or concerns.
|
||||
|
||||
Each version is given a distinguishing version number. If the
|
||||
Program specifies that a certain numbered version of the GNU General
|
||||
Public License "or any later version" applies to it, you have the
|
||||
option of following the terms and conditions either of that numbered
|
||||
version or of any later version published by the Free Software
|
||||
Foundation. If the Program does not specify a version number of the
|
||||
GNU General Public License, you may choose any version ever published
|
||||
by the Free Software Foundation.
|
||||
|
||||
If the Program specifies that a proxy can decide which future
|
||||
versions of the GNU General Public License can be used, that proxy's
|
||||
public statement of acceptance of a version permanently authorizes you
|
||||
to choose that version for the Program.
|
||||
|
||||
Later license versions may give you additional or different
|
||||
permissions. However, no additional obligations are imposed on any
|
||||
author or copyright holder as a result of your choosing to follow a
|
||||
later version.
|
||||
|
||||
15. Disclaimer of Warranty.
|
||||
|
||||
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
|
||||
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
|
||||
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
|
||||
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
|
||||
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
|
||||
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
|
||||
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
|
||||
|
||||
16. Limitation of Liability.
|
||||
|
||||
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
|
||||
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
|
||||
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
|
||||
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
|
||||
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
|
||||
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
|
||||
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
|
||||
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
|
||||
SUCH DAMAGES.
|
||||
|
||||
17. Interpretation of Sections 15 and 16.
|
||||
|
||||
If the disclaimer of warranty and limitation of liability provided
|
||||
above cannot be given local legal effect according to their terms,
|
||||
reviewing courts shall apply local law that most closely approximates
|
||||
an absolute waiver of all civil liability in connection with the
|
||||
Program, unless a warranty or assumption of liability accompanies a
|
||||
copy of the Program in return for a fee.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
How to Apply These Terms to Your New Programs
|
||||
|
||||
If you develop a new program, and you want it to be of the greatest
|
||||
possible use to the public, the best way to achieve this is to make it
|
||||
free software which everyone can redistribute and change under these terms.
|
||||
|
||||
To do so, attach the following notices to the program. It is safest
|
||||
to attach them to the start of each source file to most effectively
|
||||
state the exclusion of warranty; and each file should have at least
|
||||
the "copyright" line and a pointer to where the full notice is found.
|
||||
|
||||
<one line to give the program's name and a brief idea of what it does.>
|
||||
Copyright (C) <year> <name of author>
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation, either version 3 of the License, or
|
||||
(at your option) any later version.
|
||||
|
||||
This program is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with this program. If not, see <https://www.gnu.org/licenses/>.
|
||||
|
||||
Also add information on how to contact you by electronic and paper mail.
|
||||
|
||||
If the program does terminal interaction, make it output a short
|
||||
notice like this when it starts in an interactive mode:
|
||||
|
||||
<program> Copyright (C) <year> <name of author>
|
||||
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
|
||||
This is free software, and you are welcome to redistribute it
|
||||
under certain conditions; type `show c' for details.
|
||||
|
||||
The hypothetical commands `show w' and `show c' should show the appropriate
|
||||
parts of the General Public License. Of course, your program's commands
|
||||
might be different; for a GUI interface, you would use an "about box".
|
||||
|
||||
You should also get your employer (if you work as a programmer) or school,
|
||||
if any, to sign a "copyright disclaimer" for the program, if necessary.
|
||||
For more information on this, and how to apply and follow the GNU GPL, see
|
||||
<https://www.gnu.org/licenses/>.
|
||||
|
||||
The GNU General Public License does not permit incorporating your program
|
||||
into proprietary programs. If your program is a subroutine library, you
|
||||
may consider it more useful to permit linking proprietary applications with
|
||||
the library. If this is what you want to do, use the GNU Lesser General
|
||||
Public License instead of this License. But first, please read
|
||||
<https://www.gnu.org/licenses/why-not-lgpl.html>.
|
||||
@@ -0,0 +1,279 @@
|
||||
# Official YOLOv7
|
||||
|
||||
Implementation of paper - [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://arxiv.org/abs/2207.02696)
|
||||
|
||||
[](https://paperswithcode.com/sota/real-time-object-detection-on-coco?p=yolov7-trainable-bag-of-freebies-sets-new)
|
||||
[](https://huggingface.co/spaces/akhaliq/yolov7)
|
||||
<a href="https://colab.research.google.com/gist/AlexeyAB/b769f5795e65fdab80086f6cb7940dae/yolov7detection.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
[](https://arxiv.org/abs/2207.02696)
|
||||
|
||||
<div align="center">
|
||||
<a href="./">
|
||||
<img src="./figure/performance.png" width="79%"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
## Web Demo
|
||||
|
||||
- Integrated into [Huggingface Spaces 🤗](https://huggingface.co/spaces/akhaliq/yolov7) using Gradio. Try out the Web Demo [](https://huggingface.co/spaces/akhaliq/yolov7)
|
||||
|
||||
## Performance
|
||||
|
||||
MS COCO
|
||||
|
||||
| Model | Test Size | AP<sup>test</sup> | AP<sub>50</sub><sup>test</sup> | AP<sub>75</sub><sup>test</sup> | batch 1 fps | batch 32 average time |
|
||||
| :-- | :-: | :-: | :-: | :-: | :-: | :-: |
|
||||
| [**YOLOv7**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) | 640 | **51.4%** | **69.7%** | **55.9%** | 161 *fps* | 2.8 *ms* |
|
||||
| [**YOLOv7-X**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) | 640 | **53.1%** | **71.2%** | **57.8%** | 114 *fps* | 4.3 *ms* |
|
||||
| | | | | | | |
|
||||
| [**YOLOv7-W6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) | 1280 | **54.9%** | **72.6%** | **60.1%** | 84 *fps* | 7.6 *ms* |
|
||||
| [**YOLOv7-E6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) | 1280 | **56.0%** | **73.5%** | **61.2%** | 56 *fps* | 12.3 *ms* |
|
||||
| [**YOLOv7-D6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) | 1280 | **56.6%** | **74.0%** | **61.8%** | 44 *fps* | 15.0 *ms* |
|
||||
| [**YOLOv7-E6E**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt) | 1280 | **56.8%** | **74.4%** | **62.1%** | 36 *fps* | 18.7 *ms* |
|
||||
|
||||
## Installation
|
||||
|
||||
Docker environment (recommended)
|
||||
<details><summary> <b>Expand</b> </summary>
|
||||
|
||||
``` shell
|
||||
# create the docker container, you can change the share memory size if you have more.
|
||||
nvidia-docker run --name yolov7 -it -v your_coco_path/:/coco/ -v your_code_path/:/yolov7 --shm-size=64g nvcr.io/nvidia/pytorch:21.08-py3
|
||||
|
||||
# apt install required packages
|
||||
apt update
|
||||
apt install -y zip htop screen libgl1-mesa-glx
|
||||
|
||||
# pip install required packages
|
||||
pip install seaborn thop
|
||||
|
||||
# go to code folder
|
||||
cd /yolov7
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
## Testing
|
||||
|
||||
[`yolov7.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) [`yolov7x.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) [`yolov7-w6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) [`yolov7-e6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) [`yolov7-d6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) [`yolov7-e6e.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt)
|
||||
|
||||
``` shell
|
||||
python test.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.65 --device 0 --weights yolov7.pt --name yolov7_640_val
|
||||
```
|
||||
|
||||
You will get the results:
|
||||
|
||||
```
|
||||
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.51206
|
||||
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.69730
|
||||
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.55521
|
||||
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35247
|
||||
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.55937
|
||||
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.66693
|
||||
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.38453
|
||||
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.63765
|
||||
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.68772
|
||||
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.53766
|
||||
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.73549
|
||||
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.83868
|
||||
```
|
||||
|
||||
To measure accuracy, download [COCO-annotations for Pycocotools](http://images.cocodataset.org/annotations/annotations_trainval2017.zip) to the `./coco/annotations/instances_val2017.json`
|
||||
|
||||
## Training
|
||||
|
||||
Data preparation
|
||||
|
||||
``` shell
|
||||
bash scripts/get_coco.sh
|
||||
```
|
||||
|
||||
* Download MS COCO dataset images ([train](http://images.cocodataset.org/zips/train2017.zip), [val](http://images.cocodataset.org/zips/val2017.zip), [test](http://images.cocodataset.org/zips/test2017.zip)) and [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip). If you have previously used a different version of YOLO, we strongly recommend that you delete `train2017.cache` and `val2017.cache` files, and redownload [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip)
|
||||
|
||||
Single GPU training
|
||||
|
||||
``` shell
|
||||
# train p5 models
|
||||
python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml
|
||||
|
||||
# train p6 models
|
||||
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
|
||||
```
|
||||
|
||||
Multiple GPU training
|
||||
|
||||
``` shell
|
||||
# train p5 models
|
||||
python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml
|
||||
|
||||
# train p6 models
|
||||
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train_aux.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch-size 128 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
|
||||
```
|
||||
|
||||
## Transfer learning
|
||||
|
||||
[`yolov7_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7_training.pt) [`yolov7x_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x_training.pt) [`yolov7-w6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6_training.pt) [`yolov7-e6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6_training.pt) [`yolov7-d6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6_training.pt) [`yolov7-e6e_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e_training.pt)
|
||||
|
||||
Single GPU finetuning for custom dataset
|
||||
|
||||
``` shell
|
||||
# finetune p5 models
|
||||
python train.py --workers 8 --device 0 --batch-size 32 --data data/custom.yaml --img 640 640 --cfg cfg/training/yolov7-custom.yaml --weights 'yolov7_training.pt' --name yolov7-custom --hyp data/hyp.scratch.custom.yaml
|
||||
|
||||
# finetune p6 models
|
||||
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/custom.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6-custom.yaml --weights 'yolov7-w6_training.pt' --name yolov7-w6-custom --hyp data/hyp.scratch.custom.yaml
|
||||
```
|
||||
|
||||
## Re-parameterization
|
||||
|
||||
See [reparameterization.ipynb](tools/reparameterization.ipynb)
|
||||
|
||||
## Inference
|
||||
|
||||
On video:
|
||||
``` shell
|
||||
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source yourvideo.mp4
|
||||
```
|
||||
|
||||
On image:
|
||||
``` shell
|
||||
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/horses.jpg
|
||||
```
|
||||
|
||||
<div align="center">
|
||||
<a href="./">
|
||||
<img src="./figure/horses_prediction.jpg" width="59%"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
|
||||
## Export
|
||||
|
||||
**Pytorch to CoreML (and inference on MacOS/iOS)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7CoreML.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
**Pytorch to ONNX with NMS (and inference)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7onnx.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
```shell
|
||||
python export.py --weights yolov7-tiny.pt --grid --end2end --simplify \
|
||||
--topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640
|
||||
```
|
||||
|
||||
**Pytorch to TensorRT with NMS (and inference)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7trt.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
```shell
|
||||
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
|
||||
python export.py --weights ./yolov7-tiny.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640
|
||||
git clone https://github.com/Linaom1214/tensorrt-python.git
|
||||
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
|
||||
```
|
||||
|
||||
**Pytorch to TensorRT another way** <a href="https://colab.research.google.com/gist/AlexeyAB/fcb47ae544cf284eb24d8ad8e880d45c/yolov7trtlinaom.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <details><summary> <b>Expand</b> </summary>
|
||||
|
||||
|
||||
```shell
|
||||
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
|
||||
python export.py --weights yolov7-tiny.pt --grid --include-nms
|
||||
git clone https://github.com/Linaom1214/tensorrt-python.git
|
||||
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
|
||||
|
||||
# Or use trtexec to convert ONNX to TensorRT engine
|
||||
/usr/src/tensorrt/bin/trtexec --onnx=yolov7-tiny.onnx --saveEngine=yolov7-tiny-nms.trt --fp16
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
Tested with: Python 3.7.13, Pytorch 1.12.0+cu113
|
||||
|
||||
## Pose estimation
|
||||
|
||||
[`code`](https://github.com/WongKinYiu/yolov7/tree/pose) [`yolov7-w6-pose.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6-pose.pt)
|
||||
|
||||
See [keypoint.ipynb](https://github.com/WongKinYiu/yolov7/blob/main/tools/keypoint.ipynb).
|
||||
|
||||
<div align="center">
|
||||
<a href="./">
|
||||
<img src="./figure/pose.png" width="39%"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
|
||||
## Instance segmentation
|
||||
|
||||
[`code`](https://github.com/WongKinYiu/yolov7/tree/mask) [`yolov7-mask.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-mask.pt)
|
||||
|
||||
See [instance.ipynb](https://github.com/WongKinYiu/yolov7/blob/main/tools/instance.ipynb).
|
||||
|
||||
<div align="center">
|
||||
<a href="./">
|
||||
<img src="./figure/mask.png" width="59%"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
## Instance segmentation
|
||||
|
||||
[`code`](https://github.com/WongKinYiu/yolov7/tree/u7/seg) [`yolov7-seg.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-seg.pt)
|
||||
|
||||
YOLOv7 for instance segmentation (YOLOR + YOLOv5 + YOLACT)
|
||||
|
||||
| Model | Test Size | AP<sup>box</sup> | AP<sub>50</sub><sup>box</sup> | AP<sub>75</sub><sup>box</sup> | AP<sup>mask</sup> | AP<sub>50</sub><sup>mask</sup> | AP<sub>75</sub><sup>mask</sup> |
|
||||
| :-- | :-: | :-: | :-: | :-: | :-: | :-: | :-: |
|
||||
| **YOLOv7-seg** | 640 | **51.4%** | **69.4%** | **55.8%** | **41.5%** | **65.5%** | **43.7%** |
|
||||
|
||||
## Anchor free detection head
|
||||
|
||||
[`code`](https://github.com/WongKinYiu/yolov7/tree/u6) [`yolov7-u6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-u6.pt)
|
||||
|
||||
YOLOv7 with decoupled TAL head (YOLOR + YOLOv5 + YOLOv6)
|
||||
|
||||
| Model | Test Size | AP<sup>val</sup> | AP<sub>50</sub><sup>val</sup> | AP<sub>75</sub><sup>val</sup> |
|
||||
| :-- | :-: | :-: | :-: | :-: |
|
||||
| **YOLOv7-u6** | 640 | **52.6%** | **69.7%** | **57.3%** |
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@article{wang2022yolov7,
|
||||
title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},
|
||||
author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
|
||||
journal={arXiv preprint arXiv:2207.02696},
|
||||
year={2022}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
## Teaser
|
||||
|
||||
Yolov7-semantic & YOLOv7-panoptic & YOLOv7-caption
|
||||
|
||||
<div align="center">
|
||||
<a href="./">
|
||||
<img src="./figure/tennis.jpg" width="24%"/>
|
||||
</a>
|
||||
<a href="./">
|
||||
<img src="./figure/tennis_semantic.jpg" width="24%"/>
|
||||
</a>
|
||||
<a href="./">
|
||||
<img src="./figure/tennis_panoptic.png" width="24%"/>
|
||||
</a>
|
||||
<a href="./">
|
||||
<img src="./figure/tennis_caption.png" width="24%"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
|
||||
## Acknowledgements
|
||||
|
||||
<details><summary> <b>Expand</b> </summary>
|
||||
|
||||
* [https://github.com/AlexeyAB/darknet](https://github.com/AlexeyAB/darknet)
|
||||
* [https://github.com/WongKinYiu/yolor](https://github.com/WongKinYiu/yolor)
|
||||
* [https://github.com/WongKinYiu/PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4)
|
||||
* [https://github.com/WongKinYiu/ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4)
|
||||
* [https://github.com/Megvii-BaseDetection/YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)
|
||||
* [https://github.com/ultralytics/yolov3](https://github.com/ultralytics/yolov3)
|
||||
* [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5)
|
||||
* [https://github.com/DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG)
|
||||
* [https://github.com/JUGGHM/OREPA_CVPR2022](https://github.com/JUGGHM/OREPA_CVPR2022)
|
||||
* [https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose](https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose)
|
||||
|
||||
</details>
|
||||
@@ -0,0 +1,49 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# CSP-ResNet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Stem, [128]], # 0-P1/2
|
||||
[-1, 3, ResCSPC, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 2-P3/8
|
||||
[-1, 4, ResCSPC, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 4-P3/8
|
||||
[-1, 6, ResCSPC, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 6-P3/8
|
||||
[-1, 3, ResCSPC, [1024]], # 7
|
||||
]
|
||||
|
||||
# CSP-Res-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 8
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[5, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, ResCSPB, [256]], # 13
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[3, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, ResCSPB, [128]], # 18
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 13], 1, Concat, [1]], # cat
|
||||
[-1, 2, ResCSPB, [256]], # 22
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 8], 1, Concat, [1]], # cat
|
||||
[-1, 2, ResCSPB, [512]], # 26
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[19,23,27], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,49 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# CSP-ResNeXt backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Stem, [128]], # 0-P1/2
|
||||
[-1, 3, ResXCSPC, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 2-P3/8
|
||||
[-1, 4, ResXCSPC, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 4-P3/8
|
||||
[-1, 6, ResXCSPC, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 6-P3/8
|
||||
[-1, 3, ResXCSPC, [1024]], # 7
|
||||
]
|
||||
|
||||
# CSP-ResX-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 8
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[5, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, ResXCSPB, [256]], # 13
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[3, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, ResXCSPB, [128]], # 18
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 13], 1, Concat, [1]], # cat
|
||||
[-1, 2, ResXCSPB, [256]], # 22
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 8], 1, Concat, [1]], # cat
|
||||
[-1, 2, ResXCSPB, [512]], # 26
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[19,23,27], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,52 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# CSP-Darknet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, BottleneckCSPC, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, BottleneckCSPC, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, BottleneckCSPC, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, BottleneckCSPC, [1024]], # 10
|
||||
]
|
||||
|
||||
# CSP-Dark-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 11
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[8, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, BottleneckCSPB, [256]], # 16
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[6, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, BottleneckCSPB, [128]], # 21
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat
|
||||
[-1, 2, BottleneckCSPB, [256]], # 25
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 11], 1, Concat, [1]], # cat
|
||||
[-1, 2, BottleneckCSPB, [512]], # 29
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[22,26,30], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,52 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# CSP-Darknet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, BottleneckCSPC, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, BottleneckCSPC, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, BottleneckCSPC, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, BottleneckCSPC, [1024]], # 10
|
||||
]
|
||||
|
||||
# CSP-Dark-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 11
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[8, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, BottleneckCSPB, [256]], # 16
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[6, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, BottleneckCSPB, [128]], # 21
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat
|
||||
[-1, 2, BottleneckCSPB, [256]], # 25
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 11], 1, Concat, [1]], # cat
|
||||
[-1, 2, BottleneckCSPB, [512]], # 29
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[22,26,30], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,63 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # expand model depth
|
||||
width_multiple: 1.25 # expand layer channels
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# CSP-Darknet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [64, 3, 1]], # 1-P1/2
|
||||
[-1, 1, DownC, [128]], # 2-P2/4
|
||||
[-1, 3, BottleneckCSPA, [128]],
|
||||
[-1, 1, DownC, [256]], # 4-P3/8
|
||||
[-1, 15, BottleneckCSPA, [256]],
|
||||
[-1, 1, DownC, [512]], # 6-P4/16
|
||||
[-1, 15, BottleneckCSPA, [512]],
|
||||
[-1, 1, DownC, [768]], # 8-P5/32
|
||||
[-1, 7, BottleneckCSPA, [768]],
|
||||
[-1, 1, DownC, [1024]], # 10-P6/64
|
||||
[-1, 7, BottleneckCSPA, [1024]], # 11
|
||||
]
|
||||
|
||||
# CSP-Dark-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 12
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-6, 1, Conv, [384, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [384]], # 17
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-13, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [256]], # 22
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-20, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [128]], # 27
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, DownC, [256]],
|
||||
[[-1, 22], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [256]], # 31
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, DownC, [384]],
|
||||
[[-1, 17], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [384]], # 35
|
||||
[-1, 1, Conv, [768, 3, 1]],
|
||||
[-2, 1, DownC, [512]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [512]], # 39
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,63 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # expand model depth
|
||||
width_multiple: 1.25 # expand layer channels
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# CSP-Darknet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [64, 3, 1]], # 1-P1/2
|
||||
[-1, 1, DownC, [128]], # 2-P2/4
|
||||
[-1, 3, BottleneckCSPA, [128]],
|
||||
[-1, 1, DownC, [256]], # 4-P3/8
|
||||
[-1, 7, BottleneckCSPA, [256]],
|
||||
[-1, 1, DownC, [512]], # 6-P4/16
|
||||
[-1, 7, BottleneckCSPA, [512]],
|
||||
[-1, 1, DownC, [768]], # 8-P5/32
|
||||
[-1, 3, BottleneckCSPA, [768]],
|
||||
[-1, 1, DownC, [1024]], # 10-P6/64
|
||||
[-1, 3, BottleneckCSPA, [1024]], # 11
|
||||
]
|
||||
|
||||
# CSP-Dark-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 12
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-6, 1, Conv, [384, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [384]], # 17
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-13, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [256]], # 22
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-20, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [128]], # 27
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, DownC, [256]],
|
||||
[[-1, 22], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [256]], # 31
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, DownC, [384]],
|
||||
[[-1, 17], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [384]], # 35
|
||||
[-1, 1, Conv, [768, 3, 1]],
|
||||
[-2, 1, DownC, [512]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [512]], # 39
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,63 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # expand model depth
|
||||
width_multiple: 1.0 # expand layer channels
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# CSP-Darknet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [64, 3, 1]], # 1-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 2-P2/4
|
||||
[-1, 3, BottleneckCSPA, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 4-P3/8
|
||||
[-1, 7, BottleneckCSPA, [256]],
|
||||
[-1, 1, Conv, [384, 3, 2]], # 6-P4/16
|
||||
[-1, 7, BottleneckCSPA, [384]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 8-P5/32
|
||||
[-1, 3, BottleneckCSPA, [512]],
|
||||
[-1, 1, Conv, [640, 3, 2]], # 10-P6/64
|
||||
[-1, 3, BottleneckCSPA, [640]], # 11
|
||||
]
|
||||
|
||||
# CSP-Dark-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [320]], # 12
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-6, 1, Conv, [256, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [256]], # 17
|
||||
[-1, 1, Conv, [192, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-13, 1, Conv, [192, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [192]], # 22
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-20, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [128]], # 27
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, Conv, [192, 3, 2]],
|
||||
[[-1, 22], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [192]], # 31
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-2, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 17], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [256]], # 35
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, Conv, [320, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [320]], # 39
|
||||
[-1, 1, Conv, [640, 3, 1]],
|
||||
|
||||
[[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,63 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # expand model depth
|
||||
width_multiple: 1.0 # expand layer channels
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# CSP-Darknet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [64, 3, 1]], # 1-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 2-P2/4
|
||||
[-1, 3, BottleneckCSPA, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 4-P3/8
|
||||
[-1, 7, BottleneckCSPA, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 6-P4/16
|
||||
[-1, 7, BottleneckCSPA, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 8-P5/32
|
||||
[-1, 3, BottleneckCSPA, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 10-P6/64
|
||||
[-1, 3, BottleneckCSPA, [1024]], # 11
|
||||
]
|
||||
|
||||
# CSP-Dark-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 12
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-6, 1, Conv, [384, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [384]], # 17
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-13, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [256]], # 22
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[-20, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 3, BottleneckCSPB, [128]], # 27
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 22], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [256]], # 31
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, Conv, [384, 3, 2]],
|
||||
[[-1, 17], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [384]], # 35
|
||||
[-1, 1, Conv, [768, 3, 1]],
|
||||
[-2, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat
|
||||
[-1, 3, BottleneckCSPB, [512]], # 39
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[28,32,36,40], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,51 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3-SPP head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, SPP, [512, [5, 9, 13]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,51 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3 head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, Conv, [512, [1, 1]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,52 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# CSP-Darknet backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, BottleneckCSPC, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, BottleneckCSPC, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, BottleneckCSPC, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, BottleneckCSPC, [1024]], # 10
|
||||
]
|
||||
|
||||
# CSP-Dark-PAN head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 11
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[8, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, BottleneckCSPB, [256]], # 16
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[6, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
[-1, 2, BottleneckCSPB, [128]], # 21
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-2, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat
|
||||
[-1, 2, BottleneckCSPB, [256]], # 25
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-2, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 11], 1, Concat, [1]], # cat
|
||||
[-1, 2, BottleneckCSPB, [512]], # 29
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[22,26,30], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,202 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7-d6 backbone
|
||||
backbone:
|
||||
# [from, number, module, args],
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [96, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, DownC, [192]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [192, 1, 1]], # 14
|
||||
|
||||
[-1, 1, DownC, [384]], # 15-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 27
|
||||
|
||||
[-1, 1, DownC, [768]], # 28-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [768, 1, 1]], # 40
|
||||
|
||||
[-1, 1, DownC, [1152]], # 41-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1152, 1, 1]], # 53
|
||||
|
||||
[-1, 1, DownC, [1536]], # 54-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1536, 1, 1]], # 66
|
||||
]
|
||||
|
||||
# yolov7-d6 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [768]], # 67
|
||||
|
||||
[-1, 1, Conv, [576, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[53, 1, Conv, [576, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [576, 1, 1]], # 83
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[40, 1, Conv, [384, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 99
|
||||
|
||||
[-1, 1, Conv, [192, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[27, 1, Conv, [192, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [192, 1, 1]], # 115
|
||||
|
||||
[-1, 1, DownC, [384]],
|
||||
[[-1, 99], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 129
|
||||
|
||||
[-1, 1, DownC, [576]],
|
||||
[[-1, 83], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [576, 1, 1]], # 143
|
||||
|
||||
[-1, 1, DownC, [768]],
|
||||
[[-1, 67], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [768, 1, 1]], # 157
|
||||
|
||||
[115, 1, Conv, [384, 3, 1]],
|
||||
[129, 1, Conv, [768, 3, 1]],
|
||||
[143, 1, Conv, [1152, 3, 1]],
|
||||
[157, 1, Conv, [1536, 3, 1]],
|
||||
|
||||
[[158,159,160,161], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,180 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7-e6 backbone
|
||||
backbone:
|
||||
# [from, number, module, args],
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [80, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, DownC, [160]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 12
|
||||
|
||||
[-1, 1, DownC, [320]], # 13-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 23
|
||||
|
||||
[-1, 1, DownC, [640]], # 24-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 34
|
||||
|
||||
[-1, 1, DownC, [960]], # 35-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [960, 1, 1]], # 45
|
||||
|
||||
[-1, 1, DownC, [1280]], # 46-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 56
|
||||
]
|
||||
|
||||
# yolov7-e6 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [640]], # 57
|
||||
|
||||
[-1, 1, Conv, [480, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[45, 1, Conv, [480, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 71
|
||||
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[34, 1, Conv, [320, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 85
|
||||
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[23, 1, Conv, [160, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 99
|
||||
|
||||
[-1, 1, DownC, [320]],
|
||||
[[-1, 85], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 111
|
||||
|
||||
[-1, 1, DownC, [480]],
|
||||
[[-1, 71], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 123
|
||||
|
||||
[-1, 1, DownC, [640]],
|
||||
[[-1, 57], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 135
|
||||
|
||||
[99, 1, Conv, [320, 3, 1]],
|
||||
[111, 1, Conv, [640, 3, 1]],
|
||||
[123, 1, Conv, [960, 3, 1]],
|
||||
[135, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[[136,137,138,139], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,301 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7-e6e backbone
|
||||
backbone:
|
||||
# [from, number, module, args],
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [80, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, DownC, [160]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 12
|
||||
[-11, 1, Conv, [64, 1, 1]],
|
||||
[-12, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 22
|
||||
[[-1, -11], 1, Shortcut, [1]], # 23
|
||||
|
||||
[-1, 1, DownC, [320]], # 24-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 34
|
||||
[-11, 1, Conv, [128, 1, 1]],
|
||||
[-12, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 44
|
||||
[[-1, -11], 1, Shortcut, [1]], # 45
|
||||
|
||||
[-1, 1, DownC, [640]], # 46-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 56
|
||||
[-11, 1, Conv, [256, 1, 1]],
|
||||
[-12, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 66
|
||||
[[-1, -11], 1, Shortcut, [1]], # 67
|
||||
|
||||
[-1, 1, DownC, [960]], # 68-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [960, 1, 1]], # 78
|
||||
[-11, 1, Conv, [384, 1, 1]],
|
||||
[-12, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [960, 1, 1]], # 88
|
||||
[[-1, -11], 1, Shortcut, [1]], # 89
|
||||
|
||||
[-1, 1, DownC, [1280]], # 90-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 100
|
||||
[-11, 1, Conv, [512, 1, 1]],
|
||||
[-12, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 110
|
||||
[[-1, -11], 1, Shortcut, [1]], # 111
|
||||
]
|
||||
|
||||
# yolov7-e6e head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [640]], # 112
|
||||
|
||||
[-1, 1, Conv, [480, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[89, 1, Conv, [480, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 126
|
||||
[-11, 1, Conv, [384, 1, 1]],
|
||||
[-12, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 136
|
||||
[[-1, -11], 1, Shortcut, [1]], # 137
|
||||
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[67, 1, Conv, [320, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 151
|
||||
[-11, 1, Conv, [256, 1, 1]],
|
||||
[-12, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 161
|
||||
[[-1, -11], 1, Shortcut, [1]], # 162
|
||||
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[45, 1, Conv, [160, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 176
|
||||
[-11, 1, Conv, [128, 1, 1]],
|
||||
[-12, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 186
|
||||
[[-1, -11], 1, Shortcut, [1]], # 187
|
||||
|
||||
[-1, 1, DownC, [320]],
|
||||
[[-1, 162], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 199
|
||||
[-11, 1, Conv, [256, 1, 1]],
|
||||
[-12, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 209
|
||||
[[-1, -11], 1, Shortcut, [1]], # 210
|
||||
|
||||
[-1, 1, DownC, [480]],
|
||||
[[-1, 137], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 222
|
||||
[-11, 1, Conv, [384, 1, 1]],
|
||||
[-12, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 232
|
||||
[[-1, -11], 1, Shortcut, [1]], # 233
|
||||
|
||||
[-1, 1, DownC, [640]],
|
||||
[[-1, 112], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 245
|
||||
[-11, 1, Conv, [512, 1, 1]],
|
||||
[-12, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 255
|
||||
[[-1, -11], 1, Shortcut, [1]], # 256
|
||||
|
||||
[187, 1, Conv, [320, 3, 1]],
|
||||
[210, 1, Conv, [640, 3, 1]],
|
||||
[233, 1, Conv, [960, 3, 1]],
|
||||
[256, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[[257,258,259,260], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,112 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv7-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 2]], # 0-P1/2
|
||||
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P2/4
|
||||
|
||||
[-1, 1, Conv, [32, 1, 1]],
|
||||
[-2, 1, Conv, [32, 1, 1]],
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [64, 1, 1]], # 7
|
||||
|
||||
[-1, 1, MP, []], # 8-P3/8
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 14
|
||||
|
||||
[-1, 1, MP, []], # 15-P4/16
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 21
|
||||
|
||||
[-1, 1, MP, []], # 22-P5/32
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 28
|
||||
]
|
||||
|
||||
# YOLOv7-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, SP, [5]],
|
||||
[-2, 1, SP, [9]],
|
||||
[-3, 1, SP, [13]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[[-1, -7], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 37
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[21, 1, Conv, [128, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 47
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[14, 1, Conv, [64, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [32, 1, 1]],
|
||||
[-2, 1, Conv, [32, 1, 1]],
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [64, 1, 1]], # 57
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, 47], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 65
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 37], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 73
|
||||
|
||||
[57, 1, Conv, [128, 3, 1]],
|
||||
[65, 1, Conv, [256, 3, 1]],
|
||||
[73, 1, Conv, [512, 3, 1]],
|
||||
|
||||
[[74,75,76], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,112 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# yolov7-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
|
||||
[[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 0-P1/2
|
||||
|
||||
[-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 1-P2/4
|
||||
|
||||
[-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 7
|
||||
|
||||
[-1, 1, MP, []], # 8-P3/8
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 14
|
||||
|
||||
[-1, 1, MP, []], # 15-P4/16
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 21
|
||||
|
||||
[-1, 1, MP, []], # 22-P5/32
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 28
|
||||
]
|
||||
|
||||
# yolov7-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, SP, [5]],
|
||||
[-2, 1, SP, [9]],
|
||||
[-3, 1, SP, [13]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -7], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 37
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 47
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 57
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, 47], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 65
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, 37], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 73
|
||||
|
||||
[57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
|
||||
[[74,75,76], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,158 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7-w6 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [64, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 10
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]], # 11-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 19
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]], # 20-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 28
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]], # 29-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [768, 1, 1]], # 37
|
||||
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 38-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1024, 1, 1]], # 46
|
||||
]
|
||||
|
||||
# yolov7-w6 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 47
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[37, 1, Conv, [384, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 59
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[28, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 71
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[19, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 83
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 71], 1, Concat, [1]], # cat
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 93
|
||||
|
||||
[-1, 1, Conv, [384, 3, 2]],
|
||||
[[-1, 59], 1, Concat, [1]], # cat
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 103
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 47], 1, Concat, [1]], # cat
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 113
|
||||
|
||||
[83, 1, Conv, [256, 3, 1]],
|
||||
[93, 1, Conv, [512, 3, 1]],
|
||||
[103, 1, Conv, [768, 3, 1]],
|
||||
[113, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[[114,115,116,117], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,140 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# yolov7 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 11
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-3, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 16-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 24
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-3, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 29-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1024, 1, 1]], # 37
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-3, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 42-P5/32
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1024, 1, 1]], # 50
|
||||
]
|
||||
|
||||
# yolov7 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 51
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[37, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 63
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[24, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 75
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-3, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, -3, 63], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 88
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-3, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, -3, 51], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 101
|
||||
|
||||
[75, 1, RepConv, [256, 3, 1]],
|
||||
[88, 1, RepConv, [512, 3, 1]],
|
||||
[101, 1, RepConv, [1024, 3, 1]],
|
||||
|
||||
[[102,103,104], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,156 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# yolov7x backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [40, 3, 1]], # 0
|
||||
|
||||
[-1, 1, Conv, [80, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Conv, [80, 3, 1]],
|
||||
|
||||
[-1, 1, Conv, [160, 3, 2]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 13
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-3, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, Conv, [160, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 18-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 28
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-3, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, Conv, [320, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 33-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 43
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [640, 1, 1]],
|
||||
[-3, 1, Conv, [640, 1, 1]],
|
||||
[-1, 1, Conv, [640, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 48-P5/32
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 58
|
||||
]
|
||||
|
||||
# yolov7x head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [640]], # 59
|
||||
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[43, 1, Conv, [320, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 73
|
||||
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[28, 1, Conv, [160, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 87
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-3, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, Conv, [160, 3, 2]],
|
||||
[[-1, -3, 73], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 102
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-3, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, Conv, [320, 3, 2]],
|
||||
[[-1, -3, 59], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 117
|
||||
|
||||
[87, 1, Conv, [320, 3, 1]],
|
||||
[102, 1, Conv, [640, 3, 1]],
|
||||
[117, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[[118,119,120], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,207 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7 backbone
|
||||
backbone:
|
||||
# [from, number, module, args],
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [96, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, DownC, [192]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [192, 1, 1]], # 14
|
||||
|
||||
[-1, 1, DownC, [384]], # 15-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 27
|
||||
|
||||
[-1, 1, DownC, [768]], # 28-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [768, 1, 1]], # 40
|
||||
|
||||
[-1, 1, DownC, [1152]], # 41-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1152, 1, 1]], # 53
|
||||
|
||||
[-1, 1, DownC, [1536]], # 54-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1536, 1, 1]], # 66
|
||||
]
|
||||
|
||||
# yolov7 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [768]], # 67
|
||||
|
||||
[-1, 1, Conv, [576, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[53, 1, Conv, [576, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [576, 1, 1]], # 83
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[40, 1, Conv, [384, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 99
|
||||
|
||||
[-1, 1, Conv, [192, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[27, 1, Conv, [192, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [192, 1, 1]], # 115
|
||||
|
||||
[-1, 1, DownC, [384]],
|
||||
[[-1, 99], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 129
|
||||
|
||||
[-1, 1, DownC, [576]],
|
||||
[[-1, 83], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [576, 1, 1]], # 143
|
||||
|
||||
[-1, 1, DownC, [768]],
|
||||
[[-1, 67], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [768, 1, 1]], # 157
|
||||
|
||||
[115, 1, Conv, [384, 3, 1]],
|
||||
[129, 1, Conv, [768, 3, 1]],
|
||||
[143, 1, Conv, [1152, 3, 1]],
|
||||
[157, 1, Conv, [1536, 3, 1]],
|
||||
|
||||
[115, 1, Conv, [384, 3, 1]],
|
||||
[99, 1, Conv, [768, 3, 1]],
|
||||
[83, 1, Conv, [1152, 3, 1]],
|
||||
[67, 1, Conv, [1536, 3, 1]],
|
||||
|
||||
[[158,159,160,161,162,163,164,165], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,185 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7 backbone
|
||||
backbone:
|
||||
# [from, number, module, args],
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [80, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, DownC, [160]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 12
|
||||
|
||||
[-1, 1, DownC, [320]], # 13-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 23
|
||||
|
||||
[-1, 1, DownC, [640]], # 24-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 34
|
||||
|
||||
[-1, 1, DownC, [960]], # 35-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [960, 1, 1]], # 45
|
||||
|
||||
[-1, 1, DownC, [1280]], # 46-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 56
|
||||
]
|
||||
|
||||
# yolov7 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [640]], # 57
|
||||
|
||||
[-1, 1, Conv, [480, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[45, 1, Conv, [480, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 71
|
||||
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[34, 1, Conv, [320, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 85
|
||||
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[23, 1, Conv, [160, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 99
|
||||
|
||||
[-1, 1, DownC, [320]],
|
||||
[[-1, 85], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 111
|
||||
|
||||
[-1, 1, DownC, [480]],
|
||||
[[-1, 71], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 123
|
||||
|
||||
[-1, 1, DownC, [640]],
|
||||
[[-1, 57], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 135
|
||||
|
||||
[99, 1, Conv, [320, 3, 1]],
|
||||
[111, 1, Conv, [640, 3, 1]],
|
||||
[123, 1, Conv, [960, 3, 1]],
|
||||
[135, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[99, 1, Conv, [320, 3, 1]],
|
||||
[85, 1, Conv, [640, 3, 1]],
|
||||
[71, 1, Conv, [960, 3, 1]],
|
||||
[57, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[[136,137,138,139,140,141,142,143], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,306 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7 backbone
|
||||
backbone:
|
||||
# [from, number, module, args],
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [80, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, DownC, [160]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 12
|
||||
[-11, 1, Conv, [64, 1, 1]],
|
||||
[-12, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 22
|
||||
[[-1, -11], 1, Shortcut, [1]], # 23
|
||||
|
||||
[-1, 1, DownC, [320]], # 24-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 34
|
||||
[-11, 1, Conv, [128, 1, 1]],
|
||||
[-12, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 44
|
||||
[[-1, -11], 1, Shortcut, [1]], # 45
|
||||
|
||||
[-1, 1, DownC, [640]], # 46-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 56
|
||||
[-11, 1, Conv, [256, 1, 1]],
|
||||
[-12, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 66
|
||||
[[-1, -11], 1, Shortcut, [1]], # 67
|
||||
|
||||
[-1, 1, DownC, [960]], # 68-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [960, 1, 1]], # 78
|
||||
[-11, 1, Conv, [384, 1, 1]],
|
||||
[-12, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [960, 1, 1]], # 88
|
||||
[[-1, -11], 1, Shortcut, [1]], # 89
|
||||
|
||||
[-1, 1, DownC, [1280]], # 90-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 100
|
||||
[-11, 1, Conv, [512, 1, 1]],
|
||||
[-12, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 110
|
||||
[[-1, -11], 1, Shortcut, [1]], # 111
|
||||
]
|
||||
|
||||
# yolov7 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [640]], # 112
|
||||
|
||||
[-1, 1, Conv, [480, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[89, 1, Conv, [480, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 126
|
||||
[-11, 1, Conv, [384, 1, 1]],
|
||||
[-12, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 136
|
||||
[[-1, -11], 1, Shortcut, [1]], # 137
|
||||
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[67, 1, Conv, [320, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 151
|
||||
[-11, 1, Conv, [256, 1, 1]],
|
||||
[-12, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 161
|
||||
[[-1, -11], 1, Shortcut, [1]], # 162
|
||||
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[45, 1, Conv, [160, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 176
|
||||
[-11, 1, Conv, [128, 1, 1]],
|
||||
[-12, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 186
|
||||
[[-1, -11], 1, Shortcut, [1]], # 187
|
||||
|
||||
[-1, 1, DownC, [320]],
|
||||
[[-1, 162], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 199
|
||||
[-11, 1, Conv, [256, 1, 1]],
|
||||
[-12, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 209
|
||||
[[-1, -11], 1, Shortcut, [1]], # 210
|
||||
|
||||
[-1, 1, DownC, [480]],
|
||||
[[-1, 137], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 222
|
||||
[-11, 1, Conv, [384, 1, 1]],
|
||||
[-12, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [480, 1, 1]], # 232
|
||||
[[-1, -11], 1, Shortcut, [1]], # 233
|
||||
|
||||
[-1, 1, DownC, [640]],
|
||||
[[-1, 112], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 245
|
||||
[-11, 1, Conv, [512, 1, 1]],
|
||||
[-12, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 255
|
||||
[[-1, -11], 1, Shortcut, [1]], # 256
|
||||
|
||||
[187, 1, Conv, [320, 3, 1]],
|
||||
[210, 1, Conv, [640, 3, 1]],
|
||||
[233, 1, Conv, [960, 3, 1]],
|
||||
[256, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[186, 1, Conv, [320, 3, 1]],
|
||||
[161, 1, Conv, [640, 3, 1]],
|
||||
[136, 1, Conv, [960, 3, 1]],
|
||||
[112, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[[257,258,259,260,261,262,263,264], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,112 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# yolov7-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
|
||||
[[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 0-P1/2
|
||||
|
||||
[-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 1-P2/4
|
||||
|
||||
[-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 7
|
||||
|
||||
[-1, 1, MP, []], # 8-P3/8
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 14
|
||||
|
||||
[-1, 1, MP, []], # 15-P4/16
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 21
|
||||
|
||||
[-1, 1, MP, []], # 22-P5/32
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 28
|
||||
]
|
||||
|
||||
# yolov7-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, SP, [5]],
|
||||
[-2, 1, SP, [9]],
|
||||
[-3, 1, SP, [13]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -7], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 37
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 47
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 57
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, 47], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 65
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, 37], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[[-1, -2, -3, -4], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 73
|
||||
|
||||
[57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
[73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
|
||||
|
||||
[[74,75,76], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,163 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# yolov7 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, ReOrg, []], # 0
|
||||
[-1, 1, Conv, [64, 3, 1]], # 1-P1/2
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]], # 2-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 10
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]], # 11-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 19
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]], # 20-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 28
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]], # 29-P5/32
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[-1, 1, Conv, [384, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [768, 1, 1]], # 37
|
||||
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 38-P6/64
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1024, 1, 1]], # 46
|
||||
]
|
||||
|
||||
# yolov7 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 47
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[37, 1, Conv, [384, 1, 1]], # route backbone P5
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 59
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[28, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 71
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[19, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 83
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 71], 1, Concat, [1]], # cat
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 93
|
||||
|
||||
[-1, 1, Conv, [384, 3, 2]],
|
||||
[[-1, 59], 1, Concat, [1]], # cat
|
||||
|
||||
[-1, 1, Conv, [384, 1, 1]],
|
||||
[-2, 1, Conv, [384, 1, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[-1, 1, Conv, [192, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [384, 1, 1]], # 103
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 47], 1, Concat, [1]], # cat
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 113
|
||||
|
||||
[83, 1, Conv, [256, 3, 1]],
|
||||
[93, 1, Conv, [512, 3, 1]],
|
||||
[103, 1, Conv, [768, 3, 1]],
|
||||
[113, 1, Conv, [1024, 3, 1]],
|
||||
|
||||
[83, 1, Conv, [320, 3, 1]],
|
||||
[71, 1, Conv, [640, 3, 1]],
|
||||
[59, 1, Conv, [960, 3, 1]],
|
||||
[47, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[[114,115,116,117,118,119,120,121], 1, IAuxDetect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,140 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# yolov7 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 11
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-3, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 16-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 24
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-3, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 29-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1024, 1, 1]], # 37
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-3, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 42-P5/32
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1024, 1, 1]], # 50
|
||||
]
|
||||
|
||||
# yolov7 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [512]], # 51
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[37, 1, Conv, [256, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 63
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[24, 1, Conv, [128, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [128, 1, 1]], # 75
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-3, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, -3, 63], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [256, 1, 1]], # 88
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-3, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, -3, 51], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [512, 1, 1]], # 101
|
||||
|
||||
[75, 1, RepConv, [256, 3, 1]],
|
||||
[88, 1, RepConv, [512, 3, 1]],
|
||||
[101, 1, RepConv, [1024, 3, 1]],
|
||||
|
||||
[[102,103,104], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,156 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [12,16, 19,36, 40,28] # P3/8
|
||||
- [36,75, 76,55, 72,146] # P4/16
|
||||
- [142,110, 192,243, 459,401] # P5/32
|
||||
|
||||
# yolov7 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [40, 3, 1]], # 0
|
||||
|
||||
[-1, 1, Conv, [80, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Conv, [80, 3, 1]],
|
||||
|
||||
[-1, 1, Conv, [160, 3, 2]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 1, 1]],
|
||||
[-2, 1, Conv, [64, 1, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 13
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-3, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, Conv, [160, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 18-P3/8
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 28
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-3, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, Conv, [320, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 33-P4/16
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 43
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [640, 1, 1]],
|
||||
[-3, 1, Conv, [640, 1, 1]],
|
||||
[-1, 1, Conv, [640, 3, 2]],
|
||||
[[-1, -3], 1, Concat, [1]], # 48-P5/32
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [1280, 1, 1]], # 58
|
||||
]
|
||||
|
||||
# yolov7 head
|
||||
head:
|
||||
[[-1, 1, SPPCSPC, [640]], # 59
|
||||
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[43, 1, Conv, [320, 1, 1]], # route backbone P4
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 73
|
||||
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[28, 1, Conv, [160, 1, 1]], # route backbone P3
|
||||
[[-1, -2], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [160, 1, 1]], # 87
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [160, 1, 1]],
|
||||
[-3, 1, Conv, [160, 1, 1]],
|
||||
[-1, 1, Conv, [160, 3, 2]],
|
||||
[[-1, -3, 73], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [320, 1, 1]], # 102
|
||||
|
||||
[-1, 1, MP, []],
|
||||
[-1, 1, Conv, [320, 1, 1]],
|
||||
[-3, 1, Conv, [320, 1, 1]],
|
||||
[-1, 1, Conv, [320, 3, 2]],
|
||||
[[-1, -3, 59], 1, Concat, [1]],
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-2, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[[-1, -3, -5, -7, -8], 1, Concat, [1]],
|
||||
[-1, 1, Conv, [640, 1, 1]], # 117
|
||||
|
||||
[87, 1, Conv, [320, 3, 1]],
|
||||
[102, 1, Conv, [640, 3, 1]],
|
||||
[117, 1, Conv, [1280, 3, 1]],
|
||||
|
||||
[[118,119,120], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,164 @@
|
||||
# YOLOv7 on Triton Inference Server
|
||||
|
||||
Instructions to deploy YOLOv7 as TensorRT engine to [Triton Inference Server](https://github.com/NVIDIA/triton-inference-server).
|
||||
|
||||
Triton Inference Server takes care of model deployment with many out-of-the-box benefits, like a GRPC and HTTP interface, automatic scheduling on multiple GPUs, shared memory (even on GPU), dynamic server-side batching, health metrics and memory resource management.
|
||||
|
||||
There are no additional dependencies needed to run this deployment, except a working docker daemon with GPU support.
|
||||
|
||||
## Export TensorRT
|
||||
|
||||
See https://github.com/WongKinYiu/yolov7#export for more info.
|
||||
|
||||
```bash
|
||||
#install onnx-simplifier not listed in general yolov7 requirements.txt
|
||||
pip3 install onnx-simplifier
|
||||
|
||||
# Pytorch Yolov7 -> ONNX with grid, EfficientNMS plugin and dynamic batch size
|
||||
python export.py --weights ./yolov7.pt --grid --end2end --dynamic-batch --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640
|
||||
# ONNX -> TensorRT with trtexec and docker
|
||||
docker run -it --rm --gpus=all nvcr.io/nvidia/tensorrt:22.06-py3
|
||||
# Copy onnx -> container: docker cp yolov7.onnx <container-id>:/workspace/
|
||||
# Export with FP16 precision, min batch 1, opt batch 8 and max batch 8
|
||||
./tensorrt/bin/trtexec --onnx=yolov7.onnx --minShapes=images:1x3x640x640 --optShapes=images:8x3x640x640 --maxShapes=images:8x3x640x640 --fp16 --workspace=4096 --saveEngine=yolov7-fp16-1x8x8.engine --timingCacheFile=timing.cache
|
||||
# Test engine
|
||||
./tensorrt/bin/trtexec --loadEngine=yolov7-fp16-1x8x8.engine
|
||||
# Copy engine -> host: docker cp <container-id>:/workspace/yolov7-fp16-1x8x8.engine .
|
||||
```
|
||||
|
||||
Example output of test with RTX 3090.
|
||||
|
||||
```
|
||||
[I] === Performance summary ===
|
||||
[I] Throughput: 73.4985 qps
|
||||
[I] Latency: min = 14.8578 ms, max = 15.8344 ms, mean = 15.07 ms, median = 15.0422 ms, percentile(99%) = 15.7443 ms
|
||||
[I] End-to-End Host Latency: min = 25.8715 ms, max = 28.4102 ms, mean = 26.672 ms, median = 26.6082 ms, percentile(99%) = 27.8314 ms
|
||||
[I] Enqueue Time: min = 0.793701 ms, max = 1.47144 ms, mean = 1.2008 ms, median = 1.28644 ms, percentile(99%) = 1.38965 ms
|
||||
[I] H2D Latency: min = 1.50073 ms, max = 1.52454 ms, mean = 1.51225 ms, median = 1.51404 ms, percentile(99%) = 1.51941 ms
|
||||
[I] GPU Compute Time: min = 13.3386 ms, max = 14.3186 ms, mean = 13.5448 ms, median = 13.5178 ms, percentile(99%) = 14.2151 ms
|
||||
[I] D2H Latency: min = 0.00878906 ms, max = 0.0172729 ms, mean = 0.0128844 ms, median = 0.0125732 ms, percentile(99%) = 0.0166016 ms
|
||||
[I] Total Host Walltime: 3.04768 s
|
||||
[I] Total GPU Compute Time: 3.03404 s
|
||||
[I] Explanations of the performance metrics are printed in the verbose logs.
|
||||
```
|
||||
Note: 73.5 qps x batch 8 = 588 fps @ ~15ms latency.
|
||||
|
||||
## Model Repository
|
||||
|
||||
See [Triton Model Repository Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_repository.md#model-repository) for more info.
|
||||
|
||||
```bash
|
||||
# Create folder structure
|
||||
mkdir -p triton-deploy/models/yolov7/1/
|
||||
touch triton-deploy/models/yolov7/config.pbtxt
|
||||
# Place model
|
||||
mv yolov7-fp16-1x8x8.engine triton-deploy/models/yolov7/1/model.plan
|
||||
```
|
||||
|
||||
## Model Configuration
|
||||
|
||||
See [Triton Model Configuration Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#model-configuration) for more info.
|
||||
|
||||
Minimal configuration for `triton-deploy/models/yolov7/config.pbtxt`:
|
||||
|
||||
```
|
||||
name: "yolov7"
|
||||
platform: "tensorrt_plan"
|
||||
max_batch_size: 8
|
||||
dynamic_batching { }
|
||||
```
|
||||
|
||||
Example repository:
|
||||
|
||||
```bash
|
||||
$ tree triton-deploy/
|
||||
triton-deploy/
|
||||
└── models
|
||||
└── yolov7
|
||||
├── 1
|
||||
│ └── model.plan
|
||||
└── config.pbtxt
|
||||
|
||||
3 directories, 2 files
|
||||
```
|
||||
|
||||
## Start Triton Inference Server
|
||||
|
||||
```
|
||||
docker run --gpus all --rm --ipc=host --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 -p8000:8000 -p8001:8001 -p8002:8002 -v$(pwd)/triton-deploy/models:/models nvcr.io/nvidia/tritonserver:22.06-py3 tritonserver --model-repository=/models --strict-model-config=false --log-verbose 1
|
||||
```
|
||||
|
||||
In the log you should see:
|
||||
|
||||
```
|
||||
+--------+---------+--------+
|
||||
| Model | Version | Status |
|
||||
+--------+---------+--------+
|
||||
| yolov7 | 1 | READY |
|
||||
+--------+---------+--------+
|
||||
```
|
||||
|
||||
## Performance with Model Analyzer
|
||||
|
||||
See [Triton Model Analyzer Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_analyzer.md#model-analyzer) for more info.
|
||||
|
||||
Performance numbers @ RTX 3090 + AMD Ryzen 9 5950X
|
||||
|
||||
Example test for 16 concurrent clients using shared memory, each with batch size 1 requests:
|
||||
|
||||
```bash
|
||||
docker run -it --ipc=host --net=host nvcr.io/nvidia/tritonserver:22.06-py3-sdk /bin/bash
|
||||
|
||||
./install/bin/perf_analyzer -m yolov7 -u 127.0.0.1:8001 -i grpc --shared-memory system --concurrency-range 16
|
||||
|
||||
# Result (truncated)
|
||||
Concurrency: 16, throughput: 590.119 infer/sec, latency 27080 usec
|
||||
```
|
||||
|
||||
Throughput for 16 clients with batch size 1 is the same as for a single thread running the engine at 16 batch size locally thanks to Triton [Dynamic Batching Strategy](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#dynamic-batcher). Result without dynamic batching (disable in model configuration) considerably worse:
|
||||
|
||||
```bash
|
||||
# Result (truncated)
|
||||
Concurrency: 16, throughput: 335.587 infer/sec, latency 47616 usec
|
||||
```
|
||||
|
||||
## How to run model in your code
|
||||
|
||||
Example client can be found in client.py. It can run dummy input, images and videos.
|
||||
|
||||
```bash
|
||||
pip3 install tritonclient[all] opencv-python
|
||||
python3 client.py image data/dog.jpg
|
||||
```
|
||||
|
||||
|
||||
|
||||
```
|
||||
$ python3 client.py --help
|
||||
usage: client.py [-h] [-m MODEL] [--width WIDTH] [--height HEIGHT] [-u URL] [-o OUT] [-f FPS] [-i] [-v] [-t CLIENT_TIMEOUT] [-s] [-r ROOT_CERTIFICATES] [-p PRIVATE_KEY] [-x CERTIFICATE_CHAIN] {dummy,image,video} [input]
|
||||
|
||||
positional arguments:
|
||||
{dummy,image,video} Run mode. 'dummy' will send an emtpy buffer to the server to test if inference works. 'image' will process an image. 'video' will process a video.
|
||||
input Input file to load from in image or video mode
|
||||
|
||||
optional arguments:
|
||||
-h, --help show this help message and exit
|
||||
-m MODEL, --model MODEL
|
||||
Inference model name, default yolov7
|
||||
--width WIDTH Inference model input width, default 640
|
||||
--height HEIGHT Inference model input height, default 640
|
||||
-u URL, --url URL Inference server URL, default localhost:8001
|
||||
-o OUT, --out OUT Write output into file instead of displaying it
|
||||
-f FPS, --fps FPS Video output fps, default 24.0 FPS
|
||||
-i, --model-info Print model status, configuration and statistics
|
||||
-v, --verbose Enable verbose client output
|
||||
-t CLIENT_TIMEOUT, --client-timeout CLIENT_TIMEOUT
|
||||
Client timeout in seconds, default no timeout
|
||||
-s, --ssl Enable SSL encrypted channel to the server
|
||||
-r ROOT_CERTIFICATES, --root-certificates ROOT_CERTIFICATES
|
||||
File holding PEM-encoded root certificates, default none
|
||||
-p PRIVATE_KEY, --private-key PRIVATE_KEY
|
||||
File holding PEM-encoded private key, default is none
|
||||
-x CERTIFICATE_CHAIN, --certificate-chain CERTIFICATE_CHAIN
|
||||
File holding PEM-encoded certicate chain default is none
|
||||
```
|
||||
@@ -0,0 +1,33 @@
|
||||
class BoundingBox:
|
||||
def __init__(self, classID, confidence, x1, x2, y1, y2, image_width, image_height):
|
||||
self.classID = classID
|
||||
self.confidence = confidence
|
||||
self.x1 = x1
|
||||
self.x2 = x2
|
||||
self.y1 = y1
|
||||
self.y2 = y2
|
||||
self.u1 = x1 / image_width
|
||||
self.u2 = x2 / image_width
|
||||
self.v1 = y1 / image_height
|
||||
self.v2 = y2 / image_height
|
||||
|
||||
def box(self):
|
||||
return (self.x1, self.y1, self.x2, self.y2)
|
||||
|
||||
def width(self):
|
||||
return self.x2 - self.x1
|
||||
|
||||
def height(self):
|
||||
return self.y2 - self.y1
|
||||
|
||||
def center_absolute(self):
|
||||
return (0.5 * (self.x1 + self.x2), 0.5 * (self.y1 + self.y2))
|
||||
|
||||
def center_normalized(self):
|
||||
return (0.5 * (self.u1 + self.u2), 0.5 * (self.v1 + self.v2))
|
||||
|
||||
def size_absolute(self):
|
||||
return (self.x2 - self.x1, self.y2 - self.y1)
|
||||
|
||||
def size_normalized(self):
|
||||
return (self.u2 - self.u1, self.v2 - self.v1)
|
||||
@@ -0,0 +1,334 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
import argparse
|
||||
import numpy as np
|
||||
import sys
|
||||
import cv2
|
||||
|
||||
import tritonclient.grpc as grpcclient
|
||||
from tritonclient.utils import InferenceServerException
|
||||
|
||||
from processing import preprocess, postprocess
|
||||
from render import render_box, render_filled_box, get_text_size, render_text, RAND_COLORS
|
||||
from labels import COCOLabels
|
||||
|
||||
INPUT_NAMES = ["images"]
|
||||
OUTPUT_NAMES = ["num_dets", "det_boxes", "det_scores", "det_classes"]
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('mode',
|
||||
choices=['dummy', 'image', 'video'],
|
||||
default='dummy',
|
||||
help='Run mode. \'dummy\' will send an emtpy buffer to the server to test if inference works. \'image\' will process an image. \'video\' will process a video.')
|
||||
parser.add_argument('input',
|
||||
type=str,
|
||||
nargs='?',
|
||||
help='Input file to load from in image or video mode')
|
||||
parser.add_argument('-m',
|
||||
'--model',
|
||||
type=str,
|
||||
required=False,
|
||||
default='yolov7',
|
||||
help='Inference model name, default yolov7')
|
||||
parser.add_argument('--width',
|
||||
type=int,
|
||||
required=False,
|
||||
default=640,
|
||||
help='Inference model input width, default 640')
|
||||
parser.add_argument('--height',
|
||||
type=int,
|
||||
required=False,
|
||||
default=640,
|
||||
help='Inference model input height, default 640')
|
||||
parser.add_argument('-u',
|
||||
'--url',
|
||||
type=str,
|
||||
required=False,
|
||||
default='localhost:8001',
|
||||
help='Inference server URL, default localhost:8001')
|
||||
parser.add_argument('-o',
|
||||
'--out',
|
||||
type=str,
|
||||
required=False,
|
||||
default='',
|
||||
help='Write output into file instead of displaying it')
|
||||
parser.add_argument('-f',
|
||||
'--fps',
|
||||
type=float,
|
||||
required=False,
|
||||
default=24.0,
|
||||
help='Video output fps, default 24.0 FPS')
|
||||
parser.add_argument('-i',
|
||||
'--model-info',
|
||||
action="store_true",
|
||||
required=False,
|
||||
default=False,
|
||||
help='Print model status, configuration and statistics')
|
||||
parser.add_argument('-v',
|
||||
'--verbose',
|
||||
action="store_true",
|
||||
required=False,
|
||||
default=False,
|
||||
help='Enable verbose client output')
|
||||
parser.add_argument('-t',
|
||||
'--client-timeout',
|
||||
type=float,
|
||||
required=False,
|
||||
default=None,
|
||||
help='Client timeout in seconds, default no timeout')
|
||||
parser.add_argument('-s',
|
||||
'--ssl',
|
||||
action="store_true",
|
||||
required=False,
|
||||
default=False,
|
||||
help='Enable SSL encrypted channel to the server')
|
||||
parser.add_argument('-r',
|
||||
'--root-certificates',
|
||||
type=str,
|
||||
required=False,
|
||||
default=None,
|
||||
help='File holding PEM-encoded root certificates, default none')
|
||||
parser.add_argument('-p',
|
||||
'--private-key',
|
||||
type=str,
|
||||
required=False,
|
||||
default=None,
|
||||
help='File holding PEM-encoded private key, default is none')
|
||||
parser.add_argument('-x',
|
||||
'--certificate-chain',
|
||||
type=str,
|
||||
required=False,
|
||||
default=None,
|
||||
help='File holding PEM-encoded certicate chain default is none')
|
||||
|
||||
FLAGS = parser.parse_args()
|
||||
|
||||
# Create server context
|
||||
try:
|
||||
triton_client = grpcclient.InferenceServerClient(
|
||||
url=FLAGS.url,
|
||||
verbose=FLAGS.verbose,
|
||||
ssl=FLAGS.ssl,
|
||||
root_certificates=FLAGS.root_certificates,
|
||||
private_key=FLAGS.private_key,
|
||||
certificate_chain=FLAGS.certificate_chain)
|
||||
except Exception as e:
|
||||
print("context creation failed: " + str(e))
|
||||
sys.exit()
|
||||
|
||||
# Health check
|
||||
if not triton_client.is_server_live():
|
||||
print("FAILED : is_server_live")
|
||||
sys.exit(1)
|
||||
|
||||
if not triton_client.is_server_ready():
|
||||
print("FAILED : is_server_ready")
|
||||
sys.exit(1)
|
||||
|
||||
if not triton_client.is_model_ready(FLAGS.model):
|
||||
print("FAILED : is_model_ready")
|
||||
sys.exit(1)
|
||||
|
||||
if FLAGS.model_info:
|
||||
# Model metadata
|
||||
try:
|
||||
metadata = triton_client.get_model_metadata(FLAGS.model)
|
||||
print(metadata)
|
||||
except InferenceServerException as ex:
|
||||
if "Request for unknown model" not in ex.message():
|
||||
print("FAILED : get_model_metadata")
|
||||
print("Got: {}".format(ex.message()))
|
||||
sys.exit(1)
|
||||
else:
|
||||
print("FAILED : get_model_metadata")
|
||||
sys.exit(1)
|
||||
|
||||
# Model configuration
|
||||
try:
|
||||
config = triton_client.get_model_config(FLAGS.model)
|
||||
if not (config.config.name == FLAGS.model):
|
||||
print("FAILED: get_model_config")
|
||||
sys.exit(1)
|
||||
print(config)
|
||||
except InferenceServerException as ex:
|
||||
print("FAILED : get_model_config")
|
||||
print("Got: {}".format(ex.message()))
|
||||
sys.exit(1)
|
||||
|
||||
# DUMMY MODE
|
||||
if FLAGS.mode == 'dummy':
|
||||
print("Running in 'dummy' mode")
|
||||
print("Creating emtpy buffer filled with ones...")
|
||||
inputs = []
|
||||
outputs = []
|
||||
inputs.append(grpcclient.InferInput(INPUT_NAMES[0], [1, 3, FLAGS.width, FLAGS.height], "FP32"))
|
||||
inputs[0].set_data_from_numpy(np.ones(shape=(1, 3, FLAGS.width, FLAGS.height), dtype=np.float32))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[0]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[1]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[2]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[3]))
|
||||
|
||||
print("Invoking inference...")
|
||||
results = triton_client.infer(model_name=FLAGS.model,
|
||||
inputs=inputs,
|
||||
outputs=outputs,
|
||||
client_timeout=FLAGS.client_timeout)
|
||||
if FLAGS.model_info:
|
||||
statistics = triton_client.get_inference_statistics(model_name=FLAGS.model)
|
||||
if len(statistics.model_stats) != 1:
|
||||
print("FAILED: get_inference_statistics")
|
||||
sys.exit(1)
|
||||
print(statistics)
|
||||
print("Done")
|
||||
|
||||
for output in OUTPUT_NAMES:
|
||||
result = results.as_numpy(output)
|
||||
print(f"Received result buffer \"{output}\" of size {result.shape}")
|
||||
print(f"Naive buffer sum: {np.sum(result)}")
|
||||
|
||||
# IMAGE MODE
|
||||
if FLAGS.mode == 'image':
|
||||
print("Running in 'image' mode")
|
||||
if not FLAGS.input:
|
||||
print("FAILED: no input image")
|
||||
sys.exit(1)
|
||||
|
||||
inputs = []
|
||||
outputs = []
|
||||
inputs.append(grpcclient.InferInput(INPUT_NAMES[0], [1, 3, FLAGS.width, FLAGS.height], "FP32"))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[0]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[1]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[2]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[3]))
|
||||
|
||||
print("Creating buffer from image file...")
|
||||
input_image = cv2.imread(str(FLAGS.input))
|
||||
if input_image is None:
|
||||
print(f"FAILED: could not load input image {str(FLAGS.input)}")
|
||||
sys.exit(1)
|
||||
input_image_buffer = preprocess(input_image, [FLAGS.width, FLAGS.height])
|
||||
input_image_buffer = np.expand_dims(input_image_buffer, axis=0)
|
||||
|
||||
inputs[0].set_data_from_numpy(input_image_buffer)
|
||||
|
||||
print("Invoking inference...")
|
||||
results = triton_client.infer(model_name=FLAGS.model,
|
||||
inputs=inputs,
|
||||
outputs=outputs,
|
||||
client_timeout=FLAGS.client_timeout)
|
||||
if FLAGS.model_info:
|
||||
statistics = triton_client.get_inference_statistics(model_name=FLAGS.model)
|
||||
if len(statistics.model_stats) != 1:
|
||||
print("FAILED: get_inference_statistics")
|
||||
sys.exit(1)
|
||||
print(statistics)
|
||||
print("Done")
|
||||
|
||||
for output in OUTPUT_NAMES:
|
||||
result = results.as_numpy(output)
|
||||
print(f"Received result buffer \"{output}\" of size {result.shape}")
|
||||
print(f"Naive buffer sum: {np.sum(result)}")
|
||||
|
||||
num_dets = results.as_numpy(OUTPUT_NAMES[0])
|
||||
det_boxes = results.as_numpy(OUTPUT_NAMES[1])
|
||||
det_scores = results.as_numpy(OUTPUT_NAMES[2])
|
||||
det_classes = results.as_numpy(OUTPUT_NAMES[3])
|
||||
detected_objects = postprocess(num_dets, det_boxes, det_scores, det_classes, input_image.shape[1], input_image.shape[0], [FLAGS.width, FLAGS.height])
|
||||
print(f"Detected objects: {len(detected_objects)}")
|
||||
|
||||
for box in detected_objects:
|
||||
print(f"{COCOLabels(box.classID).name}: {box.confidence}")
|
||||
input_image = render_box(input_image, box.box(), color=tuple(RAND_COLORS[box.classID % 64].tolist()))
|
||||
size = get_text_size(input_image, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", normalised_scaling=0.6)
|
||||
input_image = render_filled_box(input_image, (box.x1 - 3, box.y1 - 3, box.x1 + size[0], box.y1 + size[1]), color=(220, 220, 220))
|
||||
input_image = render_text(input_image, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", (box.x1, box.y1), color=(30, 30, 30), normalised_scaling=0.5)
|
||||
|
||||
if FLAGS.out:
|
||||
cv2.imwrite(FLAGS.out, input_image)
|
||||
print(f"Saved result to {FLAGS.out}")
|
||||
else:
|
||||
cv2.imshow('image', input_image)
|
||||
cv2.waitKey(0)
|
||||
cv2.destroyAllWindows()
|
||||
|
||||
# VIDEO MODE
|
||||
if FLAGS.mode == 'video':
|
||||
print("Running in 'video' mode")
|
||||
if not FLAGS.input:
|
||||
print("FAILED: no input video")
|
||||
sys.exit(1)
|
||||
|
||||
inputs = []
|
||||
outputs = []
|
||||
inputs.append(grpcclient.InferInput(INPUT_NAMES[0], [1, 3, FLAGS.width, FLAGS.height], "FP32"))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[0]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[1]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[2]))
|
||||
outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[3]))
|
||||
|
||||
print("Opening input video stream...")
|
||||
cap = cv2.VideoCapture(FLAGS.input)
|
||||
if not cap.isOpened():
|
||||
print(f"FAILED: cannot open video {FLAGS.input}")
|
||||
sys.exit(1)
|
||||
|
||||
counter = 0
|
||||
out = None
|
||||
print("Invoking inference...")
|
||||
while True:
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
print("failed to fetch next frame")
|
||||
break
|
||||
|
||||
if counter == 0 and FLAGS.out:
|
||||
print("Opening output video stream...")
|
||||
fourcc = cv2.VideoWriter_fourcc('M', 'P', '4', 'V')
|
||||
out = cv2.VideoWriter(FLAGS.out, fourcc, FLAGS.fps, (frame.shape[1], frame.shape[0]))
|
||||
|
||||
input_image_buffer = preprocess(frame, [FLAGS.width, FLAGS.height])
|
||||
input_image_buffer = np.expand_dims(input_image_buffer, axis=0)
|
||||
|
||||
inputs[0].set_data_from_numpy(input_image_buffer)
|
||||
|
||||
results = triton_client.infer(model_name=FLAGS.model,
|
||||
inputs=inputs,
|
||||
outputs=outputs,
|
||||
client_timeout=FLAGS.client_timeout)
|
||||
|
||||
num_dets = results.as_numpy("num_dets")
|
||||
det_boxes = results.as_numpy("det_boxes")
|
||||
det_scores = results.as_numpy("det_scores")
|
||||
det_classes = results.as_numpy("det_classes")
|
||||
detected_objects = postprocess(num_dets, det_boxes, det_scores, det_classes, frame.shape[1], frame.shape[0], [FLAGS.width, FLAGS.height])
|
||||
print(f"Frame {counter}: {len(detected_objects)} objects")
|
||||
counter += 1
|
||||
|
||||
for box in detected_objects:
|
||||
print(f"{COCOLabels(box.classID).name}: {box.confidence}")
|
||||
frame = render_box(frame, box.box(), color=tuple(RAND_COLORS[box.classID % 64].tolist()))
|
||||
size = get_text_size(frame, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", normalised_scaling=0.6)
|
||||
frame = render_filled_box(frame, (box.x1 - 3, box.y1 - 3, box.x1 + size[0], box.y1 + size[1]), color=(220, 220, 220))
|
||||
frame = render_text(frame, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", (box.x1, box.y1), color=(30, 30, 30), normalised_scaling=0.5)
|
||||
|
||||
if FLAGS.out:
|
||||
out.write(frame)
|
||||
else:
|
||||
cv2.imshow('image', frame)
|
||||
if cv2.waitKey(1) == ord('q'):
|
||||
break
|
||||
|
||||
if FLAGS.model_info:
|
||||
statistics = triton_client.get_inference_statistics(model_name=FLAGS.model)
|
||||
if len(statistics.model_stats) != 1:
|
||||
print("FAILED: get_inference_statistics")
|
||||
sys.exit(1)
|
||||
print(statistics)
|
||||
print("Done")
|
||||
|
||||
cap.release()
|
||||
if FLAGS.out:
|
||||
out.release()
|
||||
else:
|
||||
cv2.destroyAllWindows()
|
||||
@@ -0,0 +1,83 @@
|
||||
from enum import Enum
|
||||
|
||||
class COCOLabels(Enum):
|
||||
PERSON = 0
|
||||
BICYCLE = 1
|
||||
CAR = 2
|
||||
MOTORBIKE = 3
|
||||
AEROPLANE = 4
|
||||
BUS = 5
|
||||
TRAIN = 6
|
||||
TRUCK = 7
|
||||
BOAT = 8
|
||||
TRAFFIC_LIGHT = 9
|
||||
FIRE_HYDRANT = 10
|
||||
STOP_SIGN = 11
|
||||
PARKING_METER = 12
|
||||
BENCH = 13
|
||||
BIRD = 14
|
||||
CAT = 15
|
||||
DOG = 16
|
||||
HORSE = 17
|
||||
SHEEP = 18
|
||||
COW = 19
|
||||
ELEPHANT = 20
|
||||
BEAR = 21
|
||||
ZEBRA = 22
|
||||
GIRAFFE = 23
|
||||
BACKPACK = 24
|
||||
UMBRELLA = 25
|
||||
HANDBAG = 26
|
||||
TIE = 27
|
||||
SUITCASE = 28
|
||||
FRISBEE = 29
|
||||
SKIS = 30
|
||||
SNOWBOARD = 31
|
||||
SPORTS_BALL = 32
|
||||
KITE = 33
|
||||
BASEBALL_BAT = 34
|
||||
BASEBALL_GLOVE = 35
|
||||
SKATEBOARD = 36
|
||||
SURFBOARD = 37
|
||||
TENNIS_RACKET = 38
|
||||
BOTTLE = 39
|
||||
WINE_GLASS = 40
|
||||
CUP = 41
|
||||
FORK = 42
|
||||
KNIFE = 43
|
||||
SPOON = 44
|
||||
BOWL = 45
|
||||
BANANA = 46
|
||||
APPLE = 47
|
||||
SANDWICH = 48
|
||||
ORANGE = 49
|
||||
BROCCOLI = 50
|
||||
CARROT = 51
|
||||
HOT_DOG = 52
|
||||
PIZZA = 53
|
||||
DONUT = 54
|
||||
CAKE = 55
|
||||
CHAIR = 56
|
||||
SOFA = 57
|
||||
POTTEDPLANT = 58
|
||||
BED = 59
|
||||
DININGTABLE = 60
|
||||
TOILET = 61
|
||||
TVMONITOR = 62
|
||||
LAPTOP = 63
|
||||
MOUSE = 64
|
||||
REMOTE = 65
|
||||
KEYBOARD = 66
|
||||
CELL_PHONE = 67
|
||||
MICROWAVE = 68
|
||||
OVEN = 69
|
||||
TOASTER = 70
|
||||
SINK = 71
|
||||
REFRIGERATOR = 72
|
||||
BOOK = 73
|
||||
CLOCK = 74
|
||||
VASE = 75
|
||||
SCISSORS = 76
|
||||
TEDDY_BEAR = 77
|
||||
HAIR_DRIER = 78
|
||||
TOOTHBRUSH = 79
|
||||
@@ -0,0 +1,51 @@
|
||||
from boundingbox import BoundingBox
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
def preprocess(img, input_shape, letter_box=True):
|
||||
if letter_box:
|
||||
img_h, img_w, _ = img.shape
|
||||
new_h, new_w = input_shape[0], input_shape[1]
|
||||
offset_h, offset_w = 0, 0
|
||||
if (new_w / img_w) <= (new_h / img_h):
|
||||
new_h = int(img_h * new_w / img_w)
|
||||
offset_h = (input_shape[0] - new_h) // 2
|
||||
else:
|
||||
new_w = int(img_w * new_h / img_h)
|
||||
offset_w = (input_shape[1] - new_w) // 2
|
||||
resized = cv2.resize(img, (new_w, new_h))
|
||||
img = np.full((input_shape[0], input_shape[1], 3), 127, dtype=np.uint8)
|
||||
img[offset_h:(offset_h + new_h), offset_w:(offset_w + new_w), :] = resized
|
||||
else:
|
||||
img = cv2.resize(img, (input_shape[1], input_shape[0]))
|
||||
|
||||
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
|
||||
img = img.transpose((2, 0, 1)).astype(np.float32)
|
||||
img /= 255.0
|
||||
return img
|
||||
|
||||
def postprocess(num_dets, det_boxes, det_scores, det_classes, img_w, img_h, input_shape, letter_box=True):
|
||||
boxes = det_boxes[0, :num_dets[0][0]] / np.array([input_shape[0], input_shape[1], input_shape[0], input_shape[1]], dtype=np.float32)
|
||||
scores = det_scores[0, :num_dets[0][0]]
|
||||
classes = det_classes[0, :num_dets[0][0]].astype(np.int)
|
||||
|
||||
old_h, old_w = img_h, img_w
|
||||
offset_h, offset_w = 0, 0
|
||||
if letter_box:
|
||||
if (img_w / input_shape[1]) >= (img_h / input_shape[0]):
|
||||
old_h = int(input_shape[0] * img_w / input_shape[1])
|
||||
offset_h = (old_h - img_h) // 2
|
||||
else:
|
||||
old_w = int(input_shape[1] * img_h / input_shape[0])
|
||||
offset_w = (old_w - img_w) // 2
|
||||
|
||||
boxes = boxes * np.array([old_w, old_h, old_w, old_h], dtype=np.float32)
|
||||
if letter_box:
|
||||
boxes -= np.array([offset_w, offset_h, offset_w, offset_h], dtype=np.float32)
|
||||
boxes = boxes.astype(np.int)
|
||||
|
||||
detected_objects = []
|
||||
for box, score, label in zip(boxes, scores, classes):
|
||||
detected_objects.append(BoundingBox(label, score, box[0], box[2], box[1], box[3], img_w, img_h))
|
||||
return detected_objects
|
||||
@@ -0,0 +1,110 @@
|
||||
import numpy as np
|
||||
|
||||
import cv2
|
||||
|
||||
from math import sqrt
|
||||
|
||||
_LINE_THICKNESS_SCALING = 500.0
|
||||
|
||||
np.random.seed(0)
|
||||
RAND_COLORS = np.random.randint(50, 255, (64, 3), "int") # used for class visu
|
||||
RAND_COLORS[0] = [220, 220, 220]
|
||||
|
||||
def render_box(img, box, color=(200, 200, 200)):
|
||||
"""
|
||||
Render a box. Calculates scaling and thickness automatically.
|
||||
:param img: image to render into
|
||||
:param box: (x1, y1, x2, y2) - box coordinates
|
||||
:param color: (b, g, r) - box color
|
||||
:return: updated image
|
||||
"""
|
||||
x1, y1, x2, y2 = box
|
||||
thickness = int(
|
||||
round(
|
||||
(img.shape[0] * img.shape[1])
|
||||
/ (_LINE_THICKNESS_SCALING * _LINE_THICKNESS_SCALING)
|
||||
)
|
||||
)
|
||||
thickness = max(1, thickness)
|
||||
img = cv2.rectangle(
|
||||
img,
|
||||
(int(x1), int(y1)),
|
||||
(int(x2), int(y2)),
|
||||
color,
|
||||
thickness=thickness
|
||||
)
|
||||
return img
|
||||
|
||||
def render_filled_box(img, box, color=(200, 200, 200)):
|
||||
"""
|
||||
Render a box. Calculates scaling and thickness automatically.
|
||||
:param img: image to render into
|
||||
:param box: (x1, y1, x2, y2) - box coordinates
|
||||
:param color: (b, g, r) - box color
|
||||
:return: updated image
|
||||
"""
|
||||
x1, y1, x2, y2 = box
|
||||
img = cv2.rectangle(
|
||||
img,
|
||||
(int(x1), int(y1)),
|
||||
(int(x2), int(y2)),
|
||||
color,
|
||||
thickness=cv2.FILLED
|
||||
)
|
||||
return img
|
||||
|
||||
_TEXT_THICKNESS_SCALING = 700.0
|
||||
_TEXT_SCALING = 520.0
|
||||
|
||||
|
||||
def get_text_size(img, text, normalised_scaling=1.0):
|
||||
"""
|
||||
Get calculated text size (as box width and height)
|
||||
:param img: image reference, used to determine appropriate text scaling
|
||||
:param text: text to display
|
||||
:param normalised_scaling: additional normalised scaling. Default 1.0.
|
||||
:return: (width, height) - width and height of text box
|
||||
"""
|
||||
thickness = int(
|
||||
round(
|
||||
(img.shape[0] * img.shape[1])
|
||||
/ (_TEXT_THICKNESS_SCALING * _TEXT_THICKNESS_SCALING)
|
||||
)
|
||||
* normalised_scaling
|
||||
)
|
||||
thickness = max(1, thickness)
|
||||
scaling = img.shape[0] / _TEXT_SCALING * normalised_scaling
|
||||
return cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, scaling, thickness)[0]
|
||||
|
||||
|
||||
def render_text(img, text, pos, color=(200, 200, 200), normalised_scaling=1.0):
|
||||
"""
|
||||
Render a text into the image. Calculates scaling and thickness automatically.
|
||||
:param img: image to render into
|
||||
:param text: text to display
|
||||
:param pos: (x, y) - upper left coordinates of render position
|
||||
:param color: (b, g, r) - text color
|
||||
:param normalised_scaling: additional normalised scaling. Default 1.0.
|
||||
:return: updated image
|
||||
"""
|
||||
x, y = pos
|
||||
thickness = int(
|
||||
round(
|
||||
(img.shape[0] * img.shape[1])
|
||||
/ (_TEXT_THICKNESS_SCALING * _TEXT_THICKNESS_SCALING)
|
||||
)
|
||||
* normalised_scaling
|
||||
)
|
||||
thickness = max(1, thickness)
|
||||
scaling = img.shape[0] / _TEXT_SCALING * normalised_scaling
|
||||
size = get_text_size(img, text, normalised_scaling)
|
||||
cv2.putText(
|
||||
img,
|
||||
text,
|
||||
(int(x), int(y + size[1])),
|
||||
cv2.FONT_HERSHEY_SIMPLEX,
|
||||
scaling,
|
||||
color,
|
||||
thickness=thickness,
|
||||
)
|
||||
return img
|
||||
@@ -0,0 +1,196 @@
|
||||
import argparse
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
from numpy import random
|
||||
|
||||
from models.experimental import attempt_load
|
||||
from utils.datasets import LoadStreams, LoadImages
|
||||
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
|
||||
scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
|
||||
from utils.plots import plot_one_box
|
||||
from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel
|
||||
|
||||
|
||||
def detect(save_img=False):
|
||||
source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace
|
||||
save_img = not opt.nosave and not source.endswith('.txt') # save inference images
|
||||
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
|
||||
('rtsp://', 'rtmp://', 'http://', 'https://'))
|
||||
|
||||
# Directories
|
||||
save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run
|
||||
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||||
|
||||
# Initialize
|
||||
set_logging()
|
||||
device = select_device(opt.device)
|
||||
half = device.type != 'cpu' # half precision only supported on CUDA
|
||||
|
||||
# Load model
|
||||
model = attempt_load(weights, map_location=device) # load FP32 model
|
||||
stride = int(model.stride.max()) # model stride
|
||||
imgsz = check_img_size(imgsz, s=stride) # check img_size
|
||||
|
||||
if trace:
|
||||
model = TracedModel(model, device, opt.img_size)
|
||||
|
||||
if half:
|
||||
model.half() # to FP16
|
||||
|
||||
# Second-stage classifier
|
||||
classify = False
|
||||
if classify:
|
||||
modelc = load_classifier(name='resnet101', n=2) # initialize
|
||||
modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
|
||||
|
||||
# Set Dataloader
|
||||
vid_path, vid_writer = None, None
|
||||
if webcam:
|
||||
view_img = check_imshow()
|
||||
cudnn.benchmark = True # set True to speed up constant image size inference
|
||||
dataset = LoadStreams(source, img_size=imgsz, stride=stride)
|
||||
else:
|
||||
dataset = LoadImages(source, img_size=imgsz, stride=stride)
|
||||
|
||||
# Get names and colors
|
||||
names = model.module.names if hasattr(model, 'module') else model.names
|
||||
colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
|
||||
|
||||
# Run inference
|
||||
if device.type != 'cpu':
|
||||
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
|
||||
old_img_w = old_img_h = imgsz
|
||||
old_img_b = 1
|
||||
|
||||
t0 = time.time()
|
||||
for path, img, im0s, vid_cap in dataset:
|
||||
img = torch.from_numpy(img).to(device)
|
||||
img = img.half() if half else img.float() # uint8 to fp16/32
|
||||
img /= 255.0 # 0 - 255 to 0.0 - 1.0
|
||||
if img.ndimension() == 3:
|
||||
img = img.unsqueeze(0)
|
||||
|
||||
# Warmup
|
||||
if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]):
|
||||
old_img_b = img.shape[0]
|
||||
old_img_h = img.shape[2]
|
||||
old_img_w = img.shape[3]
|
||||
for i in range(3):
|
||||
model(img, augment=opt.augment)[0]
|
||||
|
||||
# Inference
|
||||
t1 = time_synchronized()
|
||||
with torch.no_grad(): # Calculating gradients would cause a GPU memory leak
|
||||
pred = model(img, augment=opt.augment)[0]
|
||||
t2 = time_synchronized()
|
||||
|
||||
# Apply NMS
|
||||
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
|
||||
t3 = time_synchronized()
|
||||
|
||||
# Apply Classifier
|
||||
if classify:
|
||||
pred = apply_classifier(pred, modelc, img, im0s)
|
||||
|
||||
# Process detections
|
||||
for i, det in enumerate(pred): # detections per image
|
||||
if webcam: # batch_size >= 1
|
||||
p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
|
||||
else:
|
||||
p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
|
||||
|
||||
p = Path(p) # to Path
|
||||
save_path = str(save_dir / p.name) # img.jpg
|
||||
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
|
||||
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
|
||||
if len(det):
|
||||
# Rescale boxes from img_size to im0 size
|
||||
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
|
||||
|
||||
# Print results
|
||||
for c in det[:, -1].unique():
|
||||
n = (det[:, -1] == c).sum() # detections per class
|
||||
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
|
||||
# Write results
|
||||
for *xyxy, conf, cls in reversed(det):
|
||||
if save_txt: # Write to file
|
||||
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
||||
line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) # label format
|
||||
with open(txt_path + '.txt', 'a') as f:
|
||||
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
||||
|
||||
if save_img or view_img: # Add bbox to image
|
||||
label = f'{names[int(cls)]} {conf:.2f}'
|
||||
plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=1)
|
||||
|
||||
# Print time (inference + NMS)
|
||||
print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')
|
||||
|
||||
# Stream results
|
||||
if view_img:
|
||||
cv2.imshow(str(p), im0)
|
||||
cv2.waitKey(1) # 1 millisecond
|
||||
|
||||
# Save results (image with detections)
|
||||
if save_img:
|
||||
if dataset.mode == 'image':
|
||||
cv2.imwrite(save_path, im0)
|
||||
print(f" The image with the result is saved in: {save_path}")
|
||||
else: # 'video' or 'stream'
|
||||
if vid_path != save_path: # new video
|
||||
vid_path = save_path
|
||||
if isinstance(vid_writer, cv2.VideoWriter):
|
||||
vid_writer.release() # release previous video writer
|
||||
if vid_cap: # video
|
||||
fps = vid_cap.get(cv2.CAP_PROP_FPS)
|
||||
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
else: # stream
|
||||
fps, w, h = 30, im0.shape[1], im0.shape[0]
|
||||
save_path += '.mp4'
|
||||
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
|
||||
vid_writer.write(im0)
|
||||
|
||||
if save_txt or save_img:
|
||||
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
|
||||
#print(f"Results saved to {save_dir}{s}")
|
||||
|
||||
print(f'Done. ({time.time() - t0:.3f}s)')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)')
|
||||
parser.add_argument('--source', type=str, default='inference/images', help='source') # file/folder, 0 for webcam
|
||||
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
|
||||
parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
|
||||
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--view-img', action='store_true', help='display results')
|
||||
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
|
||||
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
|
||||
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
|
||||
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
|
||||
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
|
||||
parser.add_argument('--augment', action='store_true', help='augmented inference')
|
||||
parser.add_argument('--update', action='store_true', help='update all models')
|
||||
parser.add_argument('--project', default='runs/detect', help='save results to project/name')
|
||||
parser.add_argument('--name', default='exp', help='save results to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
parser.add_argument('--no-trace', action='store_true', help='don`t trace model')
|
||||
opt = parser.parse_args()
|
||||
print(opt)
|
||||
#check_requirements(exclude=('pycocotools', 'thop'))
|
||||
|
||||
with torch.no_grad():
|
||||
if opt.update: # update all models (to fix SourceChangeWarning)
|
||||
for opt.weights in ['yolov7.pt']:
|
||||
detect()
|
||||
strip_optimizer(opt.weights)
|
||||
else:
|
||||
detect()
|
||||
@@ -0,0 +1,205 @@
|
||||
import argparse
|
||||
import sys
|
||||
import time
|
||||
import warnings
|
||||
|
||||
sys.path.append('./') # to run '$ python *.py' files in subdirectories
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.utils.mobile_optimizer import optimize_for_mobile
|
||||
|
||||
import models
|
||||
from models.experimental import attempt_load, End2End
|
||||
from utils.activations import Hardswish, SiLU
|
||||
from utils.general import set_logging, check_img_size
|
||||
from utils.torch_utils import select_device
|
||||
from utils.add_nms import RegisterNMS
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default='./yolor-csp-c.pt', help='weights path')
|
||||
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
||||
parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes')
|
||||
parser.add_argument('--dynamic-batch', action='store_true', help='dynamic batch onnx for tensorrt and onnx-runtime')
|
||||
parser.add_argument('--grid', action='store_true', help='export Detect() layer grid')
|
||||
parser.add_argument('--end2end', action='store_true', help='export end2end onnx')
|
||||
parser.add_argument('--max-wh', type=int, default=None, help='None for tensorrt nms, int value for onnx-runtime nms')
|
||||
parser.add_argument('--topk-all', type=int, default=100, help='topk objects for every images')
|
||||
parser.add_argument('--iou-thres', type=float, default=0.45, help='iou threshold for NMS')
|
||||
parser.add_argument('--conf-thres', type=float, default=0.25, help='conf threshold for NMS')
|
||||
parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--simplify', action='store_true', help='simplify onnx model')
|
||||
parser.add_argument('--include-nms', action='store_true', help='export end2end onnx')
|
||||
parser.add_argument('--fp16', action='store_true', help='CoreML FP16 half-precision export')
|
||||
parser.add_argument('--int8', action='store_true', help='CoreML INT8 quantization')
|
||||
opt = parser.parse_args()
|
||||
opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand
|
||||
opt.dynamic = opt.dynamic and not opt.end2end
|
||||
opt.dynamic = False if opt.dynamic_batch else opt.dynamic
|
||||
print(opt)
|
||||
set_logging()
|
||||
t = time.time()
|
||||
|
||||
# Load PyTorch model
|
||||
device = select_device(opt.device)
|
||||
model = attempt_load(opt.weights, map_location=device) # load FP32 model
|
||||
labels = model.names
|
||||
|
||||
# Checks
|
||||
gs = int(max(model.stride)) # grid size (max stride)
|
||||
opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples
|
||||
|
||||
# Input
|
||||
img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection
|
||||
|
||||
# Update model
|
||||
for k, m in model.named_modules():
|
||||
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
|
||||
if isinstance(m, models.common.Conv): # assign export-friendly activations
|
||||
if isinstance(m.act, nn.Hardswish):
|
||||
m.act = Hardswish()
|
||||
elif isinstance(m.act, nn.SiLU):
|
||||
m.act = SiLU()
|
||||
# elif isinstance(m, models.yolo.Detect):
|
||||
# m.forward = m.forward_export # assign forward (optional)
|
||||
model.model[-1].export = not opt.grid # set Detect() layer grid export
|
||||
y = model(img) # dry run
|
||||
if opt.include_nms:
|
||||
model.model[-1].include_nms = True
|
||||
y = None
|
||||
|
||||
# TorchScript export
|
||||
try:
|
||||
print('\nStarting TorchScript export with torch %s...' % torch.__version__)
|
||||
f = opt.weights.replace('.pt', '.torchscript.pt') # filename
|
||||
ts = torch.jit.trace(model, img, strict=False)
|
||||
ts.save(f)
|
||||
print('TorchScript export success, saved as %s' % f)
|
||||
except Exception as e:
|
||||
print('TorchScript export failure: %s' % e)
|
||||
|
||||
# CoreML export
|
||||
try:
|
||||
import coremltools as ct
|
||||
|
||||
print('\nStarting CoreML export with coremltools %s...' % ct.__version__)
|
||||
# convert model from torchscript and apply pixel scaling as per detect.py
|
||||
ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
|
||||
bits, mode = (8, 'kmeans_lut') if opt.int8 else (16, 'linear') if opt.fp16 else (32, None)
|
||||
if bits < 32:
|
||||
if sys.platform.lower() == 'darwin': # quantization only supported on macOS
|
||||
with warnings.catch_warnings():
|
||||
warnings.filterwarnings("ignore", category=DeprecationWarning) # suppress numpy==1.20 float warning
|
||||
ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
|
||||
else:
|
||||
print('quantization only supported on macOS, skipping...')
|
||||
|
||||
f = opt.weights.replace('.pt', '.mlmodel') # filename
|
||||
ct_model.save(f)
|
||||
print('CoreML export success, saved as %s' % f)
|
||||
except Exception as e:
|
||||
print('CoreML export failure: %s' % e)
|
||||
|
||||
# TorchScript-Lite export
|
||||
try:
|
||||
print('\nStarting TorchScript-Lite export with torch %s...' % torch.__version__)
|
||||
f = opt.weights.replace('.pt', '.torchscript.ptl') # filename
|
||||
tsl = torch.jit.trace(model, img, strict=False)
|
||||
tsl = optimize_for_mobile(tsl)
|
||||
tsl._save_for_lite_interpreter(f)
|
||||
print('TorchScript-Lite export success, saved as %s' % f)
|
||||
except Exception as e:
|
||||
print('TorchScript-Lite export failure: %s' % e)
|
||||
|
||||
# ONNX export
|
||||
try:
|
||||
import onnx
|
||||
|
||||
print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
|
||||
f = opt.weights.replace('.pt', '.onnx') # filename
|
||||
model.eval()
|
||||
output_names = ['classes', 'boxes'] if y is None else ['output']
|
||||
dynamic_axes = None
|
||||
if opt.dynamic:
|
||||
dynamic_axes = {'images': {0: 'batch', 2: 'height', 3: 'width'}, # size(1,3,640,640)
|
||||
'output': {0: 'batch', 2: 'y', 3: 'x'}}
|
||||
if opt.dynamic_batch:
|
||||
opt.batch_size = 'batch'
|
||||
dynamic_axes = {
|
||||
'images': {
|
||||
0: 'batch',
|
||||
}, }
|
||||
if opt.end2end and opt.max_wh is None:
|
||||
output_axes = {
|
||||
'num_dets': {0: 'batch'},
|
||||
'det_boxes': {0: 'batch'},
|
||||
'det_scores': {0: 'batch'},
|
||||
'det_classes': {0: 'batch'},
|
||||
}
|
||||
else:
|
||||
output_axes = {
|
||||
'output': {0: 'batch'},
|
||||
}
|
||||
dynamic_axes.update(output_axes)
|
||||
if opt.grid:
|
||||
if opt.end2end:
|
||||
print('\nStarting export end2end onnx model for %s...' % 'TensorRT' if opt.max_wh is None else 'onnxruntime')
|
||||
model = End2End(model,opt.topk_all,opt.iou_thres,opt.conf_thres,opt.max_wh,device,len(labels))
|
||||
if opt.end2end and opt.max_wh is None:
|
||||
output_names = ['num_dets', 'det_boxes', 'det_scores', 'det_classes']
|
||||
shapes = [opt.batch_size, 1, opt.batch_size, opt.topk_all, 4,
|
||||
opt.batch_size, opt.topk_all, opt.batch_size, opt.topk_all]
|
||||
else:
|
||||
output_names = ['output']
|
||||
else:
|
||||
model.model[-1].concat = True
|
||||
|
||||
torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
|
||||
output_names=output_names,
|
||||
dynamic_axes=dynamic_axes)
|
||||
|
||||
# Checks
|
||||
onnx_model = onnx.load(f) # load onnx model
|
||||
onnx.checker.check_model(onnx_model) # check onnx model
|
||||
|
||||
if opt.end2end and opt.max_wh is None:
|
||||
for i in onnx_model.graph.output:
|
||||
for j in i.type.tensor_type.shape.dim:
|
||||
j.dim_param = str(shapes.pop(0))
|
||||
|
||||
# print(onnx.helper.printable_graph(onnx_model.graph)) # print a human readable model
|
||||
|
||||
# # Metadata
|
||||
# d = {'stride': int(max(model.stride))}
|
||||
# for k, v in d.items():
|
||||
# meta = onnx_model.metadata_props.add()
|
||||
# meta.key, meta.value = k, str(v)
|
||||
# onnx.save(onnx_model, f)
|
||||
|
||||
if opt.simplify:
|
||||
try:
|
||||
import onnxsim
|
||||
|
||||
print('\nStarting to simplify ONNX...')
|
||||
onnx_model, check = onnxsim.simplify(onnx_model)
|
||||
assert check, 'assert check failed'
|
||||
except Exception as e:
|
||||
print(f'Simplifier failure: {e}')
|
||||
|
||||
# print(onnx.helper.printable_graph(onnx_model.graph)) # print a human readable model
|
||||
onnx.save(onnx_model,f)
|
||||
print('ONNX export success, saved as %s' % f)
|
||||
|
||||
if opt.include_nms:
|
||||
print('Registering NMS plugin for ONNX...')
|
||||
mo = RegisterNMS(f)
|
||||
mo.register_nms()
|
||||
mo.save(f)
|
||||
|
||||
except Exception as e:
|
||||
print('ONNX export failure: %s' % e)
|
||||
|
||||
# Finish
|
||||
print('\nExport complete (%.2fs). Visualize with https://github.com/lutzroeder/netron.' % (time.time() - t))
|
||||
@@ -0,0 +1,97 @@
|
||||
"""PyTorch Hub models
|
||||
|
||||
Usage:
|
||||
import torch
|
||||
model = torch.hub.load('repo', 'model')
|
||||
"""
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
|
||||
from models.yolo import Model
|
||||
from utils.general import check_requirements, set_logging
|
||||
from utils.google_utils import attempt_download
|
||||
from utils.torch_utils import select_device
|
||||
|
||||
dependencies = ['torch', 'yaml']
|
||||
check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('pycocotools', 'thop'))
|
||||
set_logging()
|
||||
|
||||
|
||||
def create(name, pretrained, channels, classes, autoshape):
|
||||
"""Creates a specified model
|
||||
|
||||
Arguments:
|
||||
name (str): name of model, i.e. 'yolov7'
|
||||
pretrained (bool): load pretrained weights into the model
|
||||
channels (int): number of input channels
|
||||
classes (int): number of model classes
|
||||
|
||||
Returns:
|
||||
pytorch model
|
||||
"""
|
||||
try:
|
||||
cfg = list((Path(__file__).parent / 'cfg').rglob(f'{name}.yaml'))[0] # model.yaml path
|
||||
model = Model(cfg, channels, classes)
|
||||
if pretrained:
|
||||
fname = f'{name}.pt' # checkpoint filename
|
||||
attempt_download(fname) # download if not found locally
|
||||
ckpt = torch.load(fname, map_location=torch.device('cpu')) # load
|
||||
msd = model.state_dict() # model state_dict
|
||||
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
|
||||
csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter
|
||||
model.load_state_dict(csd, strict=False) # load
|
||||
if len(ckpt['model'].names) == classes:
|
||||
model.names = ckpt['model'].names # set class names attribute
|
||||
if autoshape:
|
||||
model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
|
||||
device = select_device('0' if torch.cuda.is_available() else 'cpu') # default to GPU if available
|
||||
return model.to(device)
|
||||
|
||||
except Exception as e:
|
||||
s = 'Cache maybe be out of date, try force_reload=True.'
|
||||
raise Exception(s) from e
|
||||
|
||||
|
||||
def custom(path_or_model='path/to/model.pt', autoshape=True):
|
||||
"""custom mode
|
||||
|
||||
Arguments (3 options):
|
||||
path_or_model (str): 'path/to/model.pt'
|
||||
path_or_model (dict): torch.load('path/to/model.pt')
|
||||
path_or_model (nn.Module): torch.load('path/to/model.pt')['model']
|
||||
|
||||
Returns:
|
||||
pytorch model
|
||||
"""
|
||||
model = torch.load(path_or_model, map_location=torch.device('cpu')) if isinstance(path_or_model, str) else path_or_model # load checkpoint
|
||||
if isinstance(model, dict):
|
||||
model = model['ema' if model.get('ema') else 'model'] # load model
|
||||
|
||||
hub_model = Model(model.yaml).to(next(model.parameters()).device) # create
|
||||
hub_model.load_state_dict(model.float().state_dict()) # load state_dict
|
||||
hub_model.names = model.names # class names
|
||||
if autoshape:
|
||||
hub_model = hub_model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
|
||||
device = select_device('0' if torch.cuda.is_available() else 'cpu') # default to GPU if available
|
||||
return hub_model.to(device)
|
||||
|
||||
|
||||
def yolov7(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
return create('yolov7', pretrained, channels, classes, autoshape)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
model = custom(path_or_model='yolov7.pt') # custom example
|
||||
# model = create(name='yolov7', pretrained=True, channels=3, classes=80, autoshape=True) # pretrained example
|
||||
|
||||
# Verify inference
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
|
||||
imgs = [np.zeros((640, 480, 3))]
|
||||
|
||||
results = model(imgs) # batched inference
|
||||
results.print()
|
||||
results.save()
|
||||
@@ -0,0 +1 @@
|
||||
# init
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,272 @@
|
||||
import numpy as np
|
||||
import random
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from models.common import Conv, DWConv
|
||||
from utils.google_utils import attempt_download
|
||||
|
||||
|
||||
class CrossConv(nn.Module):
|
||||
# Cross Convolution Downsample
|
||||
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
|
||||
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut
|
||||
super(CrossConv, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, (1, k), (1, s))
|
||||
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class Sum(nn.Module):
|
||||
# Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
|
||||
def __init__(self, n, weight=False): # n: number of inputs
|
||||
super(Sum, self).__init__()
|
||||
self.weight = weight # apply weights boolean
|
||||
self.iter = range(n - 1) # iter object
|
||||
if weight:
|
||||
self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True) # layer weights
|
||||
|
||||
def forward(self, x):
|
||||
y = x[0] # no weight
|
||||
if self.weight:
|
||||
w = torch.sigmoid(self.w) * 2
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1] * w[i]
|
||||
else:
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1]
|
||||
return y
|
||||
|
||||
|
||||
class MixConv2d(nn.Module):
|
||||
# Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
|
||||
def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
|
||||
super(MixConv2d, self).__init__()
|
||||
groups = len(k)
|
||||
if equal_ch: # equal c_ per group
|
||||
i = torch.linspace(0, groups - 1E-6, c2).floor() # c2 indices
|
||||
c_ = [(i == g).sum() for g in range(groups)] # intermediate channels
|
||||
else: # equal weight.numel() per group
|
||||
b = [c2] + [0] * groups
|
||||
a = np.eye(groups + 1, groups, k=-1)
|
||||
a -= np.roll(a, 1, axis=1)
|
||||
a *= np.array(k) ** 2
|
||||
a[0] = 1
|
||||
c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
|
||||
|
||||
self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.LeakyReLU(0.1, inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
|
||||
|
||||
|
||||
class Ensemble(nn.ModuleList):
|
||||
# Ensemble of models
|
||||
def __init__(self):
|
||||
super(Ensemble, self).__init__()
|
||||
|
||||
def forward(self, x, augment=False):
|
||||
y = []
|
||||
for module in self:
|
||||
y.append(module(x, augment)[0])
|
||||
# y = torch.stack(y).max(0)[0] # max ensemble
|
||||
# y = torch.stack(y).mean(0) # mean ensemble
|
||||
y = torch.cat(y, 1) # nms ensemble
|
||||
return y, None # inference, train output
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
class ORT_NMS(torch.autograd.Function):
|
||||
'''ONNX-Runtime NMS operation'''
|
||||
@staticmethod
|
||||
def forward(ctx,
|
||||
boxes,
|
||||
scores,
|
||||
max_output_boxes_per_class=torch.tensor([100]),
|
||||
iou_threshold=torch.tensor([0.45]),
|
||||
score_threshold=torch.tensor([0.25])):
|
||||
device = boxes.device
|
||||
batch = scores.shape[0]
|
||||
num_det = random.randint(0, 100)
|
||||
batches = torch.randint(0, batch, (num_det,)).sort()[0].to(device)
|
||||
idxs = torch.arange(100, 100 + num_det).to(device)
|
||||
zeros = torch.zeros((num_det,), dtype=torch.int64).to(device)
|
||||
selected_indices = torch.cat([batches[None], zeros[None], idxs[None]], 0).T.contiguous()
|
||||
selected_indices = selected_indices.to(torch.int64)
|
||||
return selected_indices
|
||||
|
||||
@staticmethod
|
||||
def symbolic(g, boxes, scores, max_output_boxes_per_class, iou_threshold, score_threshold):
|
||||
return g.op("NonMaxSuppression", boxes, scores, max_output_boxes_per_class, iou_threshold, score_threshold)
|
||||
|
||||
|
||||
class TRT_NMS(torch.autograd.Function):
|
||||
'''TensorRT NMS operation'''
|
||||
@staticmethod
|
||||
def forward(
|
||||
ctx,
|
||||
boxes,
|
||||
scores,
|
||||
background_class=-1,
|
||||
box_coding=1,
|
||||
iou_threshold=0.45,
|
||||
max_output_boxes=100,
|
||||
plugin_version="1",
|
||||
score_activation=0,
|
||||
score_threshold=0.25,
|
||||
):
|
||||
batch_size, num_boxes, num_classes = scores.shape
|
||||
num_det = torch.randint(0, max_output_boxes, (batch_size, 1), dtype=torch.int32)
|
||||
det_boxes = torch.randn(batch_size, max_output_boxes, 4)
|
||||
det_scores = torch.randn(batch_size, max_output_boxes)
|
||||
det_classes = torch.randint(0, num_classes, (batch_size, max_output_boxes), dtype=torch.int32)
|
||||
return num_det, det_boxes, det_scores, det_classes
|
||||
|
||||
@staticmethod
|
||||
def symbolic(g,
|
||||
boxes,
|
||||
scores,
|
||||
background_class=-1,
|
||||
box_coding=1,
|
||||
iou_threshold=0.45,
|
||||
max_output_boxes=100,
|
||||
plugin_version="1",
|
||||
score_activation=0,
|
||||
score_threshold=0.25):
|
||||
out = g.op("TRT::EfficientNMS_TRT",
|
||||
boxes,
|
||||
scores,
|
||||
background_class_i=background_class,
|
||||
box_coding_i=box_coding,
|
||||
iou_threshold_f=iou_threshold,
|
||||
max_output_boxes_i=max_output_boxes,
|
||||
plugin_version_s=plugin_version,
|
||||
score_activation_i=score_activation,
|
||||
score_threshold_f=score_threshold,
|
||||
outputs=4)
|
||||
nums, boxes, scores, classes = out
|
||||
return nums, boxes, scores, classes
|
||||
|
||||
|
||||
class ONNX_ORT(nn.Module):
|
||||
'''onnx module with ONNX-Runtime NMS operation.'''
|
||||
def __init__(self, max_obj=100, iou_thres=0.45, score_thres=0.25, max_wh=640, device=None, n_classes=80):
|
||||
super().__init__()
|
||||
self.device = device if device else torch.device("cpu")
|
||||
self.max_obj = torch.tensor([max_obj]).to(device)
|
||||
self.iou_threshold = torch.tensor([iou_thres]).to(device)
|
||||
self.score_threshold = torch.tensor([score_thres]).to(device)
|
||||
self.max_wh = max_wh # if max_wh != 0 : non-agnostic else : agnostic
|
||||
self.convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
|
||||
dtype=torch.float32,
|
||||
device=self.device)
|
||||
self.n_classes=n_classes
|
||||
|
||||
def forward(self, x):
|
||||
boxes = x[:, :, :4]
|
||||
conf = x[:, :, 4:5]
|
||||
scores = x[:, :, 5:]
|
||||
if self.n_classes == 1:
|
||||
scores = conf # for models with one class, cls_loss is 0 and cls_conf is always 0.5,
|
||||
# so there is no need to multiplicate.
|
||||
else:
|
||||
scores *= conf # conf = obj_conf * cls_conf
|
||||
boxes @= self.convert_matrix
|
||||
max_score, category_id = scores.max(2, keepdim=True)
|
||||
dis = category_id.float() * self.max_wh
|
||||
nmsbox = boxes + dis
|
||||
max_score_tp = max_score.transpose(1, 2).contiguous()
|
||||
selected_indices = ORT_NMS.apply(nmsbox, max_score_tp, self.max_obj, self.iou_threshold, self.score_threshold)
|
||||
X, Y = selected_indices[:, 0], selected_indices[:, 2]
|
||||
selected_boxes = boxes[X, Y, :]
|
||||
selected_categories = category_id[X, Y, :].float()
|
||||
selected_scores = max_score[X, Y, :]
|
||||
X = X.unsqueeze(1).float()
|
||||
return torch.cat([X, selected_boxes, selected_categories, selected_scores], 1)
|
||||
|
||||
class ONNX_TRT(nn.Module):
|
||||
'''onnx module with TensorRT NMS operation.'''
|
||||
def __init__(self, max_obj=100, iou_thres=0.45, score_thres=0.25, max_wh=None ,device=None, n_classes=80):
|
||||
super().__init__()
|
||||
assert max_wh is None
|
||||
self.device = device if device else torch.device('cpu')
|
||||
self.background_class = -1,
|
||||
self.box_coding = 1,
|
||||
self.iou_threshold = iou_thres
|
||||
self.max_obj = max_obj
|
||||
self.plugin_version = '1'
|
||||
self.score_activation = 0
|
||||
self.score_threshold = score_thres
|
||||
self.n_classes=n_classes
|
||||
|
||||
def forward(self, x):
|
||||
boxes = x[:, :, :4]
|
||||
conf = x[:, :, 4:5]
|
||||
scores = x[:, :, 5:]
|
||||
if self.n_classes == 1:
|
||||
scores = conf # for models with one class, cls_loss is 0 and cls_conf is always 0.5,
|
||||
# so there is no need to multiplicate.
|
||||
else:
|
||||
scores *= conf # conf = obj_conf * cls_conf
|
||||
num_det, det_boxes, det_scores, det_classes = TRT_NMS.apply(boxes, scores, self.background_class, self.box_coding,
|
||||
self.iou_threshold, self.max_obj,
|
||||
self.plugin_version, self.score_activation,
|
||||
self.score_threshold)
|
||||
return num_det, det_boxes, det_scores, det_classes
|
||||
|
||||
|
||||
class End2End(nn.Module):
|
||||
'''export onnx or tensorrt model with NMS operation.'''
|
||||
def __init__(self, model, max_obj=100, iou_thres=0.45, score_thres=0.25, max_wh=None, device=None, n_classes=80):
|
||||
super().__init__()
|
||||
device = device if device else torch.device('cpu')
|
||||
assert isinstance(max_wh,(int)) or max_wh is None
|
||||
self.model = model.to(device)
|
||||
self.model.model[-1].end2end = True
|
||||
self.patch_model = ONNX_TRT if max_wh is None else ONNX_ORT
|
||||
self.end2end = self.patch_model(max_obj, iou_thres, score_thres, max_wh, device, n_classes)
|
||||
self.end2end.eval()
|
||||
|
||||
def forward(self, x):
|
||||
x = self.model(x)
|
||||
x = self.end2end(x)
|
||||
return x
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def attempt_load(weights, map_location=None):
|
||||
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
|
||||
model = Ensemble()
|
||||
for w in weights if isinstance(weights, list) else [weights]:
|
||||
attempt_download(w)
|
||||
ckpt = torch.load(w, map_location=map_location) # load
|
||||
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
|
||||
|
||||
# Compatibility updates
|
||||
for m in model.modules():
|
||||
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
|
||||
m.inplace = True # pytorch 1.7.0 compatibility
|
||||
elif type(m) is nn.Upsample:
|
||||
m.recompute_scale_factor = None # torch 1.11.0 compatibility
|
||||
elif type(m) is Conv:
|
||||
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
|
||||
|
||||
if len(model) == 1:
|
||||
return model[-1] # return model
|
||||
else:
|
||||
print('Ensemble created with %s\n' % weights)
|
||||
for k in ['names', 'stride']:
|
||||
setattr(model, k, getattr(model[-1], k))
|
||||
return model # return ensemble
|
||||
|
||||
|
||||
@@ -0,0 +1,843 @@
|
||||
import argparse
|
||||
import logging
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
|
||||
sys.path.append('./') # to run '$ python *.py' files in subdirectories
|
||||
logger = logging.getLogger(__name__)
|
||||
import torch
|
||||
from models.common import *
|
||||
from models.experimental import *
|
||||
from utils.autoanchor import check_anchor_order
|
||||
from utils.general import make_divisible, check_file, set_logging
|
||||
from utils.torch_utils import time_synchronized, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
|
||||
select_device, copy_attr
|
||||
from utils.loss import SigmoidBin
|
||||
|
||||
try:
|
||||
import thop # for FLOPS computation
|
||||
except ImportError:
|
||||
thop = None
|
||||
|
||||
|
||||
class Detect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
export = False # onnx export
|
||||
end2end = False
|
||||
include_nms = False
|
||||
concat = False
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=()): # detection layer
|
||||
super(Detect, self).__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
|
||||
self.register_buffer('anchors', a) # shape(nl,na,2)
|
||||
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
|
||||
|
||||
def forward(self, x):
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
self.training |= self.export
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](x[i]) # conv
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
y = x[i].sigmoid()
|
||||
if not torch.onnx.is_in_onnx_export():
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else:
|
||||
xy, wh, conf = y.split((2, 2, self.nc + 1), 4) # y.tensor_split((2, 4, 5), 4) # torch 1.8.0
|
||||
xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5)) # new xy
|
||||
wh = wh ** 2 * (4 * self.anchor_grid[i].data) # new wh
|
||||
y = torch.cat((xy, wh, conf), 4)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
if self.training:
|
||||
out = x
|
||||
elif self.end2end:
|
||||
out = torch.cat(z, 1)
|
||||
elif self.include_nms:
|
||||
z = self.convert(z)
|
||||
out = (z, )
|
||||
elif self.concat:
|
||||
out = torch.cat(z, 1)
|
||||
else:
|
||||
out = (torch.cat(z, 1), x)
|
||||
|
||||
return out
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
|
||||
def convert(self, z):
|
||||
z = torch.cat(z, 1)
|
||||
box = z[:, :, :4]
|
||||
conf = z[:, :, 4:5]
|
||||
score = z[:, :, 5:]
|
||||
score *= conf
|
||||
convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
|
||||
dtype=torch.float32,
|
||||
device=z.device)
|
||||
box @= convert_matrix
|
||||
return (box, score)
|
||||
|
||||
|
||||
class IDetect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
export = False # onnx export
|
||||
end2end = False
|
||||
include_nms = False
|
||||
concat = False
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=()): # detection layer
|
||||
super(IDetect, self).__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
|
||||
self.register_buffer('anchors', a) # shape(nl,na,2)
|
||||
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
|
||||
|
||||
self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
|
||||
self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch)
|
||||
|
||||
def forward(self, x):
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
self.training |= self.export
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](self.ia[i](x[i])) # conv
|
||||
x[i] = self.im[i](x[i])
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
return x if self.training else (torch.cat(z, 1), x)
|
||||
|
||||
def fuseforward(self, x):
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
self.training |= self.export
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](x[i]) # conv
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
if not torch.onnx.is_in_onnx_export():
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else:
|
||||
xy, wh, conf = y.split((2, 2, self.nc + 1), 4) # y.tensor_split((2, 4, 5), 4) # torch 1.8.0
|
||||
xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5)) # new xy
|
||||
wh = wh ** 2 * (4 * self.anchor_grid[i].data) # new wh
|
||||
y = torch.cat((xy, wh, conf), 4)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
if self.training:
|
||||
out = x
|
||||
elif self.end2end:
|
||||
out = torch.cat(z, 1)
|
||||
elif self.include_nms:
|
||||
z = self.convert(z)
|
||||
out = (z, )
|
||||
elif self.concat:
|
||||
out = torch.cat(z, 1)
|
||||
else:
|
||||
out = (torch.cat(z, 1), x)
|
||||
|
||||
return out
|
||||
|
||||
def fuse(self):
|
||||
print("IDetect.fuse")
|
||||
# fuse ImplicitA and Convolution
|
||||
for i in range(len(self.m)):
|
||||
c1,c2,_,_ = self.m[i].weight.shape
|
||||
c1_,c2_, _,_ = self.ia[i].implicit.shape
|
||||
self.m[i].bias += torch.matmul(self.m[i].weight.reshape(c1,c2),self.ia[i].implicit.reshape(c2_,c1_)).squeeze(1)
|
||||
|
||||
# fuse ImplicitM and Convolution
|
||||
for i in range(len(self.m)):
|
||||
c1,c2, _,_ = self.im[i].implicit.shape
|
||||
self.m[i].bias *= self.im[i].implicit.reshape(c2)
|
||||
self.m[i].weight *= self.im[i].implicit.transpose(0,1)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
|
||||
def convert(self, z):
|
||||
z = torch.cat(z, 1)
|
||||
box = z[:, :, :4]
|
||||
conf = z[:, :, 4:5]
|
||||
score = z[:, :, 5:]
|
||||
score *= conf
|
||||
convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
|
||||
dtype=torch.float32,
|
||||
device=z.device)
|
||||
box @= convert_matrix
|
||||
return (box, score)
|
||||
|
||||
|
||||
class IKeypoint(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
export = False # onnx export
|
||||
|
||||
def __init__(self, nc=80, anchors=(), nkpt=17, ch=(), inplace=True, dw_conv_kpt=False): # detection layer
|
||||
super(IKeypoint, self).__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.nkpt = nkpt
|
||||
self.dw_conv_kpt = dw_conv_kpt
|
||||
self.no_det=(nc + 5) # number of outputs per anchor for box and class
|
||||
self.no_kpt = 3*self.nkpt ## number of outputs per anchor for keypoints
|
||||
self.no = self.no_det+self.no_kpt
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
self.flip_test = False
|
||||
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
|
||||
self.register_buffer('anchors', a) # shape(nl,na,2)
|
||||
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no_det * self.na, 1) for x in ch) # output conv
|
||||
|
||||
self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
|
||||
self.im = nn.ModuleList(ImplicitM(self.no_det * self.na) for _ in ch)
|
||||
|
||||
if self.nkpt is not None:
|
||||
if self.dw_conv_kpt: #keypoint head is slightly more complex
|
||||
self.m_kpt = nn.ModuleList(
|
||||
nn.Sequential(DWConv(x, x, k=3), Conv(x,x),
|
||||
DWConv(x, x, k=3), Conv(x, x),
|
||||
DWConv(x, x, k=3), Conv(x,x),
|
||||
DWConv(x, x, k=3), Conv(x, x),
|
||||
DWConv(x, x, k=3), Conv(x, x),
|
||||
DWConv(x, x, k=3), nn.Conv2d(x, self.no_kpt * self.na, 1)) for x in ch)
|
||||
else: #keypoint head is a single convolution
|
||||
self.m_kpt = nn.ModuleList(nn.Conv2d(x, self.no_kpt * self.na, 1) for x in ch)
|
||||
|
||||
self.inplace = inplace # use in-place ops (e.g. slice assignment)
|
||||
|
||||
def forward(self, x):
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
self.training |= self.export
|
||||
for i in range(self.nl):
|
||||
if self.nkpt is None or self.nkpt==0:
|
||||
x[i] = self.im[i](self.m[i](self.ia[i](x[i]))) # conv
|
||||
else :
|
||||
x[i] = torch.cat((self.im[i](self.m[i](self.ia[i](x[i]))), self.m_kpt[i](x[i])), axis=1)
|
||||
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
x_det = x[i][..., :6]
|
||||
x_kpt = x[i][..., 6:]
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
kpt_grid_x = self.grid[i][..., 0:1]
|
||||
kpt_grid_y = self.grid[i][..., 1:2]
|
||||
|
||||
if self.nkpt == 0:
|
||||
y = x[i].sigmoid()
|
||||
else:
|
||||
y = x_det.sigmoid()
|
||||
|
||||
if self.inplace:
|
||||
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2) # wh
|
||||
if self.nkpt != 0:
|
||||
x_kpt[..., 0::3] = (x_kpt[..., ::3] * 2. - 0.5 + kpt_grid_x.repeat(1,1,1,1,17)) * self.stride[i] # xy
|
||||
x_kpt[..., 1::3] = (x_kpt[..., 1::3] * 2. - 0.5 + kpt_grid_y.repeat(1,1,1,1,17)) * self.stride[i] # xy
|
||||
#x_kpt[..., 0::3] = (x_kpt[..., ::3] + kpt_grid_x.repeat(1,1,1,1,17)) * self.stride[i] # xy
|
||||
#x_kpt[..., 1::3] = (x_kpt[..., 1::3] + kpt_grid_y.repeat(1,1,1,1,17)) * self.stride[i] # xy
|
||||
#print('=============')
|
||||
#print(self.anchor_grid[i].shape)
|
||||
#print(self.anchor_grid[i][...,0].unsqueeze(4).shape)
|
||||
#print(x_kpt[..., 0::3].shape)
|
||||
#x_kpt[..., 0::3] = ((x_kpt[..., 0::3].tanh() * 2.) ** 3 * self.anchor_grid[i][...,0].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_x.repeat(1,1,1,1,17) * self.stride[i] # xy
|
||||
#x_kpt[..., 1::3] = ((x_kpt[..., 1::3].tanh() * 2.) ** 3 * self.anchor_grid[i][...,1].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_y.repeat(1,1,1,1,17) * self.stride[i] # xy
|
||||
#x_kpt[..., 0::3] = (((x_kpt[..., 0::3].sigmoid() * 4.) ** 2 - 8.) * self.anchor_grid[i][...,0].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_x.repeat(1,1,1,1,17) * self.stride[i] # xy
|
||||
#x_kpt[..., 1::3] = (((x_kpt[..., 1::3].sigmoid() * 4.) ** 2 - 8.) * self.anchor_grid[i][...,1].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_y.repeat(1,1,1,1,17) * self.stride[i] # xy
|
||||
x_kpt[..., 2::3] = x_kpt[..., 2::3].sigmoid()
|
||||
|
||||
y = torch.cat((xy, wh, y[..., 4:], x_kpt), dim = -1)
|
||||
|
||||
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
|
||||
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
if self.nkpt != 0:
|
||||
y[..., 6:] = (y[..., 6:] * 2. - 0.5 + self.grid[i].repeat((1,1,1,1,self.nkpt))) * self.stride[i] # xy
|
||||
y = torch.cat((xy, wh, y[..., 4:]), -1)
|
||||
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
return x if self.training else (torch.cat(z, 1), x)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
|
||||
|
||||
class IAuxDetect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
export = False # onnx export
|
||||
end2end = False
|
||||
include_nms = False
|
||||
concat = False
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=()): # detection layer
|
||||
super(IAuxDetect, self).__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
|
||||
self.register_buffer('anchors', a) # shape(nl,na,2)
|
||||
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch[:self.nl]) # output conv
|
||||
self.m2 = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch[self.nl:]) # output conv
|
||||
|
||||
self.ia = nn.ModuleList(ImplicitA(x) for x in ch[:self.nl])
|
||||
self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch[:self.nl])
|
||||
|
||||
def forward(self, x):
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
self.training |= self.export
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](self.ia[i](x[i])) # conv
|
||||
x[i] = self.im[i](x[i])
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
x[i+self.nl] = self.m2[i](x[i+self.nl])
|
||||
x[i+self.nl] = x[i+self.nl].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
if not torch.onnx.is_in_onnx_export():
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else:
|
||||
xy, wh, conf = y.split((2, 2, self.nc + 1), 4) # y.tensor_split((2, 4, 5), 4) # torch 1.8.0
|
||||
xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5)) # new xy
|
||||
wh = wh ** 2 * (4 * self.anchor_grid[i].data) # new wh
|
||||
y = torch.cat((xy, wh, conf), 4)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
return x if self.training else (torch.cat(z, 1), x[:self.nl])
|
||||
|
||||
def fuseforward(self, x):
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
self.training |= self.export
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](x[i]) # conv
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
if not torch.onnx.is_in_onnx_export():
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else:
|
||||
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].data # wh
|
||||
y = torch.cat((xy, wh, y[..., 4:]), -1)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
if self.training:
|
||||
out = x
|
||||
elif self.end2end:
|
||||
out = torch.cat(z, 1)
|
||||
elif self.include_nms:
|
||||
z = self.convert(z)
|
||||
out = (z, )
|
||||
elif self.concat:
|
||||
out = torch.cat(z, 1)
|
||||
else:
|
||||
out = (torch.cat(z, 1), x)
|
||||
|
||||
return out
|
||||
|
||||
def fuse(self):
|
||||
print("IAuxDetect.fuse")
|
||||
# fuse ImplicitA and Convolution
|
||||
for i in range(len(self.m)):
|
||||
c1,c2,_,_ = self.m[i].weight.shape
|
||||
c1_,c2_, _,_ = self.ia[i].implicit.shape
|
||||
self.m[i].bias += torch.matmul(self.m[i].weight.reshape(c1,c2),self.ia[i].implicit.reshape(c2_,c1_)).squeeze(1)
|
||||
|
||||
# fuse ImplicitM and Convolution
|
||||
for i in range(len(self.m)):
|
||||
c1,c2, _,_ = self.im[i].implicit.shape
|
||||
self.m[i].bias *= self.im[i].implicit.reshape(c2)
|
||||
self.m[i].weight *= self.im[i].implicit.transpose(0,1)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
|
||||
def convert(self, z):
|
||||
z = torch.cat(z, 1)
|
||||
box = z[:, :, :4]
|
||||
conf = z[:, :, 4:5]
|
||||
score = z[:, :, 5:]
|
||||
score *= conf
|
||||
convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
|
||||
dtype=torch.float32,
|
||||
device=z.device)
|
||||
box @= convert_matrix
|
||||
return (box, score)
|
||||
|
||||
|
||||
class IBin(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
export = False # onnx export
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=(), bin_count=21): # detection layer
|
||||
super(IBin, self).__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.bin_count = bin_count
|
||||
|
||||
self.w_bin_sigmoid = SigmoidBin(bin_count=self.bin_count, min=0.0, max=4.0)
|
||||
self.h_bin_sigmoid = SigmoidBin(bin_count=self.bin_count, min=0.0, max=4.0)
|
||||
# classes, x,y,obj
|
||||
self.no = nc + 3 + \
|
||||
self.w_bin_sigmoid.get_length() + self.h_bin_sigmoid.get_length() # w-bce, h-bce
|
||||
# + self.x_bin_sigmoid.get_length() + self.y_bin_sigmoid.get_length()
|
||||
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
|
||||
self.register_buffer('anchors', a) # shape(nl,na,2)
|
||||
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
|
||||
|
||||
self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
|
||||
self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch)
|
||||
|
||||
def forward(self, x):
|
||||
|
||||
#self.x_bin_sigmoid.use_fw_regression = True
|
||||
#self.y_bin_sigmoid.use_fw_regression = True
|
||||
self.w_bin_sigmoid.use_fw_regression = True
|
||||
self.h_bin_sigmoid.use_fw_regression = True
|
||||
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
self.training |= self.export
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](self.ia[i](x[i])) # conv
|
||||
x[i] = self.im[i](x[i])
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
#y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
|
||||
|
||||
#px = (self.x_bin_sigmoid.forward(y[..., 0:12]) + self.grid[i][..., 0]) * self.stride[i]
|
||||
#py = (self.y_bin_sigmoid.forward(y[..., 12:24]) + self.grid[i][..., 1]) * self.stride[i]
|
||||
|
||||
pw = self.w_bin_sigmoid.forward(y[..., 2:24]) * self.anchor_grid[i][..., 0]
|
||||
ph = self.h_bin_sigmoid.forward(y[..., 24:46]) * self.anchor_grid[i][..., 1]
|
||||
|
||||
#y[..., 0] = px
|
||||
#y[..., 1] = py
|
||||
y[..., 2] = pw
|
||||
y[..., 3] = ph
|
||||
|
||||
y = torch.cat((y[..., 0:4], y[..., 46:]), dim=-1)
|
||||
|
||||
z.append(y.view(bs, -1, y.shape[-1]))
|
||||
|
||||
return x if self.training else (torch.cat(z, 1), x)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
|
||||
|
||||
class Model(nn.Module):
|
||||
def __init__(self, cfg='yolor-csp-c.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
|
||||
super(Model, self).__init__()
|
||||
self.traced = False
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg) as f:
|
||||
self.yaml = yaml.load(f, Loader=yaml.SafeLoader) # model dict
|
||||
|
||||
# Define model
|
||||
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
|
||||
if nc and nc != self.yaml['nc']:
|
||||
logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
if anchors:
|
||||
logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
|
||||
self.yaml['anchors'] = round(anchors) # override yaml value
|
||||
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
|
||||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
|
||||
# print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
|
||||
|
||||
# Build strides, anchors
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
s = 256 # 2x min stride
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
check_anchor_order(m)
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases() # only run once
|
||||
# print('Strides: %s' % m.stride.tolist())
|
||||
if isinstance(m, IDetect):
|
||||
s = 256 # 2x min stride
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
check_anchor_order(m)
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases() # only run once
|
||||
# print('Strides: %s' % m.stride.tolist())
|
||||
if isinstance(m, IAuxDetect):
|
||||
s = 256 # 2x min stride
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))[:4]]) # forward
|
||||
#print(m.stride)
|
||||
check_anchor_order(m)
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
self.stride = m.stride
|
||||
self._initialize_aux_biases() # only run once
|
||||
# print('Strides: %s' % m.stride.tolist())
|
||||
if isinstance(m, IBin):
|
||||
s = 256 # 2x min stride
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
check_anchor_order(m)
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases_bin() # only run once
|
||||
# print('Strides: %s' % m.stride.tolist())
|
||||
if isinstance(m, IKeypoint):
|
||||
s = 256 # 2x min stride
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
check_anchor_order(m)
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases_kpt() # only run once
|
||||
# print('Strides: %s' % m.stride.tolist())
|
||||
|
||||
# Init weights, biases
|
||||
initialize_weights(self)
|
||||
self.info()
|
||||
logger.info('')
|
||||
|
||||
def forward(self, x, augment=False, profile=False):
|
||||
if augment:
|
||||
img_size = x.shape[-2:] # height, width
|
||||
s = [1, 0.83, 0.67] # scales
|
||||
f = [None, 3, None] # flips (2-ud, 3-lr)
|
||||
y = [] # outputs
|
||||
for si, fi in zip(s, f):
|
||||
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
|
||||
yi = self.forward_once(xi)[0] # forward
|
||||
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
|
||||
yi[..., :4] /= si # de-scale
|
||||
if fi == 2:
|
||||
yi[..., 1] = img_size[0] - yi[..., 1] # de-flip ud
|
||||
elif fi == 3:
|
||||
yi[..., 0] = img_size[1] - yi[..., 0] # de-flip lr
|
||||
y.append(yi)
|
||||
return torch.cat(y, 1), None # augmented inference, train
|
||||
else:
|
||||
return self.forward_once(x, profile) # single-scale inference, train
|
||||
|
||||
def forward_once(self, x, profile=False):
|
||||
y, dt = [], [] # outputs
|
||||
for m in self.model:
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
|
||||
if not hasattr(self, 'traced'):
|
||||
self.traced=False
|
||||
|
||||
if self.traced:
|
||||
if isinstance(m, Detect) or isinstance(m, IDetect) or isinstance(m, IAuxDetect) or isinstance(m, IKeypoint):
|
||||
break
|
||||
|
||||
if profile:
|
||||
c = isinstance(m, (Detect, IDetect, IAuxDetect, IBin))
|
||||
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPS
|
||||
for _ in range(10):
|
||||
m(x.copy() if c else x)
|
||||
t = time_synchronized()
|
||||
for _ in range(10):
|
||||
m(x.copy() if c else x)
|
||||
dt.append((time_synchronized() - t) * 100)
|
||||
print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
|
||||
|
||||
x = m(x) # run
|
||||
|
||||
y.append(x if m.i in self.save else None) # save output
|
||||
|
||||
if profile:
|
||||
print('%.1fms total' % sum(dt))
|
||||
return x
|
||||
|
||||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi, s in zip(m.m, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
|
||||
def _initialize_aux_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi, mi2, s in zip(m.m, m.m2, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
b2 = mi2.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b2.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b2.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi2.bias = torch.nn.Parameter(b2.view(-1), requires_grad=True)
|
||||
|
||||
def _initialize_biases_bin(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Bin() module
|
||||
bc = m.bin_count
|
||||
for mi, s in zip(m.m, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
old = b[:, (0,1,2,bc+3)].data
|
||||
obj_idx = 2*bc+4
|
||||
b[:, :obj_idx].data += math.log(0.6 / (bc + 1 - 0.99))
|
||||
b[:, obj_idx].data += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b[:, (obj_idx+1):].data += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
b[:, (0,1,2,bc+3)].data = old
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
|
||||
def _initialize_biases_kpt(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi, s in zip(m.m, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
|
||||
def _print_biases(self):
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi in m.m: # from
|
||||
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
|
||||
print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
|
||||
|
||||
# def _print_weights(self):
|
||||
# for m in self.model.modules():
|
||||
# if type(m) is Bottleneck:
|
||||
# print('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||||
|
||||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||||
print('Fusing layers... ')
|
||||
for m in self.model.modules():
|
||||
if isinstance(m, RepConv):
|
||||
#print(f" fuse_repvgg_block")
|
||||
m.fuse_repvgg_block()
|
||||
elif isinstance(m, RepConv_OREPA):
|
||||
#print(f" switch_to_deploy")
|
||||
m.switch_to_deploy()
|
||||
elif type(m) is Conv and hasattr(m, 'bn'):
|
||||
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
|
||||
delattr(m, 'bn') # remove batchnorm
|
||||
m.forward = m.fuseforward # update forward
|
||||
elif isinstance(m, (IDetect, IAuxDetect)):
|
||||
m.fuse()
|
||||
m.forward = m.fuseforward
|
||||
self.info()
|
||||
return self
|
||||
|
||||
def nms(self, mode=True): # add or remove NMS module
|
||||
present = type(self.model[-1]) is NMS # last layer is NMS
|
||||
if mode and not present:
|
||||
print('Adding NMS... ')
|
||||
m = NMS() # module
|
||||
m.f = -1 # from
|
||||
m.i = self.model[-1].i + 1 # index
|
||||
self.model.add_module(name='%s' % m.i, module=m) # add
|
||||
self.eval()
|
||||
elif not mode and present:
|
||||
print('Removing NMS... ')
|
||||
self.model = self.model[:-1] # remove
|
||||
return self
|
||||
|
||||
def autoshape(self): # add autoShape module
|
||||
print('Adding autoShape... ')
|
||||
m = autoShape(self) # wrap model
|
||||
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
|
||||
return m
|
||||
|
||||
def info(self, verbose=False, img_size=640): # print model information
|
||||
model_info(self, verbose, img_size)
|
||||
|
||||
|
||||
def parse_model(d, ch): # model_dict, input_channels(3)
|
||||
logger.info('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
try:
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
except:
|
||||
pass
|
||||
|
||||
n = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in [nn.Conv2d, Conv, RobustConv, RobustConv2, DWConv, GhostConv, RepConv, RepConv_OREPA, DownC,
|
||||
SPP, SPPF, SPPCSPC, GhostSPPCSPC, MixConv2d, Focus, Stem, GhostStem, CrossConv,
|
||||
Bottleneck, BottleneckCSPA, BottleneckCSPB, BottleneckCSPC,
|
||||
RepBottleneck, RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC,
|
||||
Res, ResCSPA, ResCSPB, ResCSPC,
|
||||
RepRes, RepResCSPA, RepResCSPB, RepResCSPC,
|
||||
ResX, ResXCSPA, ResXCSPB, ResXCSPC,
|
||||
RepResX, RepResXCSPA, RepResXCSPB, RepResXCSPC,
|
||||
Ghost, GhostCSPA, GhostCSPB, GhostCSPC,
|
||||
SwinTransformerBlock, STCSPA, STCSPB, STCSPC,
|
||||
SwinTransformer2Block, ST2CSPA, ST2CSPB, ST2CSPC]:
|
||||
c1, c2 = ch[f], args[0]
|
||||
if c2 != no: # if not output
|
||||
c2 = make_divisible(c2 * gw, 8)
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [DownC, SPPCSPC, GhostSPPCSPC,
|
||||
BottleneckCSPA, BottleneckCSPB, BottleneckCSPC,
|
||||
RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC,
|
||||
ResCSPA, ResCSPB, ResCSPC,
|
||||
RepResCSPA, RepResCSPB, RepResCSPC,
|
||||
ResXCSPA, ResXCSPB, ResXCSPC,
|
||||
RepResXCSPA, RepResXCSPB, RepResXCSPC,
|
||||
GhostCSPA, GhostCSPB, GhostCSPC,
|
||||
STCSPA, STCSPB, STCSPC,
|
||||
ST2CSPA, ST2CSPB, ST2CSPC]:
|
||||
args.insert(2, n) # number of repeats
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum([ch[x] for x in f])
|
||||
elif m is Chuncat:
|
||||
c2 = sum([ch[x] for x in f])
|
||||
elif m is Shortcut:
|
||||
c2 = ch[f[0]]
|
||||
elif m is Foldcut:
|
||||
c2 = ch[f] // 2
|
||||
elif m in [Detect, IDetect, IAuxDetect, IBin, IKeypoint]:
|
||||
args.append([ch[x] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
elif m is ReOrg:
|
||||
c2 = ch[f] * 4
|
||||
elif m is Contract:
|
||||
c2 = ch[f] * args[0] ** 2
|
||||
elif m is Expand:
|
||||
c2 = ch[f] // args[0] ** 2
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum([x.numel() for x in m_.parameters()]) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
logger.info('%3s%18s%3s%10.0f %-40s%-30s' % (i, f, n, np, t, args)) # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
if i == 0:
|
||||
ch = []
|
||||
ch.append(c2)
|
||||
return nn.Sequential(*layers), sorted(save)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--cfg', type=str, default='yolor-csp-c.yaml', help='model.yaml')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--profile', action='store_true', help='profile model speed')
|
||||
opt = parser.parse_args()
|
||||
opt.cfg = check_file(opt.cfg) # check file
|
||||
set_logging()
|
||||
device = select_device(opt.device)
|
||||
|
||||
# Create model
|
||||
model = Model(opt.cfg).to(device)
|
||||
model.train()
|
||||
|
||||
if opt.profile:
|
||||
img = torch.rand(1, 3, 640, 640).to(device)
|
||||
y = model(img, profile=True)
|
||||
|
||||
# Profile
|
||||
# img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
|
||||
# y = model(img, profile=True)
|
||||
|
||||
# Tensorboard
|
||||
# from torch.utils.tensorboard import SummaryWriter
|
||||
# tb_writer = SummaryWriter()
|
||||
# print("Run 'tensorboard --logdir=models/runs' to view tensorboard at http://localhost:6006/")
|
||||
# tb_writer.add_graph(model.model, img) # add model to tensorboard
|
||||
# tb_writer.add_image('test', img[0], dataformats='CWH') # add model to tensorboard
|
||||
Binary file not shown.
@@ -0,0 +1,39 @@
|
||||
# Usage: pip install -r requirements.txt
|
||||
|
||||
# Base ----------------------------------------
|
||||
matplotlib>=3.2.2
|
||||
numpy>=1.18.5
|
||||
opencv-python>=4.1.1
|
||||
Pillow>=7.1.2
|
||||
PyYAML>=5.3.1
|
||||
requests>=2.23.0
|
||||
scipy>=1.4.1
|
||||
torch>=1.7.0,!=1.12.0
|
||||
torchvision>=0.8.1,!=0.13.0
|
||||
tqdm>=4.41.0
|
||||
protobuf<4.21.3
|
||||
|
||||
# Logging -------------------------------------
|
||||
tensorboard>=2.4.1
|
||||
# wandb
|
||||
|
||||
# Plotting ------------------------------------
|
||||
pandas>=1.1.4
|
||||
seaborn>=0.11.0
|
||||
|
||||
# Export --------------------------------------
|
||||
# coremltools>=4.1 # CoreML export
|
||||
# onnx>=1.9.0 # ONNX export
|
||||
# onnx-simplifier>=0.3.6 # ONNX simplifier
|
||||
# scikit-learn==0.19.2 # CoreML quantization
|
||||
# tensorflow>=2.4.1 # TFLite export
|
||||
# tensorflowjs>=3.9.0 # TF.js export
|
||||
# openvino-dev # OpenVINO export
|
||||
|
||||
# Extras --------------------------------------
|
||||
ipython # interactive notebook
|
||||
psutil # system utilization
|
||||
thop # FLOPs computation
|
||||
# albumentations>=1.0.3
|
||||
# pycocotools>=2.0 # COCO mAP
|
||||
# roboflow
|
||||
@@ -0,0 +1,22 @@
|
||||
#!/bin/bash
|
||||
# COCO 2017 dataset http://cocodataset.org
|
||||
# Download command: bash ./scripts/get_coco.sh
|
||||
|
||||
# Download/unzip labels
|
||||
d='./' # unzip directory
|
||||
url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
|
||||
f='coco2017labels-segments.zip' # or 'coco2017labels.zip', 68 MB
|
||||
echo 'Downloading' $url$f ' ...'
|
||||
curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
|
||||
|
||||
# Download/unzip images
|
||||
d='./coco/images' # unzip directory
|
||||
url=http://images.cocodataset.org/zips/
|
||||
f1='train2017.zip' # 19G, 118k images
|
||||
f2='val2017.zip' # 1G, 5k images
|
||||
f3='test2017.zip' # 7G, 41k images (optional)
|
||||
for f in $f1 $f2 $f3; do
|
||||
echo 'Downloading' $url$f '...'
|
||||
curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
|
||||
done
|
||||
wait # finish background tasks
|
||||
@@ -0,0 +1,353 @@
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
from threading import Thread
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import yaml
|
||||
from tqdm import tqdm
|
||||
|
||||
from models.experimental import attempt_load
|
||||
from utils.datasets import create_dataloader
|
||||
from utils.general import coco80_to_coco91_class, check_dataset, check_file, check_img_size, check_requirements, \
|
||||
box_iou, non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, set_logging, increment_path, colorstr
|
||||
from utils.metrics import ap_per_class, ConfusionMatrix
|
||||
from utils.plots import plot_images, output_to_target, plot_study_txt
|
||||
from utils.torch_utils import select_device, time_synchronized, TracedModel
|
||||
|
||||
|
||||
def test(data,
|
||||
weights=None,
|
||||
batch_size=32,
|
||||
imgsz=640,
|
||||
conf_thres=0.001,
|
||||
iou_thres=0.6, # for NMS
|
||||
save_json=False,
|
||||
single_cls=False,
|
||||
augment=False,
|
||||
verbose=False,
|
||||
model=None,
|
||||
dataloader=None,
|
||||
save_dir=Path(''), # for saving images
|
||||
save_txt=False, # for auto-labelling
|
||||
save_hybrid=False, # for hybrid auto-labelling
|
||||
save_conf=False, # save auto-label confidences
|
||||
plots=True,
|
||||
wandb_logger=None,
|
||||
compute_loss=None,
|
||||
half_precision=True,
|
||||
trace=False,
|
||||
is_coco=False,
|
||||
v5_metric=False):
|
||||
# Initialize/load model and set device
|
||||
training = model is not None
|
||||
if training: # called by train.py
|
||||
device = next(model.parameters()).device # get model device
|
||||
|
||||
else: # called directly
|
||||
set_logging()
|
||||
device = select_device(opt.device, batch_size=batch_size)
|
||||
|
||||
# Directories
|
||||
save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run
|
||||
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||||
|
||||
# Load model
|
||||
model = attempt_load(weights, map_location=device) # load FP32 model
|
||||
gs = max(int(model.stride.max()), 32) # grid size (max stride)
|
||||
imgsz = check_img_size(imgsz, s=gs) # check img_size
|
||||
|
||||
if trace:
|
||||
model = TracedModel(model, device, imgsz)
|
||||
|
||||
# Half
|
||||
half = device.type != 'cpu' and half_precision # half precision only supported on CUDA
|
||||
if half:
|
||||
model.half()
|
||||
|
||||
# Configure
|
||||
model.eval()
|
||||
if isinstance(data, str):
|
||||
is_coco = data.endswith('coco.yaml')
|
||||
with open(data) as f:
|
||||
data = yaml.load(f, Loader=yaml.SafeLoader)
|
||||
check_dataset(data) # check
|
||||
nc = 1 if single_cls else int(data['nc']) # number of classes
|
||||
iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for mAP@0.5:0.95
|
||||
niou = iouv.numel()
|
||||
|
||||
# Logging
|
||||
log_imgs = 0
|
||||
if wandb_logger and wandb_logger.wandb:
|
||||
log_imgs = min(wandb_logger.log_imgs, 100)
|
||||
# Dataloader
|
||||
if not training:
|
||||
if device.type != 'cpu':
|
||||
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
|
||||
task = opt.task if opt.task in ('train', 'val', 'test') else 'val' # path to train/val/test images
|
||||
dataloader = create_dataloader(data[task], imgsz, batch_size, gs, opt, pad=0.5, rect=True,
|
||||
prefix=colorstr(f'{task}: '))[0]
|
||||
|
||||
if v5_metric:
|
||||
print("Testing with YOLOv5 AP metric...")
|
||||
|
||||
seen = 0
|
||||
confusion_matrix = ConfusionMatrix(nc=nc)
|
||||
names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
|
||||
coco91class = coco80_to_coco91_class()
|
||||
s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
|
||||
p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0.
|
||||
loss = torch.zeros(3, device=device)
|
||||
jdict, stats, ap, ap_class, wandb_images = [], [], [], [], []
|
||||
for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
|
||||
img = img.to(device, non_blocking=True)
|
||||
img = img.half() if half else img.float() # uint8 to fp16/32
|
||||
img /= 255.0 # 0 - 255 to 0.0 - 1.0
|
||||
targets = targets.to(device)
|
||||
nb, _, height, width = img.shape # batch size, channels, height, width
|
||||
|
||||
with torch.no_grad():
|
||||
# Run model
|
||||
t = time_synchronized()
|
||||
out, train_out = model(img, augment=augment) # inference and training outputs
|
||||
t0 += time_synchronized() - t
|
||||
|
||||
# Compute loss
|
||||
if compute_loss:
|
||||
loss += compute_loss([x.float() for x in train_out], targets)[1][:3] # box, obj, cls
|
||||
|
||||
# Run NMS
|
||||
targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels
|
||||
lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling
|
||||
t = time_synchronized()
|
||||
out = non_max_suppression(out, conf_thres=conf_thres, iou_thres=iou_thres, labels=lb, multi_label=True)
|
||||
t1 += time_synchronized() - t
|
||||
|
||||
# Statistics per image
|
||||
for si, pred in enumerate(out):
|
||||
labels = targets[targets[:, 0] == si, 1:]
|
||||
nl = len(labels)
|
||||
tcls = labels[:, 0].tolist() if nl else [] # target class
|
||||
path = Path(paths[si])
|
||||
seen += 1
|
||||
|
||||
if len(pred) == 0:
|
||||
if nl:
|
||||
stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
|
||||
continue
|
||||
|
||||
# Predictions
|
||||
predn = pred.clone()
|
||||
scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1]) # native-space pred
|
||||
|
||||
# Append to text file
|
||||
if save_txt:
|
||||
gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]] # normalization gain whwh
|
||||
for *xyxy, conf, cls in predn.tolist():
|
||||
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
||||
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
|
||||
with open(save_dir / 'labels' / (path.stem + '.txt'), 'a') as f:
|
||||
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
||||
|
||||
# W&B logging - Media Panel Plots
|
||||
if len(wandb_images) < log_imgs and wandb_logger.current_epoch > 0: # Check for test operation
|
||||
if wandb_logger.current_epoch % wandb_logger.bbox_interval == 0:
|
||||
box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
|
||||
"class_id": int(cls),
|
||||
"box_caption": "%s %.3f" % (names[cls], conf),
|
||||
"scores": {"class_score": conf},
|
||||
"domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
|
||||
boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space
|
||||
wandb_images.append(wandb_logger.wandb.Image(img[si], boxes=boxes, caption=path.name))
|
||||
wandb_logger.log_training_progress(predn, path, names) if wandb_logger and wandb_logger.wandb_run else None
|
||||
|
||||
# Append to pycocotools JSON dictionary
|
||||
if save_json:
|
||||
# [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
|
||||
image_id = int(path.stem) if path.stem.isnumeric() else path.stem
|
||||
box = xyxy2xywh(predn[:, :4]) # xywh
|
||||
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
|
||||
for p, b in zip(pred.tolist(), box.tolist()):
|
||||
jdict.append({'image_id': image_id,
|
||||
'category_id': coco91class[int(p[5])] if is_coco else int(p[5]),
|
||||
'bbox': [round(x, 3) for x in b],
|
||||
'score': round(p[4], 5)})
|
||||
|
||||
# Assign all predictions as incorrect
|
||||
correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
|
||||
if nl:
|
||||
detected = [] # target indices
|
||||
tcls_tensor = labels[:, 0]
|
||||
|
||||
# target boxes
|
||||
tbox = xywh2xyxy(labels[:, 1:5])
|
||||
scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1]) # native-space labels
|
||||
if plots:
|
||||
confusion_matrix.process_batch(predn, torch.cat((labels[:, 0:1], tbox), 1))
|
||||
|
||||
# Per target class
|
||||
for cls in torch.unique(tcls_tensor):
|
||||
ti = (cls == tcls_tensor).nonzero(as_tuple=False).view(-1) # prediction indices
|
||||
pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view(-1) # target indices
|
||||
|
||||
# Search for detections
|
||||
if pi.shape[0]:
|
||||
# Prediction to target ious
|
||||
ious, i = box_iou(predn[pi, :4], tbox[ti]).max(1) # best ious, indices
|
||||
|
||||
# Append detections
|
||||
detected_set = set()
|
||||
for j in (ious > iouv[0]).nonzero(as_tuple=False):
|
||||
d = ti[i[j]] # detected target
|
||||
if d.item() not in detected_set:
|
||||
detected_set.add(d.item())
|
||||
detected.append(d)
|
||||
correct[pi[j]] = ious[j] > iouv # iou_thres is 1xn
|
||||
if len(detected) == nl: # all targets already located in image
|
||||
break
|
||||
|
||||
# Append statistics (correct, conf, pcls, tcls)
|
||||
stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))
|
||||
|
||||
# Plot images
|
||||
if plots and batch_i < 3:
|
||||
f = save_dir / f'test_batch{batch_i}_labels.jpg' # labels
|
||||
Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start()
|
||||
f = save_dir / f'test_batch{batch_i}_pred.jpg' # predictions
|
||||
Thread(target=plot_images, args=(img, output_to_target(out), paths, f, names), daemon=True).start()
|
||||
|
||||
# Compute statistics
|
||||
stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy
|
||||
if len(stats) and stats[0].any():
|
||||
p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, v5_metric=v5_metric, save_dir=save_dir, names=names)
|
||||
ap50, ap = ap[:, 0], ap.mean(1) # AP@0.5, AP@0.5:0.95
|
||||
mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
|
||||
nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class
|
||||
else:
|
||||
nt = torch.zeros(1)
|
||||
|
||||
# Print results
|
||||
pf = '%20s' + '%12i' * 2 + '%12.3g' * 4 # print format
|
||||
print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
|
||||
|
||||
# Print results per class
|
||||
if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
|
||||
for i, c in enumerate(ap_class):
|
||||
print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
|
||||
|
||||
# Print speeds
|
||||
t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size) # tuple
|
||||
if not training:
|
||||
print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)
|
||||
|
||||
# Plots
|
||||
if plots:
|
||||
confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
|
||||
if wandb_logger and wandb_logger.wandb:
|
||||
val_batches = [wandb_logger.wandb.Image(str(f), caption=f.name) for f in sorted(save_dir.glob('test*.jpg'))]
|
||||
wandb_logger.log({"Validation": val_batches})
|
||||
if wandb_images:
|
||||
wandb_logger.log({"Bounding Box Debugger/Images": wandb_images})
|
||||
|
||||
# Save JSON
|
||||
if save_json and len(jdict):
|
||||
w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else '' # weights
|
||||
anno_json = './coco/annotations/instances_val2017.json' # annotations json
|
||||
pred_json = str(save_dir / f"{w}_predictions.json") # predictions json
|
||||
print('\nEvaluating pycocotools mAP... saving %s...' % pred_json)
|
||||
with open(pred_json, 'w') as f:
|
||||
json.dump(jdict, f)
|
||||
|
||||
try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
|
||||
from pycocotools.coco import COCO
|
||||
from pycocotools.cocoeval import COCOeval
|
||||
|
||||
anno = COCO(anno_json) # init annotations api
|
||||
pred = anno.loadRes(pred_json) # init predictions api
|
||||
eval = COCOeval(anno, pred, 'bbox')
|
||||
if is_coco:
|
||||
eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files] # image IDs to evaluate
|
||||
eval.evaluate()
|
||||
eval.accumulate()
|
||||
eval.summarize()
|
||||
map, map50 = eval.stats[:2] # update results (mAP@0.5:0.95, mAP@0.5)
|
||||
except Exception as e:
|
||||
print(f'pycocotools unable to run: {e}')
|
||||
|
||||
# Return results
|
||||
model.float() # for training
|
||||
if not training:
|
||||
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
|
||||
print(f"Results saved to {save_dir}{s}")
|
||||
maps = np.zeros(nc) + map
|
||||
for i, c in enumerate(ap_class):
|
||||
maps[c] = ap[i]
|
||||
return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(prog='test.py')
|
||||
parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)')
|
||||
parser.add_argument('--data', type=str, default='data/coco.yaml', help='*.data path')
|
||||
parser.add_argument('--batch-size', type=int, default=32, help='size of each image batch')
|
||||
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
|
||||
parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')
|
||||
parser.add_argument('--iou-thres', type=float, default=0.65, help='IOU threshold for NMS')
|
||||
parser.add_argument('--task', default='val', help='train, val, test, speed or study')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
|
||||
parser.add_argument('--augment', action='store_true', help='augmented inference')
|
||||
parser.add_argument('--verbose', action='store_true', help='report mAP by class')
|
||||
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
|
||||
parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
|
||||
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
|
||||
parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
|
||||
parser.add_argument('--project', default='runs/test', help='save to project/name')
|
||||
parser.add_argument('--name', default='exp', help='save to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
parser.add_argument('--no-trace', action='store_true', help='don`t trace model')
|
||||
parser.add_argument('--v5-metric', action='store_true', help='assume maximum recall as 1.0 in AP calculation')
|
||||
opt = parser.parse_args()
|
||||
opt.save_json |= opt.data.endswith('coco.yaml')
|
||||
opt.data = check_file(opt.data) # check file
|
||||
print(opt)
|
||||
#check_requirements()
|
||||
|
||||
if opt.task in ('train', 'val', 'test'): # run normally
|
||||
test(opt.data,
|
||||
opt.weights,
|
||||
opt.batch_size,
|
||||
opt.img_size,
|
||||
opt.conf_thres,
|
||||
opt.iou_thres,
|
||||
opt.save_json,
|
||||
opt.single_cls,
|
||||
opt.augment,
|
||||
opt.verbose,
|
||||
save_txt=opt.save_txt | opt.save_hybrid,
|
||||
save_hybrid=opt.save_hybrid,
|
||||
save_conf=opt.save_conf,
|
||||
trace=not opt.no_trace,
|
||||
v5_metric=opt.v5_metric
|
||||
)
|
||||
|
||||
elif opt.task == 'speed': # speed benchmarks
|
||||
for w in opt.weights:
|
||||
test(opt.data, w, opt.batch_size, opt.img_size, 0.25, 0.45, save_json=False, plots=False, v5_metric=opt.v5_metric)
|
||||
|
||||
elif opt.task == 'study': # run over a range of settings and save/plot
|
||||
# python test.py --task study --data coco.yaml --iou 0.65 --weights yolov7.pt
|
||||
x = list(range(256, 1536 + 128, 128)) # x axis (image sizes)
|
||||
for w in opt.weights:
|
||||
f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt' # filename to save to
|
||||
y = [] # y axis
|
||||
for i in x: # img-size
|
||||
print(f'\nRunning {f} point {i}...')
|
||||
r, _, t = test(opt.data, w, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json,
|
||||
plots=False, v5_metric=opt.v5_metric)
|
||||
y.append(r + t) # results and times
|
||||
np.savetxt(f, y, fmt='%10.4g') # save
|
||||
os.system('zip -r study.zip study_*.txt')
|
||||
plot_study_txt(x=x) # plot
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,538 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d7cbe5ee",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Reparameterization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9725e211",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"### What is Reparameterization ?\n",
|
||||
"Reparameterization is used to reduce trainable BoF modules into deploy model for fast inference. For example merge BN to conv, merge YOLOR to conv, ..etc\n",
|
||||
"However, before reparameterization, the model has more parameters and computation cost.reparameterized model (cfg/deploy) used for deployment purpose\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"### Steps required for model conversion.\n",
|
||||
"1.train custom model & you will get your own weight i.e custom_weight.pt / use (pretrained weight which is available i.e yolov7_traing.pt)\n",
|
||||
"\n",
|
||||
"2.Converting this weight using Reparameterization method.\n",
|
||||
"\n",
|
||||
"3.Trained model (cfg/training) and reparameterized model (cfg/deploy) will get same prediction results.\n",
|
||||
"However, before reparameterization, the model has more parameters and computation cost.\n",
|
||||
"\n",
|
||||
"4.Convert reparameterized weight into onnx & tensorrt\n",
|
||||
"For faster inference & deployment purpose."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "13393b70",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## YOLOv7 reparameterization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bf53becf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import\n",
|
||||
"from copy import deepcopy\n",
|
||||
"from models.yolo import Model\n",
|
||||
"import torch\n",
|
||||
"from utils.torch_utils import select_device, is_parallel\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"device = select_device('0', batch_size=1)\n",
|
||||
"# model trained by cfg/training/*.yaml\n",
|
||||
"ckpt = torch.load('cfg/training/yolov7_training.pt', map_location=device)\n",
|
||||
"# reparameterized model in cfg/deploy/*.yaml\n",
|
||||
"model = Model('cfg/deploy/yolov7.yaml', ch=3, nc=80).to(device)\n",
|
||||
"\n",
|
||||
"with open('cfg/deploy/yolov7.yaml') as f:\n",
|
||||
" yml = yaml.load(f, Loader=yaml.SafeLoader)\n",
|
||||
"anchors = len(yml['anchors'][0]) // 2\n",
|
||||
"\n",
|
||||
"# copy intersect weights\n",
|
||||
"state_dict = ckpt['model'].float().state_dict()\n",
|
||||
"exclude = []\n",
|
||||
"intersect_state_dict = {k: v for k, v in state_dict.items() if k in model.state_dict() and not any(x in k for x in exclude) and v.shape == model.state_dict()[k].shape}\n",
|
||||
"model.load_state_dict(intersect_state_dict, strict=False)\n",
|
||||
"model.names = ckpt['model'].names\n",
|
||||
"model.nc = ckpt['model'].nc\n",
|
||||
"\n",
|
||||
"# reparametrized YOLOR\n",
|
||||
"for i in range((model.nc+5)*anchors):\n",
|
||||
" model.state_dict()['model.105.m.0.weight'].data[i, :, :, :] *= state_dict['model.105.im.0.implicit'].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.105.m.1.weight'].data[i, :, :, :] *= state_dict['model.105.im.1.implicit'].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.105.m.2.weight'].data[i, :, :, :] *= state_dict['model.105.im.2.implicit'].data[:, i, : :].squeeze()\n",
|
||||
"model.state_dict()['model.105.m.0.bias'].data += state_dict['model.105.m.0.weight'].mul(state_dict['model.105.ia.0.implicit']).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.105.m.1.bias'].data += state_dict['model.105.m.1.weight'].mul(state_dict['model.105.ia.1.implicit']).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.105.m.2.bias'].data += state_dict['model.105.m.2.weight'].mul(state_dict['model.105.ia.2.implicit']).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.105.m.0.bias'].data *= state_dict['model.105.im.0.implicit'].data.squeeze()\n",
|
||||
"model.state_dict()['model.105.m.1.bias'].data *= state_dict['model.105.im.1.implicit'].data.squeeze()\n",
|
||||
"model.state_dict()['model.105.m.2.bias'].data *= state_dict['model.105.im.2.implicit'].data.squeeze()\n",
|
||||
"\n",
|
||||
"# model to be saved\n",
|
||||
"ckpt = {'model': deepcopy(model.module if is_parallel(model) else model).half(),\n",
|
||||
" 'optimizer': None,\n",
|
||||
" 'training_results': None,\n",
|
||||
" 'epoch': -1}\n",
|
||||
"\n",
|
||||
"# save reparameterized model\n",
|
||||
"torch.save(ckpt, 'cfg/deploy/yolov7.pt')\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5b396a53",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## YOLOv7x reparameterization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9d54d17f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import\n",
|
||||
"from copy import deepcopy\n",
|
||||
"from models.yolo import Model\n",
|
||||
"import torch\n",
|
||||
"from utils.torch_utils import select_device, is_parallel\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"device = select_device('0', batch_size=1)\n",
|
||||
"# model trained by cfg/training/*.yaml\n",
|
||||
"ckpt = torch.load('cfg/training/yolov7x_trainig.pt', map_location=device)\n",
|
||||
"# reparameterized model in cfg/deploy/*.yaml\n",
|
||||
"model = Model('cfg/deploy/yolov7x.yaml', ch=3, nc=80).to(device)\n",
|
||||
"\n",
|
||||
"with open('cfg/deploy/yolov7x.yaml') as f:\n",
|
||||
" yml = yaml.load(f, Loader=yaml.SafeLoader)\n",
|
||||
"anchors = len(yml['anchors'][0]) // 2\n",
|
||||
"\n",
|
||||
"# copy intersect weights\n",
|
||||
"state_dict = ckpt['model'].float().state_dict()\n",
|
||||
"exclude = []\n",
|
||||
"intersect_state_dict = {k: v for k, v in state_dict.items() if k in model.state_dict() and not any(x in k for x in exclude) and v.shape == model.state_dict()[k].shape}\n",
|
||||
"model.load_state_dict(intersect_state_dict, strict=False)\n",
|
||||
"model.names = ckpt['model'].names\n",
|
||||
"model.nc = ckpt['model'].nc\n",
|
||||
"\n",
|
||||
"# reparametrized YOLOR\n",
|
||||
"for i in range((model.nc+5)*anchors):\n",
|
||||
" model.state_dict()['model.121.m.0.weight'].data[i, :, :, :] *= state_dict['model.121.im.0.implicit'].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.121.m.1.weight'].data[i, :, :, :] *= state_dict['model.121.im.1.implicit'].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.121.m.2.weight'].data[i, :, :, :] *= state_dict['model.121.im.2.implicit'].data[:, i, : :].squeeze()\n",
|
||||
"model.state_dict()['model.121.m.0.bias'].data += state_dict['model.121.m.0.weight'].mul(state_dict['model.121.ia.0.implicit']).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.121.m.1.bias'].data += state_dict['model.121.m.1.weight'].mul(state_dict['model.121.ia.1.implicit']).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.121.m.2.bias'].data += state_dict['model.121.m.2.weight'].mul(state_dict['model.121.ia.2.implicit']).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.121.m.0.bias'].data *= state_dict['model.121.im.0.implicit'].data.squeeze()\n",
|
||||
"model.state_dict()['model.121.m.1.bias'].data *= state_dict['model.121.im.1.implicit'].data.squeeze()\n",
|
||||
"model.state_dict()['model.121.m.2.bias'].data *= state_dict['model.121.im.2.implicit'].data.squeeze()\n",
|
||||
"\n",
|
||||
"# model to be saved\n",
|
||||
"ckpt = {'model': deepcopy(model.module if is_parallel(model) else model).half(),\n",
|
||||
" 'optimizer': None,\n",
|
||||
" 'training_results': None,\n",
|
||||
" 'epoch': -1}\n",
|
||||
"\n",
|
||||
"# save reparameterized model\n",
|
||||
"torch.save(ckpt, 'cfg/deploy/yolov7x.pt')\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "11a9108e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## YOLOv7-W6 reparameterization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d032c629",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import\n",
|
||||
"from copy import deepcopy\n",
|
||||
"from models.yolo import Model\n",
|
||||
"import torch\n",
|
||||
"from utils.torch_utils import select_device, is_parallel\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"device = select_device('0', batch_size=1)\n",
|
||||
"# model trained by cfg/training/*.yaml\n",
|
||||
"ckpt = torch.load('cfg/training/yolov7-w6_trainig.pt', map_location=device)\n",
|
||||
"# reparameterized model in cfg/deploy/*.yaml\n",
|
||||
"model = Model('cfg/deploy/yolov7-w6.yaml', ch=3, nc=80).to(device)\n",
|
||||
"\n",
|
||||
"with open('cfg/deploy/yolov7-w6.yaml') as f:\n",
|
||||
" yml = yaml.load(f, Loader=yaml.SafeLoader)\n",
|
||||
"anchors = len(yml['anchors'][0]) // 2\n",
|
||||
"\n",
|
||||
"# copy intersect weights\n",
|
||||
"state_dict = ckpt['model'].float().state_dict()\n",
|
||||
"exclude = []\n",
|
||||
"intersect_state_dict = {k: v for k, v in state_dict.items() if k in model.state_dict() and not any(x in k for x in exclude) and v.shape == model.state_dict()[k].shape}\n",
|
||||
"model.load_state_dict(intersect_state_dict, strict=False)\n",
|
||||
"model.names = ckpt['model'].names\n",
|
||||
"model.nc = ckpt['model'].nc\n",
|
||||
"\n",
|
||||
"idx = 118\n",
|
||||
"idx2 = 122\n",
|
||||
"\n",
|
||||
"# copy weights of lead head\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data -= model.state_dict()['model.{}.m.0.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data -= model.state_dict()['model.{}.m.1.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data -= model.state_dict()['model.{}.m.2.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data -= model.state_dict()['model.{}.m.3.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data -= model.state_dict()['model.{}.m.0.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data -= model.state_dict()['model.{}.m.1.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data -= model.state_dict()['model.{}.m.2.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data -= model.state_dict()['model.{}.m.3.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.bias'.format(idx2)].data\n",
|
||||
"\n",
|
||||
"# reparametrized YOLOR\n",
|
||||
"for i in range((model.nc+5)*anchors):\n",
|
||||
" model.state_dict()['model.{}.m.0.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.0.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.1.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.1.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.2.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.2.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.3.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.3.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].mul(state_dict['model.{}.ia.0.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].mul(state_dict['model.{}.ia.1.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].mul(state_dict['model.{}.ia.2.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].mul(state_dict['model.{}.ia.3.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data *= state_dict['model.{}.im.0.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data *= state_dict['model.{}.im.1.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data *= state_dict['model.{}.im.2.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data *= state_dict['model.{}.im.3.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"\n",
|
||||
"# model to be saved\n",
|
||||
"ckpt = {'model': deepcopy(model.module if is_parallel(model) else model).half(),\n",
|
||||
" 'optimizer': None,\n",
|
||||
" 'training_results': None,\n",
|
||||
" 'epoch': -1}\n",
|
||||
"\n",
|
||||
"# save reparameterized model\n",
|
||||
"torch.save(ckpt, 'cfg/deploy/yolov7-w6.pt')\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5f093d43",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## YOLOv7-E6 reparameterization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aa2b2142",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import\n",
|
||||
"from copy import deepcopy\n",
|
||||
"from models.yolo import Model\n",
|
||||
"import torch\n",
|
||||
"from utils.torch_utils import select_device, is_parallel\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"device = select_device('0', batch_size=1)\n",
|
||||
"# model trained by cfg/training/*.yaml\n",
|
||||
"ckpt = torch.load('cfg/training/yolov7-e6.pt', map_location=device)\n",
|
||||
"# reparameterized model in cfg/deploy/*.yaml\n",
|
||||
"model = Model('cfg/deploy/yolov7-e6.yaml', ch=3, nc=80).to(device)\n",
|
||||
"\n",
|
||||
"with open('cfg/deploy/yolov7-e6.yaml') as f:\n",
|
||||
" yml = yaml.load(f, Loader=yaml.SafeLoader)\n",
|
||||
"anchors = len(yml['anchors'][0]) // 2\n",
|
||||
"\n",
|
||||
"# copy intersect weights\n",
|
||||
"state_dict = ckpt['model'].float().state_dict()\n",
|
||||
"exclude = []\n",
|
||||
"intersect_state_dict = {k: v for k, v in state_dict.items() if k in model.state_dict() and not any(x in k for x in exclude) and v.shape == model.state_dict()[k].shape}\n",
|
||||
"model.load_state_dict(intersect_state_dict, strict=False)\n",
|
||||
"model.names = ckpt['model'].names\n",
|
||||
"model.nc = ckpt['model'].nc\n",
|
||||
"\n",
|
||||
"idx = 140\n",
|
||||
"idx2 = 144\n",
|
||||
"\n",
|
||||
"# copy weights of lead head\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data -= model.state_dict()['model.{}.m.0.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data -= model.state_dict()['model.{}.m.1.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data -= model.state_dict()['model.{}.m.2.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data -= model.state_dict()['model.{}.m.3.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data -= model.state_dict()['model.{}.m.0.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data -= model.state_dict()['model.{}.m.1.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data -= model.state_dict()['model.{}.m.2.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data -= model.state_dict()['model.{}.m.3.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.bias'.format(idx2)].data\n",
|
||||
"\n",
|
||||
"# reparametrized YOLOR\n",
|
||||
"for i in range((model.nc+5)*anchors):\n",
|
||||
" model.state_dict()['model.{}.m.0.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.0.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.1.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.1.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.2.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.2.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.3.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.3.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].mul(state_dict['model.{}.ia.0.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].mul(state_dict['model.{}.ia.1.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].mul(state_dict['model.{}.ia.2.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].mul(state_dict['model.{}.ia.3.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data *= state_dict['model.{}.im.0.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data *= state_dict['model.{}.im.1.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data *= state_dict['model.{}.im.2.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data *= state_dict['model.{}.im.3.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"\n",
|
||||
"# model to be saved\n",
|
||||
"ckpt = {'model': deepcopy(model.module if is_parallel(model) else model).half(),\n",
|
||||
" 'optimizer': None,\n",
|
||||
" 'training_results': None,\n",
|
||||
" 'epoch': -1}\n",
|
||||
"\n",
|
||||
"# save reparameterized model\n",
|
||||
"torch.save(ckpt, 'cfg/deploy/yolov7-e6.pt')\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a3bccf89",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## YOLOv7-D6 reparameterization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e5216b70",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import\n",
|
||||
"from copy import deepcopy\n",
|
||||
"from models.yolo import Model\n",
|
||||
"import torch\n",
|
||||
"from utils.torch_utils import select_device, is_parallel\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"device = select_device('0', batch_size=1)\n",
|
||||
"# model trained by cfg/training/*.yaml\n",
|
||||
"ckpt = torch.load('cfg/training/yolov7-d6_trainig.pt', map_location=device)\n",
|
||||
"# reparameterized model in cfg/deploy/*.yaml\n",
|
||||
"model = Model('cfg/deploy/yolov7-d6.yaml', ch=3, nc=80).to(device)\n",
|
||||
"\n",
|
||||
"with open('cfg/deploy/yolov7-d6.yaml') as f:\n",
|
||||
" yml = yaml.load(f, Loader=yaml.SafeLoader)\n",
|
||||
"anchors = len(yml['anchors'][0]) // 2\n",
|
||||
"\n",
|
||||
"# copy intersect weights\n",
|
||||
"state_dict = ckpt['model'].float().state_dict()\n",
|
||||
"exclude = []\n",
|
||||
"intersect_state_dict = {k: v for k, v in state_dict.items() if k in model.state_dict() and not any(x in k for x in exclude) and v.shape == model.state_dict()[k].shape}\n",
|
||||
"model.load_state_dict(intersect_state_dict, strict=False)\n",
|
||||
"model.names = ckpt['model'].names\n",
|
||||
"model.nc = ckpt['model'].nc\n",
|
||||
"\n",
|
||||
"idx = 162\n",
|
||||
"idx2 = 166\n",
|
||||
"\n",
|
||||
"# copy weights of lead head\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data -= model.state_dict()['model.{}.m.0.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data -= model.state_dict()['model.{}.m.1.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data -= model.state_dict()['model.{}.m.2.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data -= model.state_dict()['model.{}.m.3.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data -= model.state_dict()['model.{}.m.0.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data -= model.state_dict()['model.{}.m.1.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data -= model.state_dict()['model.{}.m.2.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data -= model.state_dict()['model.{}.m.3.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.bias'.format(idx2)].data\n",
|
||||
"\n",
|
||||
"# reparametrized YOLOR\n",
|
||||
"for i in range((model.nc+5)*anchors):\n",
|
||||
" model.state_dict()['model.{}.m.0.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.0.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.1.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.1.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.2.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.2.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.3.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.3.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].mul(state_dict['model.{}.ia.0.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].mul(state_dict['model.{}.ia.1.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].mul(state_dict['model.{}.ia.2.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].mul(state_dict['model.{}.ia.3.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data *= state_dict['model.{}.im.0.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data *= state_dict['model.{}.im.1.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data *= state_dict['model.{}.im.2.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data *= state_dict['model.{}.im.3.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"\n",
|
||||
"# model to be saved\n",
|
||||
"ckpt = {'model': deepcopy(model.module if is_parallel(model) else model).half(),\n",
|
||||
" 'optimizer': None,\n",
|
||||
" 'training_results': None,\n",
|
||||
" 'epoch': -1}\n",
|
||||
"\n",
|
||||
"# save reparameterized model\n",
|
||||
"torch.save(ckpt, 'cfg/deploy/yolov7-d6.pt')\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "334c273b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## YOLOv7-E6E reparameterization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "635fd8d2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import\n",
|
||||
"from copy import deepcopy\n",
|
||||
"from models.yolo import Model\n",
|
||||
"import torch\n",
|
||||
"from utils.torch_utils import select_device, is_parallel\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"device = select_device('0', batch_size=1)\n",
|
||||
"# model trained by cfg/training/*.yaml\n",
|
||||
"ckpt = torch.load('cfg/training/yolov7-e6e_trainig.pt', map_location=device)\n",
|
||||
"# reparameterized model in cfg/deploy/*.yaml\n",
|
||||
"model = Model('cfg/deploy/yolov7-e6e.yaml', ch=3, nc=80).to(device)\n",
|
||||
"\n",
|
||||
"with open('cfg/deploy/yolov7-e6e.yaml') as f:\n",
|
||||
" yml = yaml.load(f, Loader=yaml.SafeLoader)\n",
|
||||
"anchors = len(yml['anchors'][0]) // 2)\n",
|
||||
"\n",
|
||||
"# copy intersect weights\n",
|
||||
"state_dict = ckpt['model'].float().state_dict()\n",
|
||||
"exclude = []\n",
|
||||
"intersect_state_dict = {k: v for k, v in state_dict.items() if k in model.state_dict() and not any(x in k for x in exclude) and v.shape == model.state_dict()[k].shape}\n",
|
||||
"model.load_state_dict(intersect_state_dict, strict=False)\n",
|
||||
"model.names = ckpt['model'].names\n",
|
||||
"model.nc = ckpt['model'].nc\n",
|
||||
"\n",
|
||||
"idx = 261\n",
|
||||
"idx2 = 265\n",
|
||||
"\n",
|
||||
"# copy weights of lead head\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data -= model.state_dict()['model.{}.m.0.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data -= model.state_dict()['model.{}.m.1.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data -= model.state_dict()['model.{}.m.2.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data -= model.state_dict()['model.{}.m.3.weight'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.weight'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.weight'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.weight'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.weight'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data -= model.state_dict()['model.{}.m.0.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data -= model.state_dict()['model.{}.m.1.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data -= model.state_dict()['model.{}.m.2.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data -= model.state_dict()['model.{}.m.3.bias'.format(idx)].data\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.bias'.format(idx2)].data\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.bias'.format(idx2)].data\n",
|
||||
"\n",
|
||||
"# reparametrized YOLOR\n",
|
||||
"for i in range((model.nc+5)*anchors):\n",
|
||||
" model.state_dict()['model.{}.m.0.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.0.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.1.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.1.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.2.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.2.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
" model.state_dict()['model.{}.m.3.weight'.format(idx)].data[i, :, :, :] *= state_dict['model.{}.im.3.implicit'.format(idx2)].data[:, i, : :].squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data += state_dict['model.{}.m.0.weight'.format(idx2)].mul(state_dict['model.{}.ia.0.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data += state_dict['model.{}.m.1.weight'.format(idx2)].mul(state_dict['model.{}.ia.1.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data += state_dict['model.{}.m.2.weight'.format(idx2)].mul(state_dict['model.{}.ia.2.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data += state_dict['model.{}.m.3.weight'.format(idx2)].mul(state_dict['model.{}.ia.3.implicit'.format(idx2)]).sum(1).squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.0.bias'.format(idx)].data *= state_dict['model.{}.im.0.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.1.bias'.format(idx)].data *= state_dict['model.{}.im.1.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.2.bias'.format(idx)].data *= state_dict['model.{}.im.2.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"model.state_dict()['model.{}.m.3.bias'.format(idx)].data *= state_dict['model.{}.im.3.implicit'.format(idx2)].data.squeeze()\n",
|
||||
"\n",
|
||||
"# model to be saved\n",
|
||||
"ckpt = {'model': deepcopy(model.module if is_parallel(model) else model).half(),\n",
|
||||
" 'optimizer': None,\n",
|
||||
" 'training_results': None,\n",
|
||||
" 'epoch': -1}\n",
|
||||
"\n",
|
||||
"# save reparameterized model\n",
|
||||
"torch.save(ckpt, 'cfg/deploy/yolov7-e6e.pt')\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "63a62625",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.7"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "73080970ff6fd25f9fcdf9c6f9e85b950a97864bb936ee53fb633f473cbfae4b"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,705 @@
|
||||
import argparse
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
import time
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
from threading import Thread
|
||||
|
||||
import numpy as np
|
||||
import torch.distributed as dist
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torch.optim as optim
|
||||
import torch.optim.lr_scheduler as lr_scheduler
|
||||
import torch.utils.data
|
||||
import yaml
|
||||
from torch.cuda import amp
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
from torch.utils.tensorboard import SummaryWriter
|
||||
from tqdm import tqdm
|
||||
|
||||
import test # import test.py to get mAP after each epoch
|
||||
from models.experimental import attempt_load
|
||||
from models.yolo import Model
|
||||
from utils.autoanchor import check_anchors
|
||||
from utils.datasets import create_dataloader
|
||||
from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
|
||||
fitness, strip_optimizer, get_latest_run, check_dataset, check_file, check_git_status, check_img_size, \
|
||||
check_requirements, print_mutation, set_logging, one_cycle, colorstr
|
||||
from utils.google_utils import attempt_download
|
||||
from utils.loss import ComputeLoss, ComputeLossOTA
|
||||
from utils.plots import plot_images, plot_labels, plot_results, plot_evolution
|
||||
from utils.torch_utils import ModelEMA, select_device, intersect_dicts, torch_distributed_zero_first, is_parallel
|
||||
from utils.wandb_logging.wandb_utils import WandbLogger, check_wandb_resume
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def train(hyp, opt, device, tb_writer=None):
|
||||
logger.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
|
||||
save_dir, epochs, batch_size, total_batch_size, weights, rank, freeze = \
|
||||
Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank, opt.freeze
|
||||
|
||||
# Directories
|
||||
wdir = save_dir / 'weights'
|
||||
wdir.mkdir(parents=True, exist_ok=True) # make dir
|
||||
last = wdir / 'last.pt'
|
||||
best = wdir / 'best.pt'
|
||||
results_file = save_dir / 'results.txt'
|
||||
|
||||
# Save run settings
|
||||
with open(save_dir / 'hyp.yaml', 'w') as f:
|
||||
yaml.dump(hyp, f, sort_keys=False)
|
||||
with open(save_dir / 'opt.yaml', 'w') as f:
|
||||
yaml.dump(vars(opt), f, sort_keys=False)
|
||||
|
||||
# Configure
|
||||
plots = not opt.evolve # create plots
|
||||
cuda = device.type != 'cpu'
|
||||
init_seeds(2 + rank)
|
||||
with open(opt.data) as f:
|
||||
data_dict = yaml.load(f, Loader=yaml.SafeLoader) # data dict
|
||||
is_coco = opt.data.endswith('coco.yaml')
|
||||
|
||||
# Logging- Doing this before checking the dataset. Might update data_dict
|
||||
loggers = {'wandb': None} # loggers dict
|
||||
if rank in [-1, 0]:
|
||||
opt.hyp = hyp # add hyperparameters
|
||||
run_id = torch.load(weights, map_location=device).get('wandb_id') if weights.endswith('.pt') and os.path.isfile(weights) else None
|
||||
wandb_logger = WandbLogger(opt, Path(opt.save_dir).stem, run_id, data_dict)
|
||||
loggers['wandb'] = wandb_logger.wandb
|
||||
data_dict = wandb_logger.data_dict
|
||||
if wandb_logger.wandb:
|
||||
weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp # WandbLogger might update weights, epochs if resuming
|
||||
|
||||
nc = 1 if opt.single_cls else int(data_dict['nc']) # number of classes
|
||||
names = ['item'] if opt.single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names
|
||||
assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, opt.data) # check
|
||||
|
||||
# Model
|
||||
pretrained = weights.endswith('.pt')
|
||||
if pretrained:
|
||||
with torch_distributed_zero_first(rank):
|
||||
attempt_download(weights) # download if not found locally
|
||||
ckpt = torch.load(weights, map_location=device) # load checkpoint
|
||||
model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
|
||||
exclude = ['anchor'] if (opt.cfg or hyp.get('anchors')) and not opt.resume else [] # exclude keys
|
||||
state_dict = ckpt['model'].float().state_dict() # to FP32
|
||||
state_dict = intersect_dicts(state_dict, model.state_dict(), exclude=exclude) # intersect
|
||||
model.load_state_dict(state_dict, strict=False) # load
|
||||
logger.info('Transferred %g/%g items from %s' % (len(state_dict), len(model.state_dict()), weights)) # report
|
||||
else:
|
||||
model = Model(opt.cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
|
||||
with torch_distributed_zero_first(rank):
|
||||
check_dataset(data_dict) # check
|
||||
train_path = data_dict['train']
|
||||
test_path = data_dict['val']
|
||||
|
||||
# Freeze
|
||||
freeze = [f'model.{x}.' for x in (freeze if len(freeze) > 1 else range(freeze[0]))] # parameter names to freeze (full or partial)
|
||||
for k, v in model.named_parameters():
|
||||
v.requires_grad = True # train all layers
|
||||
if any(x in k for x in freeze):
|
||||
print('freezing %s' % k)
|
||||
v.requires_grad = False
|
||||
|
||||
# Optimizer
|
||||
nbs = 64 # nominal batch size
|
||||
accumulate = max(round(nbs / total_batch_size), 1) # accumulate loss before optimizing
|
||||
hyp['weight_decay'] *= total_batch_size * accumulate / nbs # scale weight_decay
|
||||
logger.info(f"Scaled weight_decay = {hyp['weight_decay']}")
|
||||
|
||||
pg0, pg1, pg2 = [], [], [] # optimizer parameter groups
|
||||
for k, v in model.named_modules():
|
||||
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
|
||||
pg2.append(v.bias) # biases
|
||||
if isinstance(v, nn.BatchNorm2d):
|
||||
pg0.append(v.weight) # no decay
|
||||
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
|
||||
pg1.append(v.weight) # apply decay
|
||||
if hasattr(v, 'im'):
|
||||
if hasattr(v.im, 'implicit'):
|
||||
pg0.append(v.im.implicit)
|
||||
else:
|
||||
for iv in v.im:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'imc'):
|
||||
if hasattr(v.imc, 'implicit'):
|
||||
pg0.append(v.imc.implicit)
|
||||
else:
|
||||
for iv in v.imc:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'imb'):
|
||||
if hasattr(v.imb, 'implicit'):
|
||||
pg0.append(v.imb.implicit)
|
||||
else:
|
||||
for iv in v.imb:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'imo'):
|
||||
if hasattr(v.imo, 'implicit'):
|
||||
pg0.append(v.imo.implicit)
|
||||
else:
|
||||
for iv in v.imo:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'ia'):
|
||||
if hasattr(v.ia, 'implicit'):
|
||||
pg0.append(v.ia.implicit)
|
||||
else:
|
||||
for iv in v.ia:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'attn'):
|
||||
if hasattr(v.attn, 'logit_scale'):
|
||||
pg0.append(v.attn.logit_scale)
|
||||
if hasattr(v.attn, 'q_bias'):
|
||||
pg0.append(v.attn.q_bias)
|
||||
if hasattr(v.attn, 'v_bias'):
|
||||
pg0.append(v.attn.v_bias)
|
||||
if hasattr(v.attn, 'relative_position_bias_table'):
|
||||
pg0.append(v.attn.relative_position_bias_table)
|
||||
if hasattr(v, 'rbr_dense'):
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_origin'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_origin)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_avg_conv'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_avg_conv)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_pfir_conv'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_pfir_conv)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_1x1_kxk_idconv1'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_1x1_kxk_idconv1)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_1x1_kxk_conv2'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_1x1_kxk_conv2)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_gconv_dw'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_gconv_dw)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_gconv_pw'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_gconv_pw)
|
||||
if hasattr(v.rbr_dense, 'vector'):
|
||||
pg0.append(v.rbr_dense.vector)
|
||||
|
||||
if opt.adam:
|
||||
optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
|
||||
else:
|
||||
optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
|
||||
|
||||
optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']}) # add pg1 with weight_decay
|
||||
optimizer.add_param_group({'params': pg2}) # add pg2 (biases)
|
||||
logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
|
||||
del pg0, pg1, pg2
|
||||
|
||||
# Scheduler https://arxiv.org/pdf/1812.01187.pdf
|
||||
# https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
|
||||
if opt.linear_lr:
|
||||
lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear
|
||||
else:
|
||||
lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf']
|
||||
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
|
||||
# plot_lr_scheduler(optimizer, scheduler, epochs)
|
||||
|
||||
# EMA
|
||||
ema = ModelEMA(model) if rank in [-1, 0] else None
|
||||
|
||||
# Resume
|
||||
start_epoch, best_fitness = 0, 0.0
|
||||
if pretrained:
|
||||
# Optimizer
|
||||
if ckpt['optimizer'] is not None:
|
||||
optimizer.load_state_dict(ckpt['optimizer'])
|
||||
best_fitness = ckpt['best_fitness']
|
||||
|
||||
# EMA
|
||||
if ema and ckpt.get('ema'):
|
||||
ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
|
||||
ema.updates = ckpt['updates']
|
||||
|
||||
# Results
|
||||
if ckpt.get('training_results') is not None:
|
||||
results_file.write_text(ckpt['training_results']) # write results.txt
|
||||
|
||||
# Epochs
|
||||
start_epoch = ckpt['epoch'] + 1
|
||||
if opt.resume:
|
||||
assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (weights, epochs)
|
||||
if epochs < start_epoch:
|
||||
logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
|
||||
(weights, ckpt['epoch'], epochs))
|
||||
epochs += ckpt['epoch'] # finetune additional epochs
|
||||
|
||||
del ckpt, state_dict
|
||||
|
||||
# Image sizes
|
||||
gs = max(int(model.stride.max()), 32) # grid size (max stride)
|
||||
nl = model.model[-1].nl # number of detection layers (used for scaling hyp['obj'])
|
||||
imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size] # verify imgsz are gs-multiples
|
||||
|
||||
# DP mode
|
||||
if cuda and rank == -1 and torch.cuda.device_count() > 1:
|
||||
model = torch.nn.DataParallel(model)
|
||||
|
||||
# SyncBatchNorm
|
||||
if opt.sync_bn and cuda and rank != -1:
|
||||
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
|
||||
logger.info('Using SyncBatchNorm()')
|
||||
|
||||
# Trainloader
|
||||
dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt,
|
||||
hyp=hyp, augment=True, cache=opt.cache_images, rect=opt.rect, rank=rank,
|
||||
world_size=opt.world_size, workers=opt.workers,
|
||||
image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '))
|
||||
mlc = np.concatenate(dataset.labels, 0)[:, 0].max() # max label class
|
||||
nb = len(dataloader) # number of batches
|
||||
assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, opt.data, nc - 1)
|
||||
|
||||
# Process 0
|
||||
if rank in [-1, 0]:
|
||||
testloader = create_dataloader(test_path, imgsz_test, batch_size * 2, gs, opt, # testloader
|
||||
hyp=hyp, cache=opt.cache_images and not opt.notest, rect=True, rank=-1,
|
||||
world_size=opt.world_size, workers=opt.workers,
|
||||
pad=0.5, prefix=colorstr('val: '))[0]
|
||||
|
||||
if not opt.resume:
|
||||
labels = np.concatenate(dataset.labels, 0)
|
||||
c = torch.tensor(labels[:, 0]) # classes
|
||||
# cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency
|
||||
# model._initialize_biases(cf.to(device))
|
||||
if plots:
|
||||
#plot_labels(labels, names, save_dir, loggers)
|
||||
if tb_writer:
|
||||
tb_writer.add_histogram('classes', c, 0)
|
||||
|
||||
# Anchors
|
||||
if not opt.noautoanchor:
|
||||
check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
|
||||
model.half().float() # pre-reduce anchor precision
|
||||
|
||||
# DDP mode
|
||||
if cuda and rank != -1:
|
||||
model = DDP(model, device_ids=[opt.local_rank], output_device=opt.local_rank,
|
||||
# nn.MultiheadAttention incompatibility with DDP https://github.com/pytorch/pytorch/issues/26698
|
||||
find_unused_parameters=any(isinstance(layer, nn.MultiheadAttention) for layer in model.modules()))
|
||||
|
||||
# Model parameters
|
||||
hyp['box'] *= 3. / nl # scale to layers
|
||||
hyp['cls'] *= nc / 80. * 3. / nl # scale to classes and layers
|
||||
hyp['obj'] *= (imgsz / 640) ** 2 * 3. / nl # scale to image size and layers
|
||||
hyp['label_smoothing'] = opt.label_smoothing
|
||||
model.nc = nc # attach number of classes to model
|
||||
model.hyp = hyp # attach hyperparameters to model
|
||||
model.gr = 1.0 # iou loss ratio (obj_loss = 1.0 or iou)
|
||||
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights
|
||||
model.names = names
|
||||
|
||||
# Start training
|
||||
t0 = time.time()
|
||||
nw = max(round(hyp['warmup_epochs'] * nb), 1000) # number of warmup iterations, max(3 epochs, 1k iterations)
|
||||
# nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
|
||||
maps = np.zeros(nc) # mAP per class
|
||||
results = (0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
|
||||
scheduler.last_epoch = start_epoch - 1 # do not move
|
||||
scaler = amp.GradScaler(enabled=cuda)
|
||||
compute_loss_ota = ComputeLossOTA(model) # init loss class
|
||||
compute_loss = ComputeLoss(model) # init loss class
|
||||
logger.info(f'Image sizes {imgsz} train, {imgsz_test} test\n'
|
||||
f'Using {dataloader.num_workers} dataloader workers\n'
|
||||
f'Logging results to {save_dir}\n'
|
||||
f'Starting training for {epochs} epochs...')
|
||||
torch.save(model, wdir / 'init.pt')
|
||||
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
|
||||
model.train()
|
||||
|
||||
# Update image weights (optional)
|
||||
if opt.image_weights:
|
||||
# Generate indices
|
||||
if rank in [-1, 0]:
|
||||
cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights
|
||||
iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights
|
||||
dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx
|
||||
# Broadcast if DDP
|
||||
if rank != -1:
|
||||
indices = (torch.tensor(dataset.indices) if rank == 0 else torch.zeros(dataset.n)).int()
|
||||
dist.broadcast(indices, 0)
|
||||
if rank != 0:
|
||||
dataset.indices = indices.cpu().numpy()
|
||||
|
||||
# Update mosaic border
|
||||
# b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
|
||||
# dataset.mosaic_border = [b - imgsz, -b] # height, width borders
|
||||
|
||||
mloss = torch.zeros(4, device=device) # mean losses
|
||||
if rank != -1:
|
||||
dataloader.sampler.set_epoch(epoch)
|
||||
pbar = enumerate(dataloader)
|
||||
logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'labels', 'img_size'))
|
||||
if rank in [-1, 0]:
|
||||
pbar = tqdm(pbar, total=nb) # progress bar
|
||||
optimizer.zero_grad()
|
||||
for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
|
||||
ni = i + nb * epoch # number integrated batches (since train start)
|
||||
imgs = imgs.to(device, non_blocking=True).float() / 255.0 # uint8 to float32, 0-255 to 0.0-1.0
|
||||
|
||||
# Warmup
|
||||
if ni <= nw:
|
||||
xi = [0, nw] # x interp
|
||||
# model.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
|
||||
accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
|
||||
for j, x in enumerate(optimizer.param_groups):
|
||||
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
|
||||
x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
|
||||
if 'momentum' in x:
|
||||
x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
|
||||
|
||||
# Multi-scale
|
||||
if opt.multi_scale:
|
||||
sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size
|
||||
sf = sz / max(imgs.shape[2:]) # scale factor
|
||||
if sf != 1:
|
||||
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
|
||||
imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
|
||||
|
||||
# Forward
|
||||
with amp.autocast(enabled=cuda):
|
||||
pred = model(imgs) # forward
|
||||
if 'loss_ota' not in hyp or hyp['loss_ota'] == 1:
|
||||
loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) # loss scaled by batch_size
|
||||
else:
|
||||
loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size
|
||||
if rank != -1:
|
||||
loss *= opt.world_size # gradient averaged between devices in DDP mode
|
||||
if opt.quad:
|
||||
loss *= 4.
|
||||
|
||||
# Backward
|
||||
scaler.scale(loss).backward()
|
||||
|
||||
# Optimize
|
||||
if ni % accumulate == 0:
|
||||
scaler.step(optimizer) # optimizer.step
|
||||
scaler.update()
|
||||
optimizer.zero_grad()
|
||||
if ema:
|
||||
ema.update(model)
|
||||
|
||||
# Print
|
||||
if rank in [-1, 0]:
|
||||
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
|
||||
mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0) # (GB)
|
||||
s = ('%10s' * 2 + '%10.4g' * 6) % (
|
||||
'%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
|
||||
pbar.set_description(s)
|
||||
|
||||
# Plot
|
||||
if plots and ni < 10:
|
||||
f = save_dir / f'train_batch{ni}.jpg' # filename
|
||||
Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
|
||||
# if tb_writer:
|
||||
# tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
|
||||
# tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), []) # add model graph
|
||||
elif plots and ni == 10 and wandb_logger.wandb:
|
||||
wandb_logger.log({"Mosaics": [wandb_logger.wandb.Image(str(x), caption=x.name) for x in
|
||||
save_dir.glob('train*.jpg') if x.exists()]})
|
||||
|
||||
# end batch ------------------------------------------------------------------------------------------------
|
||||
# end epoch ----------------------------------------------------------------------------------------------------
|
||||
|
||||
# Scheduler
|
||||
lr = [x['lr'] for x in optimizer.param_groups] # for tensorboard
|
||||
scheduler.step()
|
||||
|
||||
# DDP process 0 or single-GPU
|
||||
if rank in [-1, 0]:
|
||||
# mAP
|
||||
ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride', 'class_weights'])
|
||||
final_epoch = epoch + 1 == epochs
|
||||
if not opt.notest or final_epoch: # Calculate mAP
|
||||
wandb_logger.current_epoch = epoch + 1
|
||||
results, maps, times = test.test(data_dict,
|
||||
batch_size=batch_size * 2,
|
||||
imgsz=imgsz_test,
|
||||
model=ema.ema,
|
||||
single_cls=opt.single_cls,
|
||||
dataloader=testloader,
|
||||
save_dir=save_dir,
|
||||
verbose=nc < 50 and final_epoch,
|
||||
plots=plots and final_epoch,
|
||||
wandb_logger=wandb_logger,
|
||||
compute_loss=compute_loss,
|
||||
is_coco=is_coco,
|
||||
v5_metric=opt.v5_metric)
|
||||
|
||||
# Write
|
||||
with open(results_file, 'a') as f:
|
||||
f.write(s + '%10.4g' * 7 % results + '\n') # append metrics, val_loss
|
||||
if len(opt.name) and opt.bucket:
|
||||
os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name))
|
||||
|
||||
# Log
|
||||
tags = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', # train loss
|
||||
'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
|
||||
'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss
|
||||
'x/lr0', 'x/lr1', 'x/lr2'] # params
|
||||
for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags):
|
||||
if tb_writer:
|
||||
tb_writer.add_scalar(tag, x, epoch) # tensorboard
|
||||
if wandb_logger.wandb:
|
||||
wandb_logger.log({tag: x}) # W&B
|
||||
|
||||
# Update best mAP
|
||||
fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
|
||||
if fi > best_fitness:
|
||||
best_fitness = fi
|
||||
wandb_logger.end_epoch(best_result=best_fitness == fi)
|
||||
|
||||
# Save model
|
||||
if (not opt.nosave) or (final_epoch and not opt.evolve): # if save
|
||||
ckpt = {'epoch': epoch,
|
||||
'best_fitness': best_fitness,
|
||||
'training_results': results_file.read_text(),
|
||||
'model': deepcopy(model.module if is_parallel(model) else model).half(),
|
||||
'ema': deepcopy(ema.ema).half(),
|
||||
'updates': ema.updates,
|
||||
'optimizer': optimizer.state_dict(),
|
||||
'wandb_id': wandb_logger.wandb_run.id if wandb_logger.wandb else None}
|
||||
|
||||
# Save last, best and delete
|
||||
torch.save(ckpt, last)
|
||||
if best_fitness == fi:
|
||||
torch.save(ckpt, best)
|
||||
if (best_fitness == fi) and (epoch >= 200):
|
||||
torch.save(ckpt, wdir / 'best_{:03d}.pt'.format(epoch))
|
||||
if epoch == 0:
|
||||
torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
|
||||
elif ((epoch+1) % 25) == 0:
|
||||
torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
|
||||
elif epoch >= (epochs-5):
|
||||
torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
|
||||
if wandb_logger.wandb:
|
||||
if ((epoch + 1) % opt.save_period == 0 and not final_epoch) and opt.save_period != -1:
|
||||
wandb_logger.log_model(
|
||||
last.parent, opt, epoch, fi, best_model=best_fitness == fi)
|
||||
del ckpt
|
||||
|
||||
# end epoch ----------------------------------------------------------------------------------------------------
|
||||
# end training
|
||||
if rank in [-1, 0]:
|
||||
# Plots
|
||||
if plots:
|
||||
plot_results(save_dir=save_dir) # save as results.png
|
||||
if wandb_logger.wandb:
|
||||
files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
|
||||
wandb_logger.log({"Results": [wandb_logger.wandb.Image(str(save_dir / f), caption=f) for f in files
|
||||
if (save_dir / f).exists()]})
|
||||
# Test best.pt
|
||||
logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
|
||||
if opt.data.endswith('coco.yaml') and nc == 80: # if COCO
|
||||
for m in (last, best) if best.exists() else (last): # speed, mAP tests
|
||||
results, _, _ = test.test(opt.data,
|
||||
batch_size=batch_size * 2,
|
||||
imgsz=imgsz_test,
|
||||
conf_thres=0.001,
|
||||
iou_thres=0.7,
|
||||
model=attempt_load(m, device).half(),
|
||||
single_cls=opt.single_cls,
|
||||
dataloader=testloader,
|
||||
save_dir=save_dir,
|
||||
save_json=True,
|
||||
plots=False,
|
||||
is_coco=is_coco,
|
||||
v5_metric=opt.v5_metric)
|
||||
|
||||
# Strip optimizers
|
||||
final = best if best.exists() else last # final model
|
||||
for f in last, best:
|
||||
if f.exists():
|
||||
strip_optimizer(f) # strip optimizers
|
||||
if opt.bucket:
|
||||
os.system(f'gsutil cp {final} gs://{opt.bucket}/weights') # upload
|
||||
if wandb_logger.wandb and not opt.evolve: # Log the stripped model
|
||||
wandb_logger.wandb.log_artifact(str(final), type='model',
|
||||
name='run_' + wandb_logger.wandb_run.id + '_model',
|
||||
aliases=['last', 'best', 'stripped'])
|
||||
wandb_logger.finish_run()
|
||||
else:
|
||||
dist.destroy_process_group()
|
||||
torch.cuda.empty_cache()
|
||||
return results
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default='yolo7.pt', help='initial weights path')
|
||||
parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
|
||||
parser.add_argument('--data', type=str, default='data/coco.yaml', help='data.yaml path')
|
||||
parser.add_argument('--hyp', type=str, default='data/hyp.scratch.p5.yaml', help='hyperparameters path')
|
||||
parser.add_argument('--epochs', type=int, default=300)
|
||||
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
|
||||
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')
|
||||
parser.add_argument('--rect', action='store_true', help='rectangular training')
|
||||
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
|
||||
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
|
||||
parser.add_argument('--notest', action='store_true', help='only test final epoch')
|
||||
parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
|
||||
parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
|
||||
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
|
||||
parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
|
||||
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
|
||||
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
|
||||
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
|
||||
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
|
||||
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
|
||||
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
|
||||
parser.add_argument('--project', default='runs/train', help='save to project/name')
|
||||
parser.add_argument('--entity', default=None, help='W&B entity')
|
||||
parser.add_argument('--name', default='exp', help='save to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
parser.add_argument('--quad', action='store_true', help='quad dataloader')
|
||||
parser.add_argument('--linear-lr', action='store_true', help='linear LR')
|
||||
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
|
||||
parser.add_argument('--upload_dataset', action='store_true', help='Upload dataset as W&B artifact table')
|
||||
parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval for W&B')
|
||||
parser.add_argument('--save_period', type=int, default=-1, help='Log model after every "save_period" epoch')
|
||||
parser.add_argument('--artifact_alias', type=str, default="latest", help='version of dataset artifact to be used')
|
||||
parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone of yolov7=50, first3=0 1 2')
|
||||
parser.add_argument('--v5-metric', action='store_true', help='assume maximum recall as 1.0 in AP calculation')
|
||||
opt = parser.parse_args()
|
||||
|
||||
# Set DDP variables
|
||||
opt.world_size = int(os.environ['WORLD_SIZE']) if 'WORLD_SIZE' in os.environ else 1
|
||||
opt.global_rank = int(os.environ['RANK']) if 'RANK' in os.environ else -1
|
||||
set_logging(opt.global_rank)
|
||||
#if opt.global_rank in [-1, 0]:
|
||||
# check_git_status()
|
||||
# check_requirements()
|
||||
|
||||
# Resume
|
||||
wandb_run = check_wandb_resume(opt)
|
||||
if opt.resume and not wandb_run: # resume an interrupted run
|
||||
ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path
|
||||
assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
|
||||
apriori = opt.global_rank, opt.local_rank
|
||||
with open(Path(ckpt).parent.parent / 'opt.yaml') as f:
|
||||
opt = argparse.Namespace(**yaml.load(f, Loader=yaml.SafeLoader)) # replace
|
||||
opt.cfg, opt.weights, opt.resume, opt.batch_size, opt.global_rank, opt.local_rank = '', ckpt, True, opt.total_batch_size, *apriori # reinstate
|
||||
logger.info('Resuming training from %s' % ckpt)
|
||||
else:
|
||||
# opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
|
||||
opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp) # check files
|
||||
assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
|
||||
opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size))) # extend to 2 sizes (train, test)
|
||||
opt.name = 'evolve' if opt.evolve else opt.name
|
||||
opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve) # increment run
|
||||
|
||||
# DDP mode
|
||||
opt.total_batch_size = opt.batch_size
|
||||
device = select_device(opt.device, batch_size=opt.batch_size)
|
||||
if opt.local_rank != -1:
|
||||
assert torch.cuda.device_count() > opt.local_rank
|
||||
torch.cuda.set_device(opt.local_rank)
|
||||
device = torch.device('cuda', opt.local_rank)
|
||||
dist.init_process_group(backend='nccl', init_method='env://') # distributed backend
|
||||
assert opt.batch_size % opt.world_size == 0, '--batch-size must be multiple of CUDA device count'
|
||||
opt.batch_size = opt.total_batch_size // opt.world_size
|
||||
|
||||
# Hyperparameters
|
||||
with open(opt.hyp) as f:
|
||||
hyp = yaml.load(f, Loader=yaml.SafeLoader) # load hyps
|
||||
|
||||
# Train
|
||||
logger.info(opt)
|
||||
if not opt.evolve:
|
||||
tb_writer = None # init loggers
|
||||
if opt.global_rank in [-1, 0]:
|
||||
prefix = colorstr('tensorboard: ')
|
||||
logger.info(f"{prefix}Start with 'tensorboard --logdir {opt.project}', view at http://localhost:6006/")
|
||||
tb_writer = SummaryWriter(opt.save_dir) # Tensorboard
|
||||
train(hyp, opt, device, tb_writer)
|
||||
|
||||
# Evolve hyperparameters (optional)
|
||||
else:
|
||||
# Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
|
||||
meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||||
'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
|
||||
'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
|
||||
'weight_decay': (1, 0.0, 0.001), # optimizer weight decay
|
||||
'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok)
|
||||
'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum
|
||||
'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr
|
||||
'box': (1, 0.02, 0.2), # box loss gain
|
||||
'cls': (1, 0.2, 4.0), # cls loss gain
|
||||
'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight
|
||||
'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels)
|
||||
'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight
|
||||
'iou_t': (0, 0.1, 0.7), # IoU training threshold
|
||||
'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold
|
||||
'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
|
||||
'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
|
||||
'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
|
||||
'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
|
||||
'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
|
||||
'degrees': (1, 0.0, 45.0), # image rotation (+/- deg)
|
||||
'translate': (1, 0.0, 0.9), # image translation (+/- fraction)
|
||||
'scale': (1, 0.0, 0.9), # image scale (+/- gain)
|
||||
'shear': (1, 0.0, 10.0), # image shear (+/- deg)
|
||||
'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
|
||||
'flipud': (1, 0.0, 1.0), # image flip up-down (probability)
|
||||
'fliplr': (0, 0.0, 1.0), # image flip left-right (probability)
|
||||
'mosaic': (1, 0.0, 1.0), # image mixup (probability)
|
||||
'mixup': (1, 0.0, 1.0), # image mixup (probability)
|
||||
'copy_paste': (1, 0.0, 1.0), # segment copy-paste (probability)
|
||||
'paste_in': (1, 0.0, 1.0)} # segment copy-paste (probability)
|
||||
|
||||
with open(opt.hyp, errors='ignore') as f:
|
||||
hyp = yaml.safe_load(f) # load hyps dict
|
||||
if 'anchors' not in hyp: # anchors commented in hyp.yaml
|
||||
hyp['anchors'] = 3
|
||||
|
||||
assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
|
||||
opt.notest, opt.nosave = True, True # only test/save final epoch
|
||||
# ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
|
||||
yaml_file = Path(opt.save_dir) / 'hyp_evolved.yaml' # save best result here
|
||||
if opt.bucket:
|
||||
os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket) # download evolve.txt if exists
|
||||
|
||||
for _ in range(300): # generations to evolve
|
||||
if Path('evolve.txt').exists(): # if evolve.txt exists: select best hyps and mutate
|
||||
# Select parent(s)
|
||||
parent = 'single' # parent selection method: 'single' or 'weighted'
|
||||
x = np.loadtxt('evolve.txt', ndmin=2)
|
||||
n = min(5, len(x)) # number of previous results to consider
|
||||
x = x[np.argsort(-fitness(x))][:n] # top n mutations
|
||||
w = fitness(x) - fitness(x).min() # weights
|
||||
if parent == 'single' or len(x) == 1:
|
||||
# x = x[random.randint(0, n - 1)] # random selection
|
||||
x = x[random.choices(range(n), weights=w)[0]] # weighted selection
|
||||
elif parent == 'weighted':
|
||||
x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination
|
||||
|
||||
# Mutate
|
||||
mp, s = 0.8, 0.2 # mutation probability, sigma
|
||||
npr = np.random
|
||||
npr.seed(int(time.time()))
|
||||
g = np.array([x[0] for x in meta.values()]) # gains 0-1
|
||||
ng = len(meta)
|
||||
v = np.ones(ng)
|
||||
while all(v == 1): # mutate until a change occurs (prevent duplicates)
|
||||
v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
|
||||
for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300)
|
||||
hyp[k] = float(x[i + 7] * v[i]) # mutate
|
||||
|
||||
# Constrain to limits
|
||||
for k, v in meta.items():
|
||||
hyp[k] = max(hyp[k], v[1]) # lower limit
|
||||
hyp[k] = min(hyp[k], v[2]) # upper limit
|
||||
hyp[k] = round(hyp[k], 5) # significant digits
|
||||
|
||||
# Train mutation
|
||||
results = train(hyp.copy(), opt, device)
|
||||
|
||||
# Write mutation results
|
||||
print_mutation(hyp.copy(), results, yaml_file, opt.bucket)
|
||||
|
||||
# Plot results
|
||||
plot_evolution(yaml_file)
|
||||
print(f'Hyperparameter evolution complete. Best results saved as: {yaml_file}\n'
|
||||
f'Command to train a new model with these hyperparameters: $ python train.py --hyp {yaml_file}')
|
||||
@@ -0,0 +1,699 @@
|
||||
import argparse
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
import time
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
from threading import Thread
|
||||
|
||||
import numpy as np
|
||||
import torch.distributed as dist
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torch.optim as optim
|
||||
import torch.optim.lr_scheduler as lr_scheduler
|
||||
import torch.utils.data
|
||||
import yaml
|
||||
from torch.cuda import amp
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
from torch.utils.tensorboard import SummaryWriter
|
||||
from tqdm import tqdm
|
||||
|
||||
import test # import test.py to get mAP after each epoch
|
||||
from models.experimental import attempt_load
|
||||
from models.yolo import Model
|
||||
from utils.autoanchor import check_anchors
|
||||
from utils.datasets import create_dataloader
|
||||
from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
|
||||
fitness, strip_optimizer, get_latest_run, check_dataset, check_file, check_git_status, check_img_size, \
|
||||
check_requirements, print_mutation, set_logging, one_cycle, colorstr
|
||||
from utils.google_utils import attempt_download
|
||||
from utils.loss import ComputeLoss, ComputeLossAuxOTA
|
||||
from utils.plots import plot_images, plot_labels, plot_results, plot_evolution
|
||||
from utils.torch_utils import ModelEMA, select_device, intersect_dicts, torch_distributed_zero_first, is_parallel
|
||||
from utils.wandb_logging.wandb_utils import WandbLogger, check_wandb_resume
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def train(hyp, opt, device, tb_writer=None):
|
||||
logger.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
|
||||
save_dir, epochs, batch_size, total_batch_size, weights, rank = \
|
||||
Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
|
||||
|
||||
# Directories
|
||||
wdir = save_dir / 'weights'
|
||||
wdir.mkdir(parents=True, exist_ok=True) # make dir
|
||||
last = wdir / 'last.pt'
|
||||
best = wdir / 'best.pt'
|
||||
results_file = save_dir / 'results.txt'
|
||||
|
||||
# Save run settings
|
||||
with open(save_dir / 'hyp.yaml', 'w') as f:
|
||||
yaml.dump(hyp, f, sort_keys=False)
|
||||
with open(save_dir / 'opt.yaml', 'w') as f:
|
||||
yaml.dump(vars(opt), f, sort_keys=False)
|
||||
|
||||
# Configure
|
||||
plots = not opt.evolve # create plots
|
||||
cuda = device.type != 'cpu'
|
||||
init_seeds(2 + rank)
|
||||
with open(opt.data) as f:
|
||||
data_dict = yaml.load(f, Loader=yaml.SafeLoader) # data dict
|
||||
is_coco = opt.data.endswith('coco.yaml')
|
||||
|
||||
# Logging- Doing this before checking the dataset. Might update data_dict
|
||||
loggers = {'wandb': None} # loggers dict
|
||||
if rank in [-1, 0]:
|
||||
opt.hyp = hyp # add hyperparameters
|
||||
run_id = torch.load(weights).get('wandb_id') if weights.endswith('.pt') and os.path.isfile(weights) else None
|
||||
wandb_logger = WandbLogger(opt, Path(opt.save_dir).stem, run_id, data_dict)
|
||||
loggers['wandb'] = wandb_logger.wandb
|
||||
data_dict = wandb_logger.data_dict
|
||||
if wandb_logger.wandb:
|
||||
weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp # WandbLogger might update weights, epochs if resuming
|
||||
|
||||
nc = 1 if opt.single_cls else int(data_dict['nc']) # number of classes
|
||||
names = ['item'] if opt.single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names
|
||||
assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, opt.data) # check
|
||||
|
||||
# Model
|
||||
pretrained = weights.endswith('.pt')
|
||||
if pretrained:
|
||||
with torch_distributed_zero_first(rank):
|
||||
attempt_download(weights) # download if not found locally
|
||||
ckpt = torch.load(weights, map_location=device) # load checkpoint
|
||||
model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
|
||||
exclude = ['anchor'] if (opt.cfg or hyp.get('anchors')) and not opt.resume else [] # exclude keys
|
||||
state_dict = ckpt['model'].float().state_dict() # to FP32
|
||||
state_dict = intersect_dicts(state_dict, model.state_dict(), exclude=exclude) # intersect
|
||||
model.load_state_dict(state_dict, strict=False) # load
|
||||
logger.info('Transferred %g/%g items from %s' % (len(state_dict), len(model.state_dict()), weights)) # report
|
||||
else:
|
||||
model = Model(opt.cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
|
||||
with torch_distributed_zero_first(rank):
|
||||
check_dataset(data_dict) # check
|
||||
train_path = data_dict['train']
|
||||
test_path = data_dict['val']
|
||||
|
||||
# Freeze
|
||||
freeze = [] # parameter names to freeze (full or partial)
|
||||
for k, v in model.named_parameters():
|
||||
v.requires_grad = True # train all layers
|
||||
if any(x in k for x in freeze):
|
||||
print('freezing %s' % k)
|
||||
v.requires_grad = False
|
||||
|
||||
# Optimizer
|
||||
nbs = 64 # nominal batch size
|
||||
accumulate = max(round(nbs / total_batch_size), 1) # accumulate loss before optimizing
|
||||
hyp['weight_decay'] *= total_batch_size * accumulate / nbs # scale weight_decay
|
||||
logger.info(f"Scaled weight_decay = {hyp['weight_decay']}")
|
||||
|
||||
pg0, pg1, pg2 = [], [], [] # optimizer parameter groups
|
||||
for k, v in model.named_modules():
|
||||
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
|
||||
pg2.append(v.bias) # biases
|
||||
if isinstance(v, nn.BatchNorm2d):
|
||||
pg0.append(v.weight) # no decay
|
||||
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
|
||||
pg1.append(v.weight) # apply decay
|
||||
if hasattr(v, 'im'):
|
||||
if hasattr(v.im, 'implicit'):
|
||||
pg0.append(v.im.implicit)
|
||||
else:
|
||||
for iv in v.im:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'imc'):
|
||||
if hasattr(v.imc, 'implicit'):
|
||||
pg0.append(v.imc.implicit)
|
||||
else:
|
||||
for iv in v.imc:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'imb'):
|
||||
if hasattr(v.imb, 'implicit'):
|
||||
pg0.append(v.imb.implicit)
|
||||
else:
|
||||
for iv in v.imb:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'imo'):
|
||||
if hasattr(v.imo, 'implicit'):
|
||||
pg0.append(v.imo.implicit)
|
||||
else:
|
||||
for iv in v.imo:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'ia'):
|
||||
if hasattr(v.ia, 'implicit'):
|
||||
pg0.append(v.ia.implicit)
|
||||
else:
|
||||
for iv in v.ia:
|
||||
pg0.append(iv.implicit)
|
||||
if hasattr(v, 'attn'):
|
||||
if hasattr(v.attn, 'logit_scale'):
|
||||
pg0.append(v.attn.logit_scale)
|
||||
if hasattr(v.attn, 'q_bias'):
|
||||
pg0.append(v.attn.q_bias)
|
||||
if hasattr(v.attn, 'v_bias'):
|
||||
pg0.append(v.attn.v_bias)
|
||||
if hasattr(v.attn, 'relative_position_bias_table'):
|
||||
pg0.append(v.attn.relative_position_bias_table)
|
||||
if hasattr(v, 'rbr_dense'):
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_origin'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_origin)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_avg_conv'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_avg_conv)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_pfir_conv'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_pfir_conv)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_1x1_kxk_idconv1'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_1x1_kxk_idconv1)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_1x1_kxk_conv2'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_1x1_kxk_conv2)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_gconv_dw'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_gconv_dw)
|
||||
if hasattr(v.rbr_dense, 'weight_rbr_gconv_pw'):
|
||||
pg0.append(v.rbr_dense.weight_rbr_gconv_pw)
|
||||
if hasattr(v.rbr_dense, 'vector'):
|
||||
pg0.append(v.rbr_dense.vector)
|
||||
|
||||
if opt.adam:
|
||||
optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
|
||||
else:
|
||||
optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
|
||||
|
||||
optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']}) # add pg1 with weight_decay
|
||||
optimizer.add_param_group({'params': pg2}) # add pg2 (biases)
|
||||
logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
|
||||
del pg0, pg1, pg2
|
||||
|
||||
# Scheduler https://arxiv.org/pdf/1812.01187.pdf
|
||||
# https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
|
||||
if opt.linear_lr:
|
||||
lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear
|
||||
else:
|
||||
lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf']
|
||||
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
|
||||
# plot_lr_scheduler(optimizer, scheduler, epochs)
|
||||
|
||||
# EMA
|
||||
ema = ModelEMA(model) if rank in [-1, 0] else None
|
||||
|
||||
# Resume
|
||||
start_epoch, best_fitness = 0, 0.0
|
||||
if pretrained:
|
||||
# Optimizer
|
||||
if ckpt['optimizer'] is not None:
|
||||
optimizer.load_state_dict(ckpt['optimizer'])
|
||||
best_fitness = ckpt['best_fitness']
|
||||
|
||||
# EMA
|
||||
if ema and ckpt.get('ema'):
|
||||
ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
|
||||
ema.updates = ckpt['updates']
|
||||
|
||||
# Results
|
||||
if ckpt.get('training_results') is not None:
|
||||
results_file.write_text(ckpt['training_results']) # write results.txt
|
||||
|
||||
# Epochs
|
||||
start_epoch = ckpt['epoch'] + 1
|
||||
if opt.resume:
|
||||
assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (weights, epochs)
|
||||
if epochs < start_epoch:
|
||||
logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
|
||||
(weights, ckpt['epoch'], epochs))
|
||||
epochs += ckpt['epoch'] # finetune additional epochs
|
||||
|
||||
del ckpt, state_dict
|
||||
|
||||
# Image sizes
|
||||
gs = max(int(model.stride.max()), 32) # grid size (max stride)
|
||||
nl = model.model[-1].nl # number of detection layers (used for scaling hyp['obj'])
|
||||
imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size] # verify imgsz are gs-multiples
|
||||
|
||||
# DP mode
|
||||
if cuda and rank == -1 and torch.cuda.device_count() > 1:
|
||||
model = torch.nn.DataParallel(model)
|
||||
|
||||
# SyncBatchNorm
|
||||
if opt.sync_bn and cuda and rank != -1:
|
||||
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
|
||||
logger.info('Using SyncBatchNorm()')
|
||||
|
||||
# Trainloader
|
||||
dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt,
|
||||
hyp=hyp, augment=True, cache=opt.cache_images, rect=opt.rect, rank=rank,
|
||||
world_size=opt.world_size, workers=opt.workers,
|
||||
image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '))
|
||||
mlc = np.concatenate(dataset.labels, 0)[:, 0].max() # max label class
|
||||
nb = len(dataloader) # number of batches
|
||||
assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, opt.data, nc - 1)
|
||||
|
||||
# Process 0
|
||||
if rank in [-1, 0]:
|
||||
testloader = create_dataloader(test_path, imgsz_test, batch_size * 2, gs, opt, # testloader
|
||||
hyp=hyp, cache=opt.cache_images and not opt.notest, rect=True, rank=-1,
|
||||
world_size=opt.world_size, workers=opt.workers,
|
||||
pad=0.5, prefix=colorstr('val: '))[0]
|
||||
|
||||
if not opt.resume:
|
||||
labels = np.concatenate(dataset.labels, 0)
|
||||
c = torch.tensor(labels[:, 0]) # classes
|
||||
# cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency
|
||||
# model._initialize_biases(cf.to(device))
|
||||
if plots:
|
||||
#plot_labels(labels, names, save_dir, loggers)
|
||||
if tb_writer:
|
||||
tb_writer.add_histogram('classes', c, 0)
|
||||
|
||||
# Anchors
|
||||
if not opt.noautoanchor:
|
||||
check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
|
||||
model.half().float() # pre-reduce anchor precision
|
||||
|
||||
# DDP mode
|
||||
if cuda and rank != -1:
|
||||
model = DDP(model, device_ids=[opt.local_rank], output_device=opt.local_rank,
|
||||
# nn.MultiheadAttention incompatibility with DDP https://github.com/pytorch/pytorch/issues/26698
|
||||
find_unused_parameters=any(isinstance(layer, nn.MultiheadAttention) for layer in model.modules()))
|
||||
|
||||
# Model parameters
|
||||
hyp['box'] *= 3. / nl # scale to layers
|
||||
hyp['cls'] *= nc / 80. * 3. / nl # scale to classes and layers
|
||||
hyp['obj'] *= (imgsz / 640) ** 2 * 3. / nl # scale to image size and layers
|
||||
hyp['label_smoothing'] = opt.label_smoothing
|
||||
model.nc = nc # attach number of classes to model
|
||||
model.hyp = hyp # attach hyperparameters to model
|
||||
model.gr = 1.0 # iou loss ratio (obj_loss = 1.0 or iou)
|
||||
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights
|
||||
model.names = names
|
||||
|
||||
# Start training
|
||||
t0 = time.time()
|
||||
nw = max(round(hyp['warmup_epochs'] * nb), 1000) # number of warmup iterations, max(3 epochs, 1k iterations)
|
||||
# nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
|
||||
maps = np.zeros(nc) # mAP per class
|
||||
results = (0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
|
||||
scheduler.last_epoch = start_epoch - 1 # do not move
|
||||
scaler = amp.GradScaler(enabled=cuda)
|
||||
compute_loss_ota = ComputeLossAuxOTA(model) # init loss class
|
||||
compute_loss = ComputeLoss(model) # init loss class
|
||||
logger.info(f'Image sizes {imgsz} train, {imgsz_test} test\n'
|
||||
f'Using {dataloader.num_workers} dataloader workers\n'
|
||||
f'Logging results to {save_dir}\n'
|
||||
f'Starting training for {epochs} epochs...')
|
||||
torch.save(model, wdir / 'init.pt')
|
||||
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
|
||||
model.train()
|
||||
|
||||
# Update image weights (optional)
|
||||
if opt.image_weights:
|
||||
# Generate indices
|
||||
if rank in [-1, 0]:
|
||||
cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights
|
||||
iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights
|
||||
dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx
|
||||
# Broadcast if DDP
|
||||
if rank != -1:
|
||||
indices = (torch.tensor(dataset.indices) if rank == 0 else torch.zeros(dataset.n)).int()
|
||||
dist.broadcast(indices, 0)
|
||||
if rank != 0:
|
||||
dataset.indices = indices.cpu().numpy()
|
||||
|
||||
# Update mosaic border
|
||||
# b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
|
||||
# dataset.mosaic_border = [b - imgsz, -b] # height, width borders
|
||||
|
||||
mloss = torch.zeros(4, device=device) # mean losses
|
||||
if rank != -1:
|
||||
dataloader.sampler.set_epoch(epoch)
|
||||
pbar = enumerate(dataloader)
|
||||
logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'labels', 'img_size'))
|
||||
if rank in [-1, 0]:
|
||||
pbar = tqdm(pbar, total=nb) # progress bar
|
||||
optimizer.zero_grad()
|
||||
for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
|
||||
ni = i + nb * epoch # number integrated batches (since train start)
|
||||
imgs = imgs.to(device, non_blocking=True).float() / 255.0 # uint8 to float32, 0-255 to 0.0-1.0
|
||||
|
||||
# Warmup
|
||||
if ni <= nw:
|
||||
xi = [0, nw] # x interp
|
||||
# model.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
|
||||
accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
|
||||
for j, x in enumerate(optimizer.param_groups):
|
||||
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
|
||||
x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
|
||||
if 'momentum' in x:
|
||||
x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
|
||||
|
||||
# Multi-scale
|
||||
if opt.multi_scale:
|
||||
sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size
|
||||
sf = sz / max(imgs.shape[2:]) # scale factor
|
||||
if sf != 1:
|
||||
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
|
||||
imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
|
||||
|
||||
# Forward
|
||||
with amp.autocast(enabled=cuda):
|
||||
pred = model(imgs) # forward
|
||||
loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs) # loss scaled by batch_size
|
||||
if rank != -1:
|
||||
loss *= opt.world_size # gradient averaged between devices in DDP mode
|
||||
if opt.quad:
|
||||
loss *= 4.
|
||||
|
||||
# Backward
|
||||
scaler.scale(loss).backward()
|
||||
|
||||
# Optimize
|
||||
if ni % accumulate == 0:
|
||||
scaler.step(optimizer) # optimizer.step
|
||||
scaler.update()
|
||||
optimizer.zero_grad()
|
||||
if ema:
|
||||
ema.update(model)
|
||||
|
||||
# Print
|
||||
if rank in [-1, 0]:
|
||||
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
|
||||
mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0) # (GB)
|
||||
s = ('%10s' * 2 + '%10.4g' * 6) % (
|
||||
'%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
|
||||
pbar.set_description(s)
|
||||
|
||||
# Plot
|
||||
if plots and ni < 10:
|
||||
f = save_dir / f'train_batch{ni}.jpg' # filename
|
||||
Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
|
||||
# if tb_writer:
|
||||
# tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
|
||||
# tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), []) # add model graph
|
||||
elif plots and ni == 10 and wandb_logger.wandb:
|
||||
wandb_logger.log({"Mosaics": [wandb_logger.wandb.Image(str(x), caption=x.name) for x in
|
||||
save_dir.glob('train*.jpg') if x.exists()]})
|
||||
|
||||
# end batch ------------------------------------------------------------------------------------------------
|
||||
# end epoch ----------------------------------------------------------------------------------------------------
|
||||
|
||||
# Scheduler
|
||||
lr = [x['lr'] for x in optimizer.param_groups] # for tensorboard
|
||||
scheduler.step()
|
||||
|
||||
# DDP process 0 or single-GPU
|
||||
if rank in [-1, 0]:
|
||||
# mAP
|
||||
ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride', 'class_weights'])
|
||||
final_epoch = epoch + 1 == epochs
|
||||
if not opt.notest or final_epoch: # Calculate mAP
|
||||
wandb_logger.current_epoch = epoch + 1
|
||||
results, maps, times = test.test(data_dict,
|
||||
batch_size=batch_size * 2,
|
||||
imgsz=imgsz_test,
|
||||
model=ema.ema,
|
||||
single_cls=opt.single_cls,
|
||||
dataloader=testloader,
|
||||
save_dir=save_dir,
|
||||
verbose=nc < 50 and final_epoch,
|
||||
plots=plots and final_epoch,
|
||||
wandb_logger=wandb_logger,
|
||||
compute_loss=compute_loss,
|
||||
is_coco=is_coco,
|
||||
v5_metric=opt.v5_metric)
|
||||
|
||||
# Write
|
||||
with open(results_file, 'a') as f:
|
||||
f.write(s + '%10.4g' * 7 % results + '\n') # append metrics, val_loss
|
||||
if len(opt.name) and opt.bucket:
|
||||
os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name))
|
||||
|
||||
# Log
|
||||
tags = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', # train loss
|
||||
'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
|
||||
'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss
|
||||
'x/lr0', 'x/lr1', 'x/lr2'] # params
|
||||
for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags):
|
||||
if tb_writer:
|
||||
tb_writer.add_scalar(tag, x, epoch) # tensorboard
|
||||
if wandb_logger.wandb:
|
||||
wandb_logger.log({tag: x}) # W&B
|
||||
|
||||
# Update best mAP
|
||||
fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
|
||||
if fi > best_fitness:
|
||||
best_fitness = fi
|
||||
wandb_logger.end_epoch(best_result=best_fitness == fi)
|
||||
|
||||
# Save model
|
||||
if (not opt.nosave) or (final_epoch and not opt.evolve): # if save
|
||||
ckpt = {'epoch': epoch,
|
||||
'best_fitness': best_fitness,
|
||||
'training_results': results_file.read_text(),
|
||||
'model': deepcopy(model.module if is_parallel(model) else model).half(),
|
||||
'ema': deepcopy(ema.ema).half(),
|
||||
'updates': ema.updates,
|
||||
'optimizer': optimizer.state_dict(),
|
||||
'wandb_id': wandb_logger.wandb_run.id if wandb_logger.wandb else None}
|
||||
|
||||
# Save last, best and delete
|
||||
torch.save(ckpt, last)
|
||||
if best_fitness == fi:
|
||||
torch.save(ckpt, best)
|
||||
if (best_fitness == fi) and (epoch >= 200):
|
||||
torch.save(ckpt, wdir / 'best_{:03d}.pt'.format(epoch))
|
||||
if epoch == 0:
|
||||
torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
|
||||
elif ((epoch+1) % 25) == 0:
|
||||
torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
|
||||
elif epoch >= (epochs-5):
|
||||
torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
|
||||
if wandb_logger.wandb:
|
||||
if ((epoch + 1) % opt.save_period == 0 and not final_epoch) and opt.save_period != -1:
|
||||
wandb_logger.log_model(
|
||||
last.parent, opt, epoch, fi, best_model=best_fitness == fi)
|
||||
del ckpt
|
||||
|
||||
# end epoch ----------------------------------------------------------------------------------------------------
|
||||
# end training
|
||||
if rank in [-1, 0]:
|
||||
# Plots
|
||||
if plots:
|
||||
plot_results(save_dir=save_dir) # save as results.png
|
||||
if wandb_logger.wandb:
|
||||
files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
|
||||
wandb_logger.log({"Results": [wandb_logger.wandb.Image(str(save_dir / f), caption=f) for f in files
|
||||
if (save_dir / f).exists()]})
|
||||
# Test best.pt
|
||||
logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
|
||||
if opt.data.endswith('coco.yaml') and nc == 80: # if COCO
|
||||
for m in (last, best) if best.exists() else (last): # speed, mAP tests
|
||||
results, _, _ = test.test(opt.data,
|
||||
batch_size=batch_size * 2,
|
||||
imgsz=imgsz_test,
|
||||
conf_thres=0.001,
|
||||
iou_thres=0.7,
|
||||
model=attempt_load(m, device).half(),
|
||||
single_cls=opt.single_cls,
|
||||
dataloader=testloader,
|
||||
save_dir=save_dir,
|
||||
save_json=True,
|
||||
plots=False,
|
||||
is_coco=is_coco,
|
||||
v5_metric=opt.v5_metric)
|
||||
|
||||
# Strip optimizers
|
||||
final = best if best.exists() else last # final model
|
||||
for f in last, best:
|
||||
if f.exists():
|
||||
strip_optimizer(f) # strip optimizers
|
||||
if opt.bucket:
|
||||
os.system(f'gsutil cp {final} gs://{opt.bucket}/weights') # upload
|
||||
if wandb_logger.wandb and not opt.evolve: # Log the stripped model
|
||||
wandb_logger.wandb.log_artifact(str(final), type='model',
|
||||
name='run_' + wandb_logger.wandb_run.id + '_model',
|
||||
aliases=['last', 'best', 'stripped'])
|
||||
wandb_logger.finish_run()
|
||||
else:
|
||||
dist.destroy_process_group()
|
||||
torch.cuda.empty_cache()
|
||||
return results
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default='yolo7.pt', help='initial weights path')
|
||||
parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
|
||||
parser.add_argument('--data', type=str, default='data/coco.yaml', help='data.yaml path')
|
||||
parser.add_argument('--hyp', type=str, default='data/hyp.scratch.p5.yaml', help='hyperparameters path')
|
||||
parser.add_argument('--epochs', type=int, default=300)
|
||||
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
|
||||
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')
|
||||
parser.add_argument('--rect', action='store_true', help='rectangular training')
|
||||
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
|
||||
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
|
||||
parser.add_argument('--notest', action='store_true', help='only test final epoch')
|
||||
parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
|
||||
parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
|
||||
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
|
||||
parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
|
||||
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
|
||||
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
|
||||
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
|
||||
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
|
||||
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
|
||||
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
|
||||
parser.add_argument('--project', default='runs/train', help='save to project/name')
|
||||
parser.add_argument('--entity', default=None, help='W&B entity')
|
||||
parser.add_argument('--name', default='exp', help='save to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
parser.add_argument('--quad', action='store_true', help='quad dataloader')
|
||||
parser.add_argument('--linear-lr', action='store_true', help='linear LR')
|
||||
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
|
||||
parser.add_argument('--upload_dataset', action='store_true', help='Upload dataset as W&B artifact table')
|
||||
parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval for W&B')
|
||||
parser.add_argument('--save_period', type=int, default=-1, help='Log model after every "save_period" epoch')
|
||||
parser.add_argument('--artifact_alias', type=str, default="latest", help='version of dataset artifact to be used')
|
||||
parser.add_argument('--v5-metric', action='store_true', help='assume maximum recall as 1.0 in AP calculation')
|
||||
opt = parser.parse_args()
|
||||
|
||||
# Set DDP variables
|
||||
opt.world_size = int(os.environ['WORLD_SIZE']) if 'WORLD_SIZE' in os.environ else 1
|
||||
opt.global_rank = int(os.environ['RANK']) if 'RANK' in os.environ else -1
|
||||
set_logging(opt.global_rank)
|
||||
#if opt.global_rank in [-1, 0]:
|
||||
# check_git_status()
|
||||
# check_requirements()
|
||||
|
||||
# Resume
|
||||
wandb_run = check_wandb_resume(opt)
|
||||
if opt.resume and not wandb_run: # resume an interrupted run
|
||||
ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path
|
||||
assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
|
||||
apriori = opt.global_rank, opt.local_rank
|
||||
with open(Path(ckpt).parent.parent / 'opt.yaml') as f:
|
||||
opt = argparse.Namespace(**yaml.load(f, Loader=yaml.SafeLoader)) # replace
|
||||
opt.cfg, opt.weights, opt.resume, opt.batch_size, opt.global_rank, opt.local_rank = '', ckpt, True, opt.total_batch_size, *apriori # reinstate
|
||||
logger.info('Resuming training from %s' % ckpt)
|
||||
else:
|
||||
# opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
|
||||
opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp) # check files
|
||||
assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
|
||||
opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size))) # extend to 2 sizes (train, test)
|
||||
opt.name = 'evolve' if opt.evolve else opt.name
|
||||
opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve) # increment run
|
||||
|
||||
# DDP mode
|
||||
opt.total_batch_size = opt.batch_size
|
||||
device = select_device(opt.device, batch_size=opt.batch_size)
|
||||
if opt.local_rank != -1:
|
||||
assert torch.cuda.device_count() > opt.local_rank
|
||||
torch.cuda.set_device(opt.local_rank)
|
||||
device = torch.device('cuda', opt.local_rank)
|
||||
dist.init_process_group(backend='nccl', init_method='env://') # distributed backend
|
||||
assert opt.batch_size % opt.world_size == 0, '--batch-size must be multiple of CUDA device count'
|
||||
opt.batch_size = opt.total_batch_size // opt.world_size
|
||||
|
||||
# Hyperparameters
|
||||
with open(opt.hyp) as f:
|
||||
hyp = yaml.load(f, Loader=yaml.SafeLoader) # load hyps
|
||||
|
||||
# Train
|
||||
logger.info(opt)
|
||||
if not opt.evolve:
|
||||
tb_writer = None # init loggers
|
||||
if opt.global_rank in [-1, 0]:
|
||||
prefix = colorstr('tensorboard: ')
|
||||
logger.info(f"{prefix}Start with 'tensorboard --logdir {opt.project}', view at http://localhost:6006/")
|
||||
tb_writer = SummaryWriter(opt.save_dir) # Tensorboard
|
||||
train(hyp, opt, device, tb_writer)
|
||||
|
||||
# Evolve hyperparameters (optional)
|
||||
else:
|
||||
# Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
|
||||
meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
|
||||
'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
|
||||
'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
|
||||
'weight_decay': (1, 0.0, 0.001), # optimizer weight decay
|
||||
'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok)
|
||||
'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum
|
||||
'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr
|
||||
'box': (1, 0.02, 0.2), # box loss gain
|
||||
'cls': (1, 0.2, 4.0), # cls loss gain
|
||||
'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight
|
||||
'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels)
|
||||
'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight
|
||||
'iou_t': (0, 0.1, 0.7), # IoU training threshold
|
||||
'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold
|
||||
'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
|
||||
'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
|
||||
'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
|
||||
'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
|
||||
'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
|
||||
'degrees': (1, 0.0, 45.0), # image rotation (+/- deg)
|
||||
'translate': (1, 0.0, 0.9), # image translation (+/- fraction)
|
||||
'scale': (1, 0.0, 0.9), # image scale (+/- gain)
|
||||
'shear': (1, 0.0, 10.0), # image shear (+/- deg)
|
||||
'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
|
||||
'flipud': (1, 0.0, 1.0), # image flip up-down (probability)
|
||||
'fliplr': (0, 0.0, 1.0), # image flip left-right (probability)
|
||||
'mosaic': (1, 0.0, 1.0), # image mixup (probability)
|
||||
'mixup': (1, 0.0, 1.0)} # image mixup (probability)
|
||||
|
||||
with open(opt.hyp, errors='ignore') as f:
|
||||
hyp = yaml.safe_load(f) # load hyps dict
|
||||
if 'anchors' not in hyp: # anchors commented in hyp.yaml
|
||||
hyp['anchors'] = 3
|
||||
|
||||
assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
|
||||
opt.notest, opt.nosave = True, True # only test/save final epoch
|
||||
# ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
|
||||
yaml_file = Path(opt.save_dir) / 'hyp_evolved.yaml' # save best result here
|
||||
if opt.bucket:
|
||||
os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket) # download evolve.txt if exists
|
||||
|
||||
for _ in range(300): # generations to evolve
|
||||
if Path('evolve.txt').exists(): # if evolve.txt exists: select best hyps and mutate
|
||||
# Select parent(s)
|
||||
parent = 'single' # parent selection method: 'single' or 'weighted'
|
||||
x = np.loadtxt('evolve.txt', ndmin=2)
|
||||
n = min(5, len(x)) # number of previous results to consider
|
||||
x = x[np.argsort(-fitness(x))][:n] # top n mutations
|
||||
w = fitness(x) - fitness(x).min() # weights
|
||||
if parent == 'single' or len(x) == 1:
|
||||
# x = x[random.randint(0, n - 1)] # random selection
|
||||
x = x[random.choices(range(n), weights=w)[0]] # weighted selection
|
||||
elif parent == 'weighted':
|
||||
x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination
|
||||
|
||||
# Mutate
|
||||
mp, s = 0.8, 0.2 # mutation probability, sigma
|
||||
npr = np.random
|
||||
npr.seed(int(time.time()))
|
||||
g = np.array([x[0] for x in meta.values()]) # gains 0-1
|
||||
ng = len(meta)
|
||||
v = np.ones(ng)
|
||||
while all(v == 1): # mutate until a change occurs (prevent duplicates)
|
||||
v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
|
||||
for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300)
|
||||
hyp[k] = float(x[i + 7] * v[i]) # mutate
|
||||
|
||||
# Constrain to limits
|
||||
for k, v in meta.items():
|
||||
hyp[k] = max(hyp[k], v[1]) # lower limit
|
||||
hyp[k] = min(hyp[k], v[2]) # upper limit
|
||||
hyp[k] = round(hyp[k], 5) # significant digits
|
||||
|
||||
# Train mutation
|
||||
results = train(hyp.copy(), opt, device)
|
||||
|
||||
# Write mutation results
|
||||
print_mutation(hyp.copy(), results, yaml_file, opt.bucket)
|
||||
|
||||
# Plot results
|
||||
plot_evolution(yaml_file)
|
||||
print(f'Hyperparameter evolution complete. Best results saved as: {yaml_file}\n'
|
||||
f'Command to train a new model with these hyperparameters: $ python train.py --hyp {yaml_file}')
|
||||
@@ -0,0 +1 @@
|
||||
# init
|
||||
@@ -0,0 +1,72 @@
|
||||
# Activation functions
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
|
||||
# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
|
||||
class SiLU(nn.Module): # export-friendly version of nn.SiLU()
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
return x * torch.sigmoid(x)
|
||||
|
||||
|
||||
class Hardswish(nn.Module): # export-friendly version of nn.Hardswish()
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
# return x * F.hardsigmoid(x) # for torchscript and CoreML
|
||||
return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX
|
||||
|
||||
|
||||
class MemoryEfficientSwish(nn.Module):
|
||||
class F(torch.autograd.Function):
|
||||
@staticmethod
|
||||
def forward(ctx, x):
|
||||
ctx.save_for_backward(x)
|
||||
return x * torch.sigmoid(x)
|
||||
|
||||
@staticmethod
|
||||
def backward(ctx, grad_output):
|
||||
x = ctx.saved_tensors[0]
|
||||
sx = torch.sigmoid(x)
|
||||
return grad_output * (sx * (1 + x * (1 - sx)))
|
||||
|
||||
def forward(self, x):
|
||||
return self.F.apply(x)
|
||||
|
||||
|
||||
# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
|
||||
class Mish(nn.Module):
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
return x * F.softplus(x).tanh()
|
||||
|
||||
|
||||
class MemoryEfficientMish(nn.Module):
|
||||
class F(torch.autograd.Function):
|
||||
@staticmethod
|
||||
def forward(ctx, x):
|
||||
ctx.save_for_backward(x)
|
||||
return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x)))
|
||||
|
||||
@staticmethod
|
||||
def backward(ctx, grad_output):
|
||||
x = ctx.saved_tensors[0]
|
||||
sx = torch.sigmoid(x)
|
||||
fx = F.softplus(x).tanh()
|
||||
return grad_output * (fx + x * sx * (1 - fx * fx))
|
||||
|
||||
def forward(self, x):
|
||||
return self.F.apply(x)
|
||||
|
||||
|
||||
# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
|
||||
class FReLU(nn.Module):
|
||||
def __init__(self, c1, k=3): # ch_in, kernel
|
||||
super().__init__()
|
||||
self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c1)
|
||||
|
||||
def forward(self, x):
|
||||
return torch.max(x, self.bn(self.conv(x)))
|
||||
@@ -0,0 +1,155 @@
|
||||
import numpy as np
|
||||
import onnx
|
||||
from onnx import shape_inference
|
||||
try:
|
||||
import onnx_graphsurgeon as gs
|
||||
except Exception as e:
|
||||
print('Import onnx_graphsurgeon failure: %s' % e)
|
||||
|
||||
import logging
|
||||
|
||||
LOGGER = logging.getLogger(__name__)
|
||||
|
||||
class RegisterNMS(object):
|
||||
def __init__(
|
||||
self,
|
||||
onnx_model_path: str,
|
||||
precision: str = "fp32",
|
||||
):
|
||||
|
||||
self.graph = gs.import_onnx(onnx.load(onnx_model_path))
|
||||
assert self.graph
|
||||
LOGGER.info("ONNX graph created successfully")
|
||||
# Fold constants via ONNX-GS that PyTorch2ONNX may have missed
|
||||
self.graph.fold_constants()
|
||||
self.precision = precision
|
||||
self.batch_size = 1
|
||||
def infer(self):
|
||||
"""
|
||||
Sanitize the graph by cleaning any unconnected nodes, do a topological resort,
|
||||
and fold constant inputs values. When possible, run shape inference on the
|
||||
ONNX graph to determine tensor shapes.
|
||||
"""
|
||||
for _ in range(3):
|
||||
count_before = len(self.graph.nodes)
|
||||
|
||||
self.graph.cleanup().toposort()
|
||||
try:
|
||||
for node in self.graph.nodes:
|
||||
for o in node.outputs:
|
||||
o.shape = None
|
||||
model = gs.export_onnx(self.graph)
|
||||
model = shape_inference.infer_shapes(model)
|
||||
self.graph = gs.import_onnx(model)
|
||||
except Exception as e:
|
||||
LOGGER.info(f"Shape inference could not be performed at this time:\n{e}")
|
||||
try:
|
||||
self.graph.fold_constants(fold_shapes=True)
|
||||
except TypeError as e:
|
||||
LOGGER.error(
|
||||
"This version of ONNX GraphSurgeon does not support folding shapes, "
|
||||
f"please upgrade your onnx_graphsurgeon module. Error:\n{e}"
|
||||
)
|
||||
raise
|
||||
|
||||
count_after = len(self.graph.nodes)
|
||||
if count_before == count_after:
|
||||
# No new folding occurred in this iteration, so we can stop for now.
|
||||
break
|
||||
|
||||
def save(self, output_path):
|
||||
"""
|
||||
Save the ONNX model to the given location.
|
||||
Args:
|
||||
output_path: Path pointing to the location where to write
|
||||
out the updated ONNX model.
|
||||
"""
|
||||
self.graph.cleanup().toposort()
|
||||
model = gs.export_onnx(self.graph)
|
||||
onnx.save(model, output_path)
|
||||
LOGGER.info(f"Saved ONNX model to {output_path}")
|
||||
|
||||
def register_nms(
|
||||
self,
|
||||
*,
|
||||
score_thresh: float = 0.25,
|
||||
nms_thresh: float = 0.45,
|
||||
detections_per_img: int = 100,
|
||||
):
|
||||
"""
|
||||
Register the ``EfficientNMS_TRT`` plugin node.
|
||||
NMS expects these shapes for its input tensors:
|
||||
- box_net: [batch_size, number_boxes, 4]
|
||||
- class_net: [batch_size, number_boxes, number_labels]
|
||||
Args:
|
||||
score_thresh (float): The scalar threshold for score (low scoring boxes are removed).
|
||||
nms_thresh (float): The scalar threshold for IOU (new boxes that have high IOU
|
||||
overlap with previously selected boxes are removed).
|
||||
detections_per_img (int): Number of best detections to keep after NMS.
|
||||
"""
|
||||
|
||||
self.infer()
|
||||
# Find the concat node at the end of the network
|
||||
op_inputs = self.graph.outputs
|
||||
op = "EfficientNMS_TRT"
|
||||
attrs = {
|
||||
"plugin_version": "1",
|
||||
"background_class": -1, # no background class
|
||||
"max_output_boxes": detections_per_img,
|
||||
"score_threshold": score_thresh,
|
||||
"iou_threshold": nms_thresh,
|
||||
"score_activation": False,
|
||||
"box_coding": 0,
|
||||
}
|
||||
|
||||
if self.precision == "fp32":
|
||||
dtype_output = np.float32
|
||||
elif self.precision == "fp16":
|
||||
dtype_output = np.float16
|
||||
else:
|
||||
raise NotImplementedError(f"Currently not supports precision: {self.precision}")
|
||||
|
||||
# NMS Outputs
|
||||
output_num_detections = gs.Variable(
|
||||
name="num_dets",
|
||||
dtype=np.int32,
|
||||
shape=[self.batch_size, 1],
|
||||
) # A scalar indicating the number of valid detections per batch image.
|
||||
output_boxes = gs.Variable(
|
||||
name="det_boxes",
|
||||
dtype=dtype_output,
|
||||
shape=[self.batch_size, detections_per_img, 4],
|
||||
)
|
||||
output_scores = gs.Variable(
|
||||
name="det_scores",
|
||||
dtype=dtype_output,
|
||||
shape=[self.batch_size, detections_per_img],
|
||||
)
|
||||
output_labels = gs.Variable(
|
||||
name="det_classes",
|
||||
dtype=np.int32,
|
||||
shape=[self.batch_size, detections_per_img],
|
||||
)
|
||||
|
||||
op_outputs = [output_num_detections, output_boxes, output_scores, output_labels]
|
||||
|
||||
# Create the NMS Plugin node with the selected inputs. The outputs of the node will also
|
||||
# become the final outputs of the graph.
|
||||
self.graph.layer(op=op, name="batched_nms", inputs=op_inputs, outputs=op_outputs, attrs=attrs)
|
||||
LOGGER.info(f"Created NMS plugin '{op}' with attributes: {attrs}")
|
||||
|
||||
self.graph.outputs = op_outputs
|
||||
|
||||
self.infer()
|
||||
|
||||
def save(self, output_path):
|
||||
"""
|
||||
Save the ONNX model to the given location.
|
||||
Args:
|
||||
output_path: Path pointing to the location where to write
|
||||
out the updated ONNX model.
|
||||
"""
|
||||
self.graph.cleanup().toposort()
|
||||
model = gs.export_onnx(self.graph)
|
||||
onnx.save(model, output_path)
|
||||
LOGGER.info(f"Saved ONNX model to {output_path}")
|
||||
@@ -0,0 +1,160 @@
|
||||
# Auto-anchor utils
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import yaml
|
||||
from scipy.cluster.vq import kmeans
|
||||
from tqdm import tqdm
|
||||
|
||||
from utils.general import colorstr
|
||||
|
||||
|
||||
def check_anchor_order(m):
|
||||
# Check anchor order against stride order for YOLO Detect() module m, and correct if necessary
|
||||
a = m.anchor_grid.prod(-1).view(-1) # anchor area
|
||||
da = a[-1] - a[0] # delta a
|
||||
ds = m.stride[-1] - m.stride[0] # delta s
|
||||
if da.sign() != ds.sign(): # same order
|
||||
print('Reversing anchor order')
|
||||
m.anchors[:] = m.anchors.flip(0)
|
||||
m.anchor_grid[:] = m.anchor_grid.flip(0)
|
||||
|
||||
|
||||
def check_anchors(dataset, model, thr=4.0, imgsz=640):
|
||||
# Check anchor fit to data, recompute if necessary
|
||||
prefix = colorstr('autoanchor: ')
|
||||
print(f'\n{prefix}Analyzing anchors... ', end='')
|
||||
m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect()
|
||||
shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
|
||||
scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale
|
||||
wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh
|
||||
|
||||
def metric(k): # compute metric
|
||||
r = wh[:, None] / k[None]
|
||||
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
|
||||
best = x.max(1)[0] # best_x
|
||||
aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold
|
||||
bpr = (best > 1. / thr).float().mean() # best possible recall
|
||||
return bpr, aat
|
||||
|
||||
anchors = m.anchor_grid.clone().cpu().view(-1, 2) # current anchors
|
||||
bpr, aat = metric(anchors)
|
||||
print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
|
||||
if bpr < 0.98: # threshold to recompute
|
||||
print('. Attempting to improve anchors, please wait...')
|
||||
na = m.anchor_grid.numel() // 2 # number of anchors
|
||||
try:
|
||||
anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
|
||||
except Exception as e:
|
||||
print(f'{prefix}ERROR: {e}')
|
||||
new_bpr = metric(anchors)[0]
|
||||
if new_bpr > bpr: # replace anchors
|
||||
anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
|
||||
m.anchor_grid[:] = anchors.clone().view_as(m.anchor_grid) # for inference
|
||||
check_anchor_order(m)
|
||||
m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss
|
||||
print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
|
||||
else:
|
||||
print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
|
||||
print('') # newline
|
||||
|
||||
|
||||
def kmean_anchors(path='./data/coco.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
|
||||
""" Creates kmeans-evolved anchors from training dataset
|
||||
|
||||
Arguments:
|
||||
path: path to dataset *.yaml, or a loaded dataset
|
||||
n: number of anchors
|
||||
img_size: image size used for training
|
||||
thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
|
||||
gen: generations to evolve anchors using genetic algorithm
|
||||
verbose: print all results
|
||||
|
||||
Return:
|
||||
k: kmeans evolved anchors
|
||||
|
||||
Usage:
|
||||
from utils.autoanchor import *; _ = kmean_anchors()
|
||||
"""
|
||||
thr = 1. / thr
|
||||
prefix = colorstr('autoanchor: ')
|
||||
|
||||
def metric(k, wh): # compute metrics
|
||||
r = wh[:, None] / k[None]
|
||||
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
|
||||
# x = wh_iou(wh, torch.tensor(k)) # iou metric
|
||||
return x, x.max(1)[0] # x, best_x
|
||||
|
||||
def anchor_fitness(k): # mutation fitness
|
||||
_, best = metric(torch.tensor(k, dtype=torch.float32), wh)
|
||||
return (best * (best > thr).float()).mean() # fitness
|
||||
|
||||
def print_results(k):
|
||||
k = k[np.argsort(k.prod(1))] # sort small to large
|
||||
x, best = metric(k, wh0)
|
||||
bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr
|
||||
print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
|
||||
print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
|
||||
f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
|
||||
for i, x in enumerate(k):
|
||||
print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg
|
||||
return k
|
||||
|
||||
if isinstance(path, str): # *.yaml file
|
||||
with open(path) as f:
|
||||
data_dict = yaml.load(f, Loader=yaml.SafeLoader) # model dict
|
||||
from utils.datasets import LoadImagesAndLabels
|
||||
dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
|
||||
else:
|
||||
dataset = path # dataset
|
||||
|
||||
# Get label wh
|
||||
shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
|
||||
wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh
|
||||
|
||||
# Filter
|
||||
i = (wh0 < 3.0).any(1).sum()
|
||||
if i:
|
||||
print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
|
||||
wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels
|
||||
# wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
|
||||
|
||||
# Kmeans calculation
|
||||
print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
|
||||
s = wh.std(0) # sigmas for whitening
|
||||
k, dist = kmeans(wh / s, n, iter=30) # points, mean distance
|
||||
assert len(k) == n, print(f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}')
|
||||
k *= s
|
||||
wh = torch.tensor(wh, dtype=torch.float32) # filtered
|
||||
wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered
|
||||
k = print_results(k)
|
||||
|
||||
# Plot
|
||||
# k, d = [None] * 20, [None] * 20
|
||||
# for i in tqdm(range(1, 21)):
|
||||
# k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance
|
||||
# fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
|
||||
# ax = ax.ravel()
|
||||
# ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
|
||||
# fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh
|
||||
# ax[0].hist(wh[wh[:, 0]<100, 0],400)
|
||||
# ax[1].hist(wh[wh[:, 1]<100, 1],400)
|
||||
# fig.savefig('wh.png', dpi=200)
|
||||
|
||||
# Evolve
|
||||
npr = np.random
|
||||
f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma
|
||||
pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:') # progress bar
|
||||
for _ in pbar:
|
||||
v = np.ones(sh)
|
||||
while (v == 1).all(): # mutate until a change occurs (prevent duplicates)
|
||||
v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
|
||||
kg = (k.copy() * v).clip(min=2.0)
|
||||
fg = anchor_fitness(kg)
|
||||
if fg > f:
|
||||
f, k = fg, kg.copy()
|
||||
pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
|
||||
if verbose:
|
||||
print_results(k)
|
||||
|
||||
return print_results(k)
|
||||
@@ -0,0 +1 @@
|
||||
#init
|
||||
@@ -0,0 +1,26 @@
|
||||
# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
|
||||
# This script will run on every instance restart, not only on first start
|
||||
# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
|
||||
|
||||
Content-Type: multipart/mixed; boundary="//"
|
||||
MIME-Version: 1.0
|
||||
|
||||
--//
|
||||
Content-Type: text/cloud-config; charset="us-ascii"
|
||||
MIME-Version: 1.0
|
||||
Content-Transfer-Encoding: 7bit
|
||||
Content-Disposition: attachment; filename="cloud-config.txt"
|
||||
|
||||
#cloud-config
|
||||
cloud_final_modules:
|
||||
- [scripts-user, always]
|
||||
|
||||
--//
|
||||
Content-Type: text/x-shellscript; charset="us-ascii"
|
||||
MIME-Version: 1.0
|
||||
Content-Transfer-Encoding: 7bit
|
||||
Content-Disposition: attachment; filename="userdata.txt"
|
||||
|
||||
#!/bin/bash
|
||||
# --- paste contents of userdata.sh here ---
|
||||
--//
|
||||
@@ -0,0 +1,37 @@
|
||||
# Resume all interrupted trainings in yolor/ dir including DDP trainings
|
||||
# Usage: $ python utils/aws/resume.py
|
||||
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import yaml
|
||||
|
||||
sys.path.append('./') # to run '$ python *.py' files in subdirectories
|
||||
|
||||
port = 0 # --master_port
|
||||
path = Path('').resolve()
|
||||
for last in path.rglob('*/**/last.pt'):
|
||||
ckpt = torch.load(last)
|
||||
if ckpt['optimizer'] is None:
|
||||
continue
|
||||
|
||||
# Load opt.yaml
|
||||
with open(last.parent.parent / 'opt.yaml') as f:
|
||||
opt = yaml.load(f, Loader=yaml.SafeLoader)
|
||||
|
||||
# Get device count
|
||||
d = opt['device'].split(',') # devices
|
||||
nd = len(d) # number of devices
|
||||
ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel
|
||||
|
||||
if ddp: # multi-GPU
|
||||
port += 1
|
||||
cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
|
||||
else: # single-GPU
|
||||
cmd = f'python train.py --resume {last}'
|
||||
|
||||
cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread
|
||||
print(cmd)
|
||||
os.system(cmd)
|
||||
@@ -0,0 +1,27 @@
|
||||
#!/bin/bash
|
||||
# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
|
||||
# This script will run only once on first instance start (for a re-start script see mime.sh)
|
||||
# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
|
||||
# Use >300 GB SSD
|
||||
|
||||
cd home/ubuntu
|
||||
if [ ! -d yolor ]; then
|
||||
echo "Running first-time script." # install dependencies, download COCO, pull Docker
|
||||
git clone -b main https://github.com/WongKinYiu/yolov7 && sudo chmod -R 777 yolov7
|
||||
cd yolov7
|
||||
bash data/scripts/get_coco.sh && echo "Data done." &
|
||||
sudo docker pull nvcr.io/nvidia/pytorch:21.08-py3 && echo "Docker done." &
|
||||
python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
|
||||
wait && echo "All tasks done." # finish background tasks
|
||||
else
|
||||
echo "Running re-start script." # resume interrupted runs
|
||||
i=0
|
||||
list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
|
||||
while IFS= read -r id; do
|
||||
((i++))
|
||||
echo "restarting container $i: $id"
|
||||
sudo docker start $id
|
||||
# sudo docker exec -it $id python train.py --resume # single-GPU
|
||||
sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
|
||||
done <<<"$list"
|
||||
fi
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,892 @@
|
||||
# YOLOR general utils
|
||||
|
||||
import glob
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import platform
|
||||
import random
|
||||
import re
|
||||
import subprocess
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import torch
|
||||
import torchvision
|
||||
import yaml
|
||||
|
||||
from utils.google_utils import gsutil_getsize
|
||||
from utils.metrics import fitness
|
||||
from utils.torch_utils import init_torch_seeds
|
||||
|
||||
# Settings
|
||||
torch.set_printoptions(linewidth=320, precision=5, profile='long')
|
||||
np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5
|
||||
pd.options.display.max_columns = 10
|
||||
cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
|
||||
os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8)) # NumExpr max threads
|
||||
|
||||
|
||||
def set_logging(rank=-1):
|
||||
logging.basicConfig(
|
||||
format="%(message)s",
|
||||
level=logging.INFO if rank in [-1, 0] else logging.WARN)
|
||||
|
||||
|
||||
def init_seeds(seed=0):
|
||||
# Initialize random number generator (RNG) seeds
|
||||
random.seed(seed)
|
||||
np.random.seed(seed)
|
||||
init_torch_seeds(seed)
|
||||
|
||||
|
||||
def get_latest_run(search_dir='.'):
|
||||
# Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
|
||||
last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
|
||||
return max(last_list, key=os.path.getctime) if last_list else ''
|
||||
|
||||
|
||||
def isdocker():
|
||||
# Is environment a Docker container
|
||||
return Path('/workspace').exists() # or Path('/.dockerenv').exists()
|
||||
|
||||
|
||||
def emojis(str=''):
|
||||
# Return platform-dependent emoji-safe version of string
|
||||
return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
|
||||
|
||||
|
||||
def check_online():
|
||||
# Check internet connectivity
|
||||
import socket
|
||||
try:
|
||||
socket.create_connection(("1.1.1.1", 443), 5) # check host accesability
|
||||
return True
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
def check_git_status():
|
||||
# Recommend 'git pull' if code is out of date
|
||||
print(colorstr('github: '), end='')
|
||||
try:
|
||||
assert Path('.git').exists(), 'skipping check (not a git repository)'
|
||||
assert not isdocker(), 'skipping check (Docker image)'
|
||||
assert check_online(), 'skipping check (offline)'
|
||||
|
||||
cmd = 'git fetch && git config --get remote.origin.url'
|
||||
url = subprocess.check_output(cmd, shell=True).decode().strip().rstrip('.git') # github repo url
|
||||
branch = subprocess.check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip() # checked out
|
||||
n = int(subprocess.check_output(f'git rev-list {branch}..origin/master --count', shell=True)) # commits behind
|
||||
if n > 0:
|
||||
s = f"⚠️ WARNING: code is out of date by {n} commit{'s' * (n > 1)}. " \
|
||||
f"Use 'git pull' to update or 'git clone {url}' to download latest."
|
||||
else:
|
||||
s = f'up to date with {url} ✅'
|
||||
print(emojis(s)) # emoji-safe
|
||||
except Exception as e:
|
||||
print(e)
|
||||
|
||||
|
||||
def check_requirements(requirements='requirements.txt', exclude=()):
|
||||
# Check installed dependencies meet requirements (pass *.txt file or list of packages)
|
||||
import pkg_resources as pkg
|
||||
prefix = colorstr('red', 'bold', 'requirements:')
|
||||
if isinstance(requirements, (str, Path)): # requirements.txt file
|
||||
file = Path(requirements)
|
||||
if not file.exists():
|
||||
print(f"{prefix} {file.resolve()} not found, check failed.")
|
||||
return
|
||||
requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
|
||||
else: # list or tuple of packages
|
||||
requirements = [x for x in requirements if x not in exclude]
|
||||
|
||||
n = 0 # number of packages updates
|
||||
for r in requirements:
|
||||
try:
|
||||
pkg.require(r)
|
||||
except Exception as e: # DistributionNotFound or VersionConflict if requirements not met
|
||||
n += 1
|
||||
print(f"{prefix} {e.req} not found and is required by YOLOR, attempting auto-update...")
|
||||
print(subprocess.check_output(f"pip install '{e.req}'", shell=True).decode())
|
||||
|
||||
if n: # if packages updated
|
||||
source = file.resolve() if 'file' in locals() else requirements
|
||||
s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
|
||||
f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
|
||||
print(emojis(s)) # emoji-safe
|
||||
|
||||
|
||||
def check_img_size(img_size, s=32):
|
||||
# Verify img_size is a multiple of stride s
|
||||
new_size = make_divisible(img_size, int(s)) # ceil gs-multiple
|
||||
if new_size != img_size:
|
||||
print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
|
||||
return new_size
|
||||
|
||||
|
||||
def check_imshow():
|
||||
# Check if environment supports image displays
|
||||
try:
|
||||
assert not isdocker(), 'cv2.imshow() is disabled in Docker environments'
|
||||
cv2.imshow('test', np.zeros((1, 1, 3)))
|
||||
cv2.waitKey(1)
|
||||
cv2.destroyAllWindows()
|
||||
cv2.waitKey(1)
|
||||
return True
|
||||
except Exception as e:
|
||||
print(f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}')
|
||||
return False
|
||||
|
||||
|
||||
def check_file(file):
|
||||
# Search for file if not found
|
||||
if Path(file).is_file() or file == '':
|
||||
return file
|
||||
else:
|
||||
files = glob.glob('./**/' + file, recursive=True) # find file
|
||||
assert len(files), f'File Not Found: {file}' # assert file was found
|
||||
assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}" # assert unique
|
||||
return files[0] # return file
|
||||
|
||||
|
||||
def check_dataset(dict):
|
||||
# Download dataset if not found locally
|
||||
val, s = dict.get('val'), dict.get('download')
|
||||
if val and len(val):
|
||||
val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path
|
||||
if not all(x.exists() for x in val):
|
||||
print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
|
||||
if s and len(s): # download script
|
||||
print('Downloading %s ...' % s)
|
||||
if s.startswith('http') and s.endswith('.zip'): # URL
|
||||
f = Path(s).name # filename
|
||||
torch.hub.download_url_to_file(s, f)
|
||||
r = os.system('unzip -q %s -d ../ && rm %s' % (f, f)) # unzip
|
||||
else: # bash script
|
||||
r = os.system(s)
|
||||
print('Dataset autodownload %s\n' % ('success' if r == 0 else 'failure')) # analyze return value
|
||||
else:
|
||||
raise Exception('Dataset not found.')
|
||||
|
||||
|
||||
def make_divisible(x, divisor):
|
||||
# Returns x evenly divisible by divisor
|
||||
return math.ceil(x / divisor) * divisor
|
||||
|
||||
|
||||
def clean_str(s):
|
||||
# Cleans a string by replacing special characters with underscore _
|
||||
return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
|
||||
|
||||
|
||||
def one_cycle(y1=0.0, y2=1.0, steps=100):
|
||||
# lambda function for sinusoidal ramp from y1 to y2
|
||||
return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
|
||||
|
||||
|
||||
def colorstr(*input):
|
||||
# Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world')
|
||||
*args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) # color arguments, string
|
||||
colors = {'black': '\033[30m', # basic colors
|
||||
'red': '\033[31m',
|
||||
'green': '\033[32m',
|
||||
'yellow': '\033[33m',
|
||||
'blue': '\033[34m',
|
||||
'magenta': '\033[35m',
|
||||
'cyan': '\033[36m',
|
||||
'white': '\033[37m',
|
||||
'bright_black': '\033[90m', # bright colors
|
||||
'bright_red': '\033[91m',
|
||||
'bright_green': '\033[92m',
|
||||
'bright_yellow': '\033[93m',
|
||||
'bright_blue': '\033[94m',
|
||||
'bright_magenta': '\033[95m',
|
||||
'bright_cyan': '\033[96m',
|
||||
'bright_white': '\033[97m',
|
||||
'end': '\033[0m', # misc
|
||||
'bold': '\033[1m',
|
||||
'underline': '\033[4m'}
|
||||
return ''.join(colors[x] for x in args) + f'{string}' + colors['end']
|
||||
|
||||
|
||||
def labels_to_class_weights(labels, nc=80):
|
||||
# Get class weights (inverse frequency) from training labels
|
||||
if labels[0] is None: # no labels loaded
|
||||
return torch.Tensor()
|
||||
|
||||
labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO
|
||||
classes = labels[:, 0].astype(np.int) # labels = [class xywh]
|
||||
weights = np.bincount(classes, minlength=nc) # occurrences per class
|
||||
|
||||
# Prepend gridpoint count (for uCE training)
|
||||
# gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image
|
||||
# weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start
|
||||
|
||||
weights[weights == 0] = 1 # replace empty bins with 1
|
||||
weights = 1 / weights # number of targets per class
|
||||
weights /= weights.sum() # normalize
|
||||
return torch.from_numpy(weights)
|
||||
|
||||
|
||||
def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
|
||||
# Produces image weights based on class_weights and image contents
|
||||
class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
|
||||
image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
|
||||
# index = random.choices(range(n), weights=image_weights, k=1) # weight image sample
|
||||
return image_weights
|
||||
|
||||
|
||||
def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper)
|
||||
# https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
|
||||
# a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
|
||||
# b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
|
||||
# x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco
|
||||
# x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet
|
||||
x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
|
||||
35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
|
||||
64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
|
||||
return x
|
||||
|
||||
|
||||
def xyxy2xywh(x):
|
||||
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
|
||||
y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
|
||||
y[:, 2] = x[:, 2] - x[:, 0] # width
|
||||
y[:, 3] = x[:, 3] - x[:, 1] # height
|
||||
return y
|
||||
|
||||
|
||||
def xywh2xyxy(x):
|
||||
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
|
||||
y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
|
||||
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
|
||||
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
|
||||
return y
|
||||
|
||||
|
||||
def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
|
||||
# Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x
|
||||
y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y
|
||||
y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x
|
||||
y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y
|
||||
return y
|
||||
|
||||
|
||||
def xyn2xy(x, w=640, h=640, padw=0, padh=0):
|
||||
# Convert normalized segments into pixel segments, shape (n,2)
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = w * x[:, 0] + padw # top left x
|
||||
y[:, 1] = h * x[:, 1] + padh # top left y
|
||||
return y
|
||||
|
||||
|
||||
def segment2box(segment, width=640, height=640):
|
||||
# Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
|
||||
x, y = segment.T # segment xy
|
||||
inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
|
||||
x, y, = x[inside], y[inside]
|
||||
return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4)) # xyxy
|
||||
|
||||
|
||||
def segments2boxes(segments):
|
||||
# Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
|
||||
boxes = []
|
||||
for s in segments:
|
||||
x, y = s.T # segment xy
|
||||
boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy
|
||||
return xyxy2xywh(np.array(boxes)) # cls, xywh
|
||||
|
||||
|
||||
def resample_segments(segments, n=1000):
|
||||
# Up-sample an (n,2) segment
|
||||
for i, s in enumerate(segments):
|
||||
s = np.concatenate((s, s[0:1, :]), axis=0)
|
||||
x = np.linspace(0, len(s) - 1, n)
|
||||
xp = np.arange(len(s))
|
||||
segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy
|
||||
return segments
|
||||
|
||||
|
||||
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
|
||||
# Rescale coords (xyxy) from img1_shape to img0_shape
|
||||
if ratio_pad is None: # calculate from img0_shape
|
||||
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
|
||||
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
|
||||
else:
|
||||
gain = ratio_pad[0][0]
|
||||
pad = ratio_pad[1]
|
||||
|
||||
coords[:, [0, 2]] -= pad[0] # x padding
|
||||
coords[:, [1, 3]] -= pad[1] # y padding
|
||||
coords[:, :4] /= gain
|
||||
clip_coords(coords, img0_shape)
|
||||
return coords
|
||||
|
||||
|
||||
def clip_coords(boxes, img_shape):
|
||||
# Clip bounding xyxy bounding boxes to image shape (height, width)
|
||||
boxes[:, 0].clamp_(0, img_shape[1]) # x1
|
||||
boxes[:, 1].clamp_(0, img_shape[0]) # y1
|
||||
boxes[:, 2].clamp_(0, img_shape[1]) # x2
|
||||
boxes[:, 3].clamp_(0, img_shape[0]) # y2
|
||||
|
||||
|
||||
def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
|
||||
# Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
|
||||
box2 = box2.T
|
||||
|
||||
# Get the coordinates of bounding boxes
|
||||
if x1y1x2y2: # x1, y1, x2, y2 = box1
|
||||
b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
|
||||
b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
|
||||
else: # transform from xywh to xyxy
|
||||
b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
|
||||
b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
|
||||
b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
|
||||
b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2
|
||||
|
||||
# Intersection area
|
||||
inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
|
||||
(torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)
|
||||
|
||||
# Union Area
|
||||
w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
|
||||
w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
|
||||
union = w1 * h1 + w2 * h2 - inter + eps
|
||||
|
||||
iou = inter / union
|
||||
|
||||
if GIoU or DIoU or CIoU:
|
||||
cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width
|
||||
ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height
|
||||
if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
|
||||
c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared
|
||||
rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
|
||||
(b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared
|
||||
if DIoU:
|
||||
return iou - rho2 / c2 # DIoU
|
||||
elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
|
||||
v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / (h2 + eps)) - torch.atan(w1 / (h1 + eps)), 2)
|
||||
with torch.no_grad():
|
||||
alpha = v / (v - iou + (1 + eps))
|
||||
return iou - (rho2 / c2 + v * alpha) # CIoU
|
||||
else: # GIoU https://arxiv.org/pdf/1902.09630.pdf
|
||||
c_area = cw * ch + eps # convex area
|
||||
return iou - (c_area - union) / c_area # GIoU
|
||||
else:
|
||||
return iou # IoU
|
||||
|
||||
|
||||
|
||||
|
||||
def bbox_alpha_iou(box1, box2, x1y1x2y2=False, GIoU=False, DIoU=False, CIoU=False, alpha=2, eps=1e-9):
|
||||
# Returns tsqrt_he IoU of box1 to box2. box1 is 4, box2 is nx4
|
||||
box2 = box2.T
|
||||
|
||||
# Get the coordinates of bounding boxes
|
||||
if x1y1x2y2: # x1, y1, x2, y2 = box1
|
||||
b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
|
||||
b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
|
||||
else: # transform from xywh to xyxy
|
||||
b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
|
||||
b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
|
||||
b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
|
||||
b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2
|
||||
|
||||
# Intersection area
|
||||
inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
|
||||
(torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)
|
||||
|
||||
# Union Area
|
||||
w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
|
||||
w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
|
||||
union = w1 * h1 + w2 * h2 - inter + eps
|
||||
|
||||
# change iou into pow(iou+eps)
|
||||
# iou = inter / union
|
||||
iou = torch.pow(inter/union + eps, alpha)
|
||||
# beta = 2 * alpha
|
||||
if GIoU or DIoU or CIoU:
|
||||
cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width
|
||||
ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height
|
||||
if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
|
||||
c2 = (cw ** 2 + ch ** 2) ** alpha + eps # convex diagonal
|
||||
rho_x = torch.abs(b2_x1 + b2_x2 - b1_x1 - b1_x2)
|
||||
rho_y = torch.abs(b2_y1 + b2_y2 - b1_y1 - b1_y2)
|
||||
rho2 = ((rho_x ** 2 + rho_y ** 2) / 4) ** alpha # center distance
|
||||
if DIoU:
|
||||
return iou - rho2 / c2 # DIoU
|
||||
elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
|
||||
v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
|
||||
with torch.no_grad():
|
||||
alpha_ciou = v / ((1 + eps) - inter / union + v)
|
||||
# return iou - (rho2 / c2 + v * alpha_ciou) # CIoU
|
||||
return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)) # CIoU
|
||||
else: # GIoU https://arxiv.org/pdf/1902.09630.pdf
|
||||
# c_area = cw * ch + eps # convex area
|
||||
# return iou - (c_area - union) / c_area # GIoU
|
||||
c_area = torch.max(cw * ch + eps, union) # convex area
|
||||
return iou - torch.pow((c_area - union) / c_area + eps, alpha) # GIoU
|
||||
else:
|
||||
return iou # torch.log(iou+eps) or iou
|
||||
|
||||
|
||||
def box_iou(box1, box2):
|
||||
# https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
|
||||
"""
|
||||
Return intersection-over-union (Jaccard index) of boxes.
|
||||
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
|
||||
Arguments:
|
||||
box1 (Tensor[N, 4])
|
||||
box2 (Tensor[M, 4])
|
||||
Returns:
|
||||
iou (Tensor[N, M]): the NxM matrix containing the pairwise
|
||||
IoU values for every element in boxes1 and boxes2
|
||||
"""
|
||||
|
||||
def box_area(box):
|
||||
# box = 4xn
|
||||
return (box[2] - box[0]) * (box[3] - box[1])
|
||||
|
||||
area1 = box_area(box1.T)
|
||||
area2 = box_area(box2.T)
|
||||
|
||||
# inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
|
||||
inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
|
||||
return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter)
|
||||
|
||||
|
||||
def wh_iou(wh1, wh2):
|
||||
# Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2
|
||||
wh1 = wh1[:, None] # [N,1,2]
|
||||
wh2 = wh2[None] # [1,M,2]
|
||||
inter = torch.min(wh1, wh2).prod(2) # [N,M]
|
||||
return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter)
|
||||
|
||||
|
||||
def box_giou(box1, box2):
|
||||
"""
|
||||
Return generalized intersection-over-union (Jaccard index) between two sets of boxes.
|
||||
Both sets of boxes are expected to be in ``(x1, y1, x2, y2)`` format with
|
||||
``0 <= x1 < x2`` and ``0 <= y1 < y2``.
|
||||
Args:
|
||||
boxes1 (Tensor[N, 4]): first set of boxes
|
||||
boxes2 (Tensor[M, 4]): second set of boxes
|
||||
Returns:
|
||||
Tensor[N, M]: the NxM matrix containing the pairwise generalized IoU values
|
||||
for every element in boxes1 and boxes2
|
||||
"""
|
||||
|
||||
def box_area(box):
|
||||
# box = 4xn
|
||||
return (box[2] - box[0]) * (box[3] - box[1])
|
||||
|
||||
area1 = box_area(box1.T)
|
||||
area2 = box_area(box2.T)
|
||||
|
||||
inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
|
||||
union = (area1[:, None] + area2 - inter)
|
||||
|
||||
iou = inter / union
|
||||
|
||||
lti = torch.min(box1[:, None, :2], box2[:, :2])
|
||||
rbi = torch.max(box1[:, None, 2:], box2[:, 2:])
|
||||
|
||||
whi = (rbi - lti).clamp(min=0) # [N,M,2]
|
||||
areai = whi[:, :, 0] * whi[:, :, 1]
|
||||
|
||||
return iou - (areai - union) / areai
|
||||
|
||||
|
||||
def box_ciou(box1, box2, eps: float = 1e-7):
|
||||
"""
|
||||
Return complete intersection-over-union (Jaccard index) between two sets of boxes.
|
||||
Both sets of boxes are expected to be in ``(x1, y1, x2, y2)`` format with
|
||||
``0 <= x1 < x2`` and ``0 <= y1 < y2``.
|
||||
Args:
|
||||
boxes1 (Tensor[N, 4]): first set of boxes
|
||||
boxes2 (Tensor[M, 4]): second set of boxes
|
||||
eps (float, optional): small number to prevent division by zero. Default: 1e-7
|
||||
Returns:
|
||||
Tensor[N, M]: the NxM matrix containing the pairwise complete IoU values
|
||||
for every element in boxes1 and boxes2
|
||||
"""
|
||||
|
||||
def box_area(box):
|
||||
# box = 4xn
|
||||
return (box[2] - box[0]) * (box[3] - box[1])
|
||||
|
||||
area1 = box_area(box1.T)
|
||||
area2 = box_area(box2.T)
|
||||
|
||||
inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
|
||||
union = (area1[:, None] + area2 - inter)
|
||||
|
||||
iou = inter / union
|
||||
|
||||
lti = torch.min(box1[:, None, :2], box2[:, :2])
|
||||
rbi = torch.max(box1[:, None, 2:], box2[:, 2:])
|
||||
|
||||
whi = (rbi - lti).clamp(min=0) # [N,M,2]
|
||||
diagonal_distance_squared = (whi[:, :, 0] ** 2) + (whi[:, :, 1] ** 2) + eps
|
||||
|
||||
# centers of boxes
|
||||
x_p = (box1[:, None, 0] + box1[:, None, 2]) / 2
|
||||
y_p = (box1[:, None, 1] + box1[:, None, 3]) / 2
|
||||
x_g = (box2[:, 0] + box2[:, 2]) / 2
|
||||
y_g = (box2[:, 1] + box2[:, 3]) / 2
|
||||
# The distance between boxes' centers squared.
|
||||
centers_distance_squared = (x_p - x_g) ** 2 + (y_p - y_g) ** 2
|
||||
|
||||
w_pred = box1[:, None, 2] - box1[:, None, 0]
|
||||
h_pred = box1[:, None, 3] - box1[:, None, 1]
|
||||
|
||||
w_gt = box2[:, 2] - box2[:, 0]
|
||||
h_gt = box2[:, 3] - box2[:, 1]
|
||||
|
||||
v = (4 / (torch.pi ** 2)) * torch.pow((torch.atan(w_gt / h_gt) - torch.atan(w_pred / h_pred)), 2)
|
||||
with torch.no_grad():
|
||||
alpha = v / (1 - iou + v + eps)
|
||||
return iou - (centers_distance_squared / diagonal_distance_squared) - alpha * v
|
||||
|
||||
|
||||
def box_diou(box1, box2, eps: float = 1e-7):
|
||||
"""
|
||||
Return distance intersection-over-union (Jaccard index) between two sets of boxes.
|
||||
Both sets of boxes are expected to be in ``(x1, y1, x2, y2)`` format with
|
||||
``0 <= x1 < x2`` and ``0 <= y1 < y2``.
|
||||
Args:
|
||||
boxes1 (Tensor[N, 4]): first set of boxes
|
||||
boxes2 (Tensor[M, 4]): second set of boxes
|
||||
eps (float, optional): small number to prevent division by zero. Default: 1e-7
|
||||
Returns:
|
||||
Tensor[N, M]: the NxM matrix containing the pairwise distance IoU values
|
||||
for every element in boxes1 and boxes2
|
||||
"""
|
||||
|
||||
def box_area(box):
|
||||
# box = 4xn
|
||||
return (box[2] - box[0]) * (box[3] - box[1])
|
||||
|
||||
area1 = box_area(box1.T)
|
||||
area2 = box_area(box2.T)
|
||||
|
||||
inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
|
||||
union = (area1[:, None] + area2 - inter)
|
||||
|
||||
iou = inter / union
|
||||
|
||||
lti = torch.min(box1[:, None, :2], box2[:, :2])
|
||||
rbi = torch.max(box1[:, None, 2:], box2[:, 2:])
|
||||
|
||||
whi = (rbi - lti).clamp(min=0) # [N,M,2]
|
||||
diagonal_distance_squared = (whi[:, :, 0] ** 2) + (whi[:, :, 1] ** 2) + eps
|
||||
|
||||
# centers of boxes
|
||||
x_p = (box1[:, None, 0] + box1[:, None, 2]) / 2
|
||||
y_p = (box1[:, None, 1] + box1[:, None, 3]) / 2
|
||||
x_g = (box2[:, 0] + box2[:, 2]) / 2
|
||||
y_g = (box2[:, 1] + box2[:, 3]) / 2
|
||||
# The distance between boxes' centers squared.
|
||||
centers_distance_squared = (x_p - x_g) ** 2 + (y_p - y_g) ** 2
|
||||
|
||||
# The distance IoU is the IoU penalized by a normalized
|
||||
# distance between boxes' centers squared.
|
||||
return iou - (centers_distance_squared / diagonal_distance_squared)
|
||||
|
||||
|
||||
def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
|
||||
labels=()):
|
||||
"""Runs Non-Maximum Suppression (NMS) on inference results
|
||||
|
||||
Returns:
|
||||
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
|
||||
"""
|
||||
|
||||
nc = prediction.shape[2] - 5 # number of classes
|
||||
xc = prediction[..., 4] > conf_thres # candidates
|
||||
|
||||
# Settings
|
||||
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
|
||||
max_det = 300 # maximum number of detections per image
|
||||
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
|
||||
time_limit = 10.0 # seconds to quit after
|
||||
redundant = True # require redundant detections
|
||||
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
|
||||
merge = False # use merge-NMS
|
||||
|
||||
t = time.time()
|
||||
output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
|
||||
for xi, x in enumerate(prediction): # image index, image inference
|
||||
# Apply constraints
|
||||
# x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
|
||||
x = x[xc[xi]] # confidence
|
||||
|
||||
# Cat apriori labels if autolabelling
|
||||
if labels and len(labels[xi]):
|
||||
l = labels[xi]
|
||||
v = torch.zeros((len(l), nc + 5), device=x.device)
|
||||
v[:, :4] = l[:, 1:5] # box
|
||||
v[:, 4] = 1.0 # conf
|
||||
v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
|
||||
x = torch.cat((x, v), 0)
|
||||
|
||||
# If none remain process next image
|
||||
if not x.shape[0]:
|
||||
continue
|
||||
|
||||
# Compute conf
|
||||
if nc == 1:
|
||||
x[:, 5:] = x[:, 4:5] # for models with one class, cls_loss is 0 and cls_conf is always 0.5,
|
||||
# so there is no need to multiplicate.
|
||||
else:
|
||||
x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
|
||||
|
||||
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
|
||||
box = xywh2xyxy(x[:, :4])
|
||||
|
||||
# Detections matrix nx6 (xyxy, conf, cls)
|
||||
if multi_label:
|
||||
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
|
||||
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
|
||||
else: # best class only
|
||||
conf, j = x[:, 5:].max(1, keepdim=True)
|
||||
x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
|
||||
|
||||
# Filter by class
|
||||
if classes is not None:
|
||||
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
|
||||
|
||||
# Apply finite constraint
|
||||
# if not torch.isfinite(x).all():
|
||||
# x = x[torch.isfinite(x).all(1)]
|
||||
|
||||
# Check shape
|
||||
n = x.shape[0] # number of boxes
|
||||
if not n: # no boxes
|
||||
continue
|
||||
elif n > max_nms: # excess boxes
|
||||
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
|
||||
|
||||
# Batched NMS
|
||||
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
|
||||
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
|
||||
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
|
||||
if i.shape[0] > max_det: # limit detections
|
||||
i = i[:max_det]
|
||||
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
|
||||
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
|
||||
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
|
||||
weights = iou * scores[None] # box weights
|
||||
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
|
||||
if redundant:
|
||||
i = i[iou.sum(1) > 1] # require redundancy
|
||||
|
||||
output[xi] = x[i]
|
||||
if (time.time() - t) > time_limit:
|
||||
print(f'WARNING: NMS time limit {time_limit}s exceeded')
|
||||
break # time limit exceeded
|
||||
|
||||
return output
|
||||
|
||||
|
||||
def non_max_suppression_kpt(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
|
||||
labels=(), kpt_label=False, nc=None, nkpt=None):
|
||||
"""Runs Non-Maximum Suppression (NMS) on inference results
|
||||
|
||||
Returns:
|
||||
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
|
||||
"""
|
||||
if nc is None:
|
||||
nc = prediction.shape[2] - 5 if not kpt_label else prediction.shape[2] - 56 # number of classes
|
||||
xc = prediction[..., 4] > conf_thres # candidates
|
||||
|
||||
# Settings
|
||||
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
|
||||
max_det = 300 # maximum number of detections per image
|
||||
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
|
||||
time_limit = 10.0 # seconds to quit after
|
||||
redundant = True # require redundant detections
|
||||
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
|
||||
merge = False # use merge-NMS
|
||||
|
||||
t = time.time()
|
||||
output = [torch.zeros((0,6), device=prediction.device)] * prediction.shape[0]
|
||||
for xi, x in enumerate(prediction): # image index, image inference
|
||||
# Apply constraints
|
||||
# x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
|
||||
x = x[xc[xi]] # confidence
|
||||
|
||||
# Cat apriori labels if autolabelling
|
||||
if labels and len(labels[xi]):
|
||||
l = labels[xi]
|
||||
v = torch.zeros((len(l), nc + 5), device=x.device)
|
||||
v[:, :4] = l[:, 1:5] # box
|
||||
v[:, 4] = 1.0 # conf
|
||||
v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
|
||||
x = torch.cat((x, v), 0)
|
||||
|
||||
# If none remain process next image
|
||||
if not x.shape[0]:
|
||||
continue
|
||||
|
||||
# Compute conf
|
||||
x[:, 5:5+nc] *= x[:, 4:5] # conf = obj_conf * cls_conf
|
||||
|
||||
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
|
||||
box = xywh2xyxy(x[:, :4])
|
||||
|
||||
# Detections matrix nx6 (xyxy, conf, cls)
|
||||
if multi_label:
|
||||
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
|
||||
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
|
||||
else: # best class only
|
||||
if not kpt_label:
|
||||
conf, j = x[:, 5:].max(1, keepdim=True)
|
||||
x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
|
||||
else:
|
||||
kpts = x[:, 6:]
|
||||
conf, j = x[:, 5:6].max(1, keepdim=True)
|
||||
x = torch.cat((box, conf, j.float(), kpts), 1)[conf.view(-1) > conf_thres]
|
||||
|
||||
|
||||
# Filter by class
|
||||
if classes is not None:
|
||||
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
|
||||
|
||||
# Apply finite constraint
|
||||
# if not torch.isfinite(x).all():
|
||||
# x = x[torch.isfinite(x).all(1)]
|
||||
|
||||
# Check shape
|
||||
n = x.shape[0] # number of boxes
|
||||
if not n: # no boxes
|
||||
continue
|
||||
elif n > max_nms: # excess boxes
|
||||
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
|
||||
|
||||
# Batched NMS
|
||||
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
|
||||
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
|
||||
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
|
||||
if i.shape[0] > max_det: # limit detections
|
||||
i = i[:max_det]
|
||||
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
|
||||
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
|
||||
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
|
||||
weights = iou * scores[None] # box weights
|
||||
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
|
||||
if redundant:
|
||||
i = i[iou.sum(1) > 1] # require redundancy
|
||||
|
||||
output[xi] = x[i]
|
||||
if (time.time() - t) > time_limit:
|
||||
print(f'WARNING: NMS time limit {time_limit}s exceeded')
|
||||
break # time limit exceeded
|
||||
|
||||
return output
|
||||
|
||||
|
||||
def strip_optimizer(f='best.pt', s=''): # from utils.general import *; strip_optimizer()
|
||||
# Strip optimizer from 'f' to finalize training, optionally save as 's'
|
||||
x = torch.load(f, map_location=torch.device('cpu'))
|
||||
if x.get('ema'):
|
||||
x['model'] = x['ema'] # replace model with ema
|
||||
for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates': # keys
|
||||
x[k] = None
|
||||
x['epoch'] = -1
|
||||
x['model'].half() # to FP16
|
||||
for p in x['model'].parameters():
|
||||
p.requires_grad = False
|
||||
torch.save(x, s or f)
|
||||
mb = os.path.getsize(s or f) / 1E6 # filesize
|
||||
print(f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB")
|
||||
|
||||
|
||||
def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''):
|
||||
# Print mutation results to evolve.txt (for use with train.py --evolve)
|
||||
a = '%10s' * len(hyp) % tuple(hyp.keys()) # hyperparam keys
|
||||
b = '%10.3g' * len(hyp) % tuple(hyp.values()) # hyperparam values
|
||||
c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
|
||||
print('\n%s\n%s\nEvolved fitness: %s\n' % (a, b, c))
|
||||
|
||||
if bucket:
|
||||
url = 'gs://%s/evolve.txt' % bucket
|
||||
if gsutil_getsize(url) > (os.path.getsize('evolve.txt') if os.path.exists('evolve.txt') else 0):
|
||||
os.system('gsutil cp %s .' % url) # download evolve.txt if larger than local
|
||||
|
||||
with open('evolve.txt', 'a') as f: # append result
|
||||
f.write(c + b + '\n')
|
||||
x = np.unique(np.loadtxt('evolve.txt', ndmin=2), axis=0) # load unique rows
|
||||
x = x[np.argsort(-fitness(x))] # sort
|
||||
np.savetxt('evolve.txt', x, '%10.3g') # save sort by fitness
|
||||
|
||||
# Save yaml
|
||||
for i, k in enumerate(hyp.keys()):
|
||||
hyp[k] = float(x[0, i + 7])
|
||||
with open(yaml_file, 'w') as f:
|
||||
results = tuple(x[0, :7])
|
||||
c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
|
||||
f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n')
|
||||
yaml.dump(hyp, f, sort_keys=False)
|
||||
|
||||
if bucket:
|
||||
os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket)) # upload
|
||||
|
||||
|
||||
def apply_classifier(x, model, img, im0):
|
||||
# applies a second stage classifier to yolo outputs
|
||||
im0 = [im0] if isinstance(im0, np.ndarray) else im0
|
||||
for i, d in enumerate(x): # per image
|
||||
if d is not None and len(d):
|
||||
d = d.clone()
|
||||
|
||||
# Reshape and pad cutouts
|
||||
b = xyxy2xywh(d[:, :4]) # boxes
|
||||
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square
|
||||
b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad
|
||||
d[:, :4] = xywh2xyxy(b).long()
|
||||
|
||||
# Rescale boxes from img_size to im0 size
|
||||
scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
|
||||
|
||||
# Classes
|
||||
pred_cls1 = d[:, 5].long()
|
||||
ims = []
|
||||
for j, a in enumerate(d): # per item
|
||||
cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
|
||||
im = cv2.resize(cutout, (224, 224)) # BGR
|
||||
# cv2.imwrite('test%i.jpg' % j, cutout)
|
||||
|
||||
im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
|
||||
im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32
|
||||
im /= 255.0 # 0 - 255 to 0.0 - 1.0
|
||||
ims.append(im)
|
||||
|
||||
pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction
|
||||
x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def increment_path(path, exist_ok=True, sep=''):
|
||||
# Increment path, i.e. runs/exp --> runs/exp{sep}0, runs/exp{sep}1 etc.
|
||||
path = Path(path) # os-agnostic
|
||||
if (path.exists() and exist_ok) or (not path.exists()):
|
||||
return str(path)
|
||||
else:
|
||||
dirs = glob.glob(f"{path}{sep}*") # similar paths
|
||||
matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
|
||||
i = [int(m.groups()[0]) for m in matches if m] # indices
|
||||
n = max(i) + 1 if i else 2 # increment number
|
||||
return f"{path}{sep}{n}" # update path
|
||||
@@ -0,0 +1,25 @@
|
||||
FROM gcr.io/google-appengine/python
|
||||
|
||||
# Create a virtualenv for dependencies. This isolates these packages from
|
||||
# system-level packages.
|
||||
# Use -p python3 or -p python3.7 to select python version. Default is version 2.
|
||||
RUN virtualenv /env -p python3
|
||||
|
||||
# Setting these environment variables are the same as running
|
||||
# source /env/bin/activate.
|
||||
ENV VIRTUAL_ENV /env
|
||||
ENV PATH /env/bin:$PATH
|
||||
|
||||
RUN apt-get update && apt-get install -y python-opencv
|
||||
|
||||
# Copy the application's requirements.txt and run pip to install all
|
||||
# dependencies into the virtualenv.
|
||||
ADD requirements.txt /app/requirements.txt
|
||||
RUN pip install -r /app/requirements.txt
|
||||
|
||||
# Add the application source code.
|
||||
ADD . /app
|
||||
|
||||
# Run a WSGI server to serve the application. gunicorn must be declared as
|
||||
# a dependency in requirements.txt.
|
||||
CMD gunicorn -b :$PORT main:app
|
||||
@@ -0,0 +1,4 @@
|
||||
# add these requirements in your app on top of the existing ones
|
||||
pip==18.1
|
||||
Flask==1.0.2
|
||||
gunicorn==19.9.0
|
||||
@@ -0,0 +1,14 @@
|
||||
runtime: custom
|
||||
env: flex
|
||||
|
||||
service: yolorapp
|
||||
|
||||
liveness_check:
|
||||
initial_delay_sec: 600
|
||||
|
||||
manual_scaling:
|
||||
instances: 1
|
||||
resources:
|
||||
cpu: 1
|
||||
memory_gb: 4
|
||||
disk_size_gb: 20
|
||||
@@ -0,0 +1,123 @@
|
||||
# Google utils: https://cloud.google.com/storage/docs/reference/libraries
|
||||
|
||||
import os
|
||||
import platform
|
||||
import subprocess
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import requests
|
||||
import torch
|
||||
|
||||
|
||||
def gsutil_getsize(url=''):
|
||||
# gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
|
||||
s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8')
|
||||
return eval(s.split(' ')[0]) if len(s) else 0 # bytes
|
||||
|
||||
|
||||
def attempt_download(file, repo='WongKinYiu/yolov7'):
|
||||
# Attempt file download if does not exist
|
||||
file = Path(str(file).strip().replace("'", '').lower())
|
||||
|
||||
if not file.exists():
|
||||
try:
|
||||
response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api
|
||||
assets = [x['name'] for x in response['assets']] # release assets
|
||||
tag = response['tag_name'] # i.e. 'v1.0'
|
||||
except: # fallback plan
|
||||
assets = ['yolov7.pt', 'yolov7-tiny.pt', 'yolov7x.pt', 'yolov7-d6.pt', 'yolov7-e6.pt',
|
||||
'yolov7-e6e.pt', 'yolov7-w6.pt']
|
||||
tag = subprocess.check_output('git tag', shell=True).decode().split()[-1]
|
||||
|
||||
name = file.name
|
||||
if name in assets:
|
||||
msg = f'{file} missing, try downloading from https://github.com/{repo}/releases/'
|
||||
redundant = False # second download option
|
||||
try: # GitHub
|
||||
url = f'https://github.com/{repo}/releases/download/{tag}/{name}'
|
||||
print(f'Downloading {url} to {file}...')
|
||||
torch.hub.download_url_to_file(url, file)
|
||||
assert file.exists() and file.stat().st_size > 1E6 # check
|
||||
except Exception as e: # GCP
|
||||
print(f'Download error: {e}')
|
||||
assert redundant, 'No secondary mirror'
|
||||
url = f'https://storage.googleapis.com/{repo}/ckpt/{name}'
|
||||
print(f'Downloading {url} to {file}...')
|
||||
os.system(f'curl -L {url} -o {file}') # torch.hub.download_url_to_file(url, weights)
|
||||
finally:
|
||||
if not file.exists() or file.stat().st_size < 1E6: # check
|
||||
file.unlink(missing_ok=True) # remove partial downloads
|
||||
print(f'ERROR: Download failure: {msg}')
|
||||
print('')
|
||||
return
|
||||
|
||||
|
||||
def gdrive_download(id='', file='tmp.zip'):
|
||||
# Downloads a file from Google Drive. from yolov7.utils.google_utils import *; gdrive_download()
|
||||
t = time.time()
|
||||
file = Path(file)
|
||||
cookie = Path('cookie') # gdrive cookie
|
||||
print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
|
||||
file.unlink(missing_ok=True) # remove existing file
|
||||
cookie.unlink(missing_ok=True) # remove existing cookie
|
||||
|
||||
# Attempt file download
|
||||
out = "NUL" if platform.system() == "Windows" else "/dev/null"
|
||||
os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
|
||||
if os.path.exists('cookie'): # large file
|
||||
s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
|
||||
else: # small file
|
||||
s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
|
||||
r = os.system(s) # execute, capture return
|
||||
cookie.unlink(missing_ok=True) # remove existing cookie
|
||||
|
||||
# Error check
|
||||
if r != 0:
|
||||
file.unlink(missing_ok=True) # remove partial
|
||||
print('Download error ') # raise Exception('Download error')
|
||||
return r
|
||||
|
||||
# Unzip if archive
|
||||
if file.suffix == '.zip':
|
||||
print('unzipping... ', end='')
|
||||
os.system(f'unzip -q {file}') # unzip
|
||||
file.unlink() # remove zip to free space
|
||||
|
||||
print(f'Done ({time.time() - t:.1f}s)')
|
||||
return r
|
||||
|
||||
|
||||
def get_token(cookie="./cookie"):
|
||||
with open(cookie) as f:
|
||||
for line in f:
|
||||
if "download" in line:
|
||||
return line.split()[-1]
|
||||
return ""
|
||||
|
||||
# def upload_blob(bucket_name, source_file_name, destination_blob_name):
|
||||
# # Uploads a file to a bucket
|
||||
# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
|
||||
#
|
||||
# storage_client = storage.Client()
|
||||
# bucket = storage_client.get_bucket(bucket_name)
|
||||
# blob = bucket.blob(destination_blob_name)
|
||||
#
|
||||
# blob.upload_from_filename(source_file_name)
|
||||
#
|
||||
# print('File {} uploaded to {}.'.format(
|
||||
# source_file_name,
|
||||
# destination_blob_name))
|
||||
#
|
||||
#
|
||||
# def download_blob(bucket_name, source_blob_name, destination_file_name):
|
||||
# # Uploads a blob from a bucket
|
||||
# storage_client = storage.Client()
|
||||
# bucket = storage_client.get_bucket(bucket_name)
|
||||
# blob = bucket.blob(source_blob_name)
|
||||
#
|
||||
# blob.download_to_filename(destination_file_name)
|
||||
#
|
||||
# print('Blob {} downloaded to {}.'.format(
|
||||
# source_blob_name,
|
||||
# destination_file_name))
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,227 @@
|
||||
# Model validation metrics
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from . import general
|
||||
|
||||
|
||||
def fitness(x):
|
||||
# Model fitness as a weighted combination of metrics
|
||||
w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
|
||||
return (x[:, :4] * w).sum(1)
|
||||
|
||||
|
||||
def ap_per_class(tp, conf, pred_cls, target_cls, v5_metric=False, plot=False, save_dir='.', names=()):
|
||||
""" Compute the average precision, given the recall and precision curves.
|
||||
Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
|
||||
# Arguments
|
||||
tp: True positives (nparray, nx1 or nx10).
|
||||
conf: Objectness value from 0-1 (nparray).
|
||||
pred_cls: Predicted object classes (nparray).
|
||||
target_cls: True object classes (nparray).
|
||||
plot: Plot precision-recall curve at mAP@0.5
|
||||
save_dir: Plot save directory
|
||||
# Returns
|
||||
The average precision as computed in py-faster-rcnn.
|
||||
"""
|
||||
|
||||
# Sort by objectness
|
||||
i = np.argsort(-conf)
|
||||
tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
|
||||
|
||||
# Find unique classes
|
||||
unique_classes = np.unique(target_cls)
|
||||
nc = unique_classes.shape[0] # number of classes, number of detections
|
||||
|
||||
# Create Precision-Recall curve and compute AP for each class
|
||||
px, py = np.linspace(0, 1, 1000), [] # for plotting
|
||||
ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
|
||||
for ci, c in enumerate(unique_classes):
|
||||
i = pred_cls == c
|
||||
n_l = (target_cls == c).sum() # number of labels
|
||||
n_p = i.sum() # number of predictions
|
||||
|
||||
if n_p == 0 or n_l == 0:
|
||||
continue
|
||||
else:
|
||||
# Accumulate FPs and TPs
|
||||
fpc = (1 - tp[i]).cumsum(0)
|
||||
tpc = tp[i].cumsum(0)
|
||||
|
||||
# Recall
|
||||
recall = tpc / (n_l + 1e-16) # recall curve
|
||||
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
|
||||
|
||||
# Precision
|
||||
precision = tpc / (tpc + fpc) # precision curve
|
||||
p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score
|
||||
|
||||
# AP from recall-precision curve
|
||||
for j in range(tp.shape[1]):
|
||||
ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j], v5_metric=v5_metric)
|
||||
if plot and j == 0:
|
||||
py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5
|
||||
|
||||
# Compute F1 (harmonic mean of precision and recall)
|
||||
f1 = 2 * p * r / (p + r + 1e-16)
|
||||
if plot:
|
||||
plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
|
||||
plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
|
||||
plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
|
||||
plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')
|
||||
|
||||
i = f1.mean(0).argmax() # max F1 index
|
||||
return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')
|
||||
|
||||
|
||||
def compute_ap(recall, precision, v5_metric=False):
|
||||
""" Compute the average precision, given the recall and precision curves
|
||||
# Arguments
|
||||
recall: The recall curve (list)
|
||||
precision: The precision curve (list)
|
||||
v5_metric: Assume maximum recall to be 1.0, as in YOLOv5, MMDetetion etc.
|
||||
# Returns
|
||||
Average precision, precision curve, recall curve
|
||||
"""
|
||||
|
||||
# Append sentinel values to beginning and end
|
||||
if v5_metric: # New YOLOv5 metric, same as MMDetection and Detectron2 repositories
|
||||
mrec = np.concatenate(([0.], recall, [1.0]))
|
||||
else: # Old YOLOv5 metric, i.e. default YOLOv7 metric
|
||||
mrec = np.concatenate(([0.], recall, [recall[-1] + 0.01]))
|
||||
mpre = np.concatenate(([1.], precision, [0.]))
|
||||
|
||||
# Compute the precision envelope
|
||||
mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
|
||||
|
||||
# Integrate area under curve
|
||||
method = 'interp' # methods: 'continuous', 'interp'
|
||||
if method == 'interp':
|
||||
x = np.linspace(0, 1, 101) # 101-point interp (COCO)
|
||||
ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate
|
||||
else: # 'continuous'
|
||||
i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes
|
||||
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve
|
||||
|
||||
return ap, mpre, mrec
|
||||
|
||||
|
||||
class ConfusionMatrix:
|
||||
# Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
|
||||
def __init__(self, nc, conf=0.25, iou_thres=0.45):
|
||||
self.matrix = np.zeros((nc + 1, nc + 1))
|
||||
self.nc = nc # number of classes
|
||||
self.conf = conf
|
||||
self.iou_thres = iou_thres
|
||||
|
||||
def process_batch(self, detections, labels):
|
||||
"""
|
||||
Return intersection-over-union (Jaccard index) of boxes.
|
||||
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
|
||||
Arguments:
|
||||
detections (Array[N, 6]), x1, y1, x2, y2, conf, class
|
||||
labels (Array[M, 5]), class, x1, y1, x2, y2
|
||||
Returns:
|
||||
None, updates confusion matrix accordingly
|
||||
"""
|
||||
detections = detections[detections[:, 4] > self.conf]
|
||||
gt_classes = labels[:, 0].int()
|
||||
detection_classes = detections[:, 5].int()
|
||||
iou = general.box_iou(labels[:, 1:], detections[:, :4])
|
||||
|
||||
x = torch.where(iou > self.iou_thres)
|
||||
if x[0].shape[0]:
|
||||
matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
|
||||
if x[0].shape[0] > 1:
|
||||
matches = matches[matches[:, 2].argsort()[::-1]]
|
||||
matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
|
||||
matches = matches[matches[:, 2].argsort()[::-1]]
|
||||
matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
|
||||
else:
|
||||
matches = np.zeros((0, 3))
|
||||
|
||||
n = matches.shape[0] > 0
|
||||
m0, m1, _ = matches.transpose().astype(np.int16)
|
||||
for i, gc in enumerate(gt_classes):
|
||||
j = m0 == i
|
||||
if n and sum(j) == 1:
|
||||
self.matrix[gc, detection_classes[m1[j]]] += 1 # correct
|
||||
else:
|
||||
self.matrix[self.nc, gc] += 1 # background FP
|
||||
|
||||
if n:
|
||||
for i, dc in enumerate(detection_classes):
|
||||
if not any(m1 == i):
|
||||
self.matrix[dc, self.nc] += 1 # background FN
|
||||
|
||||
def matrix(self):
|
||||
return self.matrix
|
||||
|
||||
def plot(self, save_dir='', names=()):
|
||||
try:
|
||||
import seaborn as sn
|
||||
|
||||
array = self.matrix / (self.matrix.sum(0).reshape(1, self.nc + 1) + 1E-6) # normalize
|
||||
array[array < 0.005] = np.nan # don't annotate (would appear as 0.00)
|
||||
|
||||
fig = plt.figure(figsize=(12, 9), tight_layout=True)
|
||||
sn.set(font_scale=1.0 if self.nc < 50 else 0.8) # for label size
|
||||
labels = (0 < len(names) < 99) and len(names) == self.nc # apply names to ticklabels
|
||||
sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
|
||||
xticklabels=names + ['background FP'] if labels else "auto",
|
||||
yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
|
||||
fig.axes[0].set_xlabel('True')
|
||||
fig.axes[0].set_ylabel('Predicted')
|
||||
fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def print(self):
|
||||
for i in range(self.nc + 1):
|
||||
print(' '.join(map(str, self.matrix[i])))
|
||||
|
||||
|
||||
# Plots ----------------------------------------------------------------------------------------------------------------
|
||||
|
||||
def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
|
||||
# Precision-recall curve
|
||||
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
|
||||
py = np.stack(py, axis=1)
|
||||
|
||||
if 0 < len(names) < 21: # display per-class legend if < 21 classes
|
||||
for i, y in enumerate(py.T):
|
||||
ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision)
|
||||
else:
|
||||
ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision)
|
||||
|
||||
ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean())
|
||||
ax.set_xlabel('Recall')
|
||||
ax.set_ylabel('Precision')
|
||||
ax.set_xlim(0, 1)
|
||||
ax.set_ylim(0, 1)
|
||||
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
|
||||
fig.savefig(Path(save_dir), dpi=250)
|
||||
|
||||
|
||||
def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'):
|
||||
# Metric-confidence curve
|
||||
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
|
||||
|
||||
if 0 < len(names) < 21: # display per-class legend if < 21 classes
|
||||
for i, y in enumerate(py):
|
||||
ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric)
|
||||
else:
|
||||
ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric)
|
||||
|
||||
y = py.mean(0)
|
||||
ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}')
|
||||
ax.set_xlabel(xlabel)
|
||||
ax.set_ylabel(ylabel)
|
||||
ax.set_xlim(0, 1)
|
||||
ax.set_ylim(0, 1)
|
||||
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
|
||||
fig.savefig(Path(save_dir), dpi=250)
|
||||
@@ -0,0 +1,489 @@
|
||||
# Plotting utils
|
||||
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
from copy import copy
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import matplotlib
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import seaborn as sns
|
||||
import torch
|
||||
import yaml
|
||||
from PIL import Image, ImageDraw, ImageFont
|
||||
from scipy.signal import butter, filtfilt
|
||||
|
||||
from utils.general import xywh2xyxy, xyxy2xywh
|
||||
from utils.metrics import fitness
|
||||
|
||||
# Settings
|
||||
matplotlib.rc('font', **{'size': 11})
|
||||
matplotlib.use('Agg') # for writing to files only
|
||||
|
||||
|
||||
def color_list():
|
||||
# Return first 10 plt colors as (r,g,b) https://stackoverflow.com/questions/51350872/python-from-color-name-to-rgb
|
||||
def hex2rgb(h):
|
||||
return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))
|
||||
|
||||
return [hex2rgb(h) for h in matplotlib.colors.TABLEAU_COLORS.values()] # or BASE_ (8), CSS4_ (148), XKCD_ (949)
|
||||
|
||||
|
||||
def hist2d(x, y, n=100):
|
||||
# 2d histogram used in labels.png and evolve.png
|
||||
xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n)
|
||||
hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges))
|
||||
xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1)
|
||||
yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1)
|
||||
return np.log(hist[xidx, yidx])
|
||||
|
||||
|
||||
def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5):
|
||||
# https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy
|
||||
def butter_lowpass(cutoff, fs, order):
|
||||
nyq = 0.5 * fs
|
||||
normal_cutoff = cutoff / nyq
|
||||
return butter(order, normal_cutoff, btype='low', analog=False)
|
||||
|
||||
b, a = butter_lowpass(cutoff, fs, order=order)
|
||||
return filtfilt(b, a, data) # forward-backward filter
|
||||
|
||||
|
||||
def plot_one_box(x, img, color=None, label=None, line_thickness=3):
|
||||
# Plots one bounding box on image img
|
||||
tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
|
||||
color = color or [random.randint(0, 255) for _ in range(3)]
|
||||
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
|
||||
cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
|
||||
if label:
|
||||
tf = max(tl - 1, 1) # font thickness
|
||||
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
|
||||
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
|
||||
cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled
|
||||
cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
|
||||
|
||||
|
||||
def plot_one_box_PIL(box, img, color=None, label=None, line_thickness=None):
|
||||
img = Image.fromarray(img)
|
||||
draw = ImageDraw.Draw(img)
|
||||
line_thickness = line_thickness or max(int(min(img.size) / 200), 2)
|
||||
draw.rectangle(box, width=line_thickness, outline=tuple(color)) # plot
|
||||
if label:
|
||||
fontsize = max(round(max(img.size) / 40), 12)
|
||||
font = ImageFont.truetype("Arial.ttf", fontsize)
|
||||
txt_width, txt_height = font.getsize(label)
|
||||
draw.rectangle([box[0], box[1] - txt_height + 4, box[0] + txt_width, box[1]], fill=tuple(color))
|
||||
draw.text((box[0], box[1] - txt_height + 1), label, fill=(255, 255, 255), font=font)
|
||||
return np.asarray(img)
|
||||
|
||||
|
||||
def plot_wh_methods(): # from utils.plots import *; plot_wh_methods()
|
||||
# Compares the two methods for width-height anchor multiplication
|
||||
# https://github.com/ultralytics/yolov3/issues/168
|
||||
x = np.arange(-4.0, 4.0, .1)
|
||||
ya = np.exp(x)
|
||||
yb = torch.sigmoid(torch.from_numpy(x)).numpy() * 2
|
||||
|
||||
fig = plt.figure(figsize=(6, 3), tight_layout=True)
|
||||
plt.plot(x, ya, '.-', label='YOLOv3')
|
||||
plt.plot(x, yb ** 2, '.-', label='YOLOR ^2')
|
||||
plt.plot(x, yb ** 1.6, '.-', label='YOLOR ^1.6')
|
||||
plt.xlim(left=-4, right=4)
|
||||
plt.ylim(bottom=0, top=6)
|
||||
plt.xlabel('input')
|
||||
plt.ylabel('output')
|
||||
plt.grid()
|
||||
plt.legend()
|
||||
fig.savefig('comparison.png', dpi=200)
|
||||
|
||||
|
||||
def output_to_target(output):
|
||||
# Convert model output to target format [batch_id, class_id, x, y, w, h, conf]
|
||||
targets = []
|
||||
for i, o in enumerate(output):
|
||||
for *box, conf, cls in o.cpu().numpy():
|
||||
targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf])
|
||||
return np.array(targets)
|
||||
|
||||
|
||||
def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=640, max_subplots=16):
|
||||
# Plot image grid with labels
|
||||
|
||||
if isinstance(images, torch.Tensor):
|
||||
images = images.cpu().float().numpy()
|
||||
if isinstance(targets, torch.Tensor):
|
||||
targets = targets.cpu().numpy()
|
||||
|
||||
# un-normalise
|
||||
if np.max(images[0]) <= 1:
|
||||
images *= 255
|
||||
|
||||
tl = 3 # line thickness
|
||||
tf = max(tl - 1, 1) # font thickness
|
||||
bs, _, h, w = images.shape # batch size, _, height, width
|
||||
bs = min(bs, max_subplots) # limit plot images
|
||||
ns = np.ceil(bs ** 0.5) # number of subplots (square)
|
||||
|
||||
# Check if we should resize
|
||||
scale_factor = max_size / max(h, w)
|
||||
if scale_factor < 1:
|
||||
h = math.ceil(scale_factor * h)
|
||||
w = math.ceil(scale_factor * w)
|
||||
|
||||
colors = color_list() # list of colors
|
||||
mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init
|
||||
for i, img in enumerate(images):
|
||||
if i == max_subplots: # if last batch has fewer images than we expect
|
||||
break
|
||||
|
||||
block_x = int(w * (i // ns))
|
||||
block_y = int(h * (i % ns))
|
||||
|
||||
img = img.transpose(1, 2, 0)
|
||||
if scale_factor < 1:
|
||||
img = cv2.resize(img, (w, h))
|
||||
|
||||
mosaic[block_y:block_y + h, block_x:block_x + w, :] = img
|
||||
if len(targets) > 0:
|
||||
image_targets = targets[targets[:, 0] == i]
|
||||
boxes = xywh2xyxy(image_targets[:, 2:6]).T
|
||||
classes = image_targets[:, 1].astype('int')
|
||||
labels = image_targets.shape[1] == 6 # labels if no conf column
|
||||
conf = None if labels else image_targets[:, 6] # check for confidence presence (label vs pred)
|
||||
|
||||
if boxes.shape[1]:
|
||||
if boxes.max() <= 1.01: # if normalized with tolerance 0.01
|
||||
boxes[[0, 2]] *= w # scale to pixels
|
||||
boxes[[1, 3]] *= h
|
||||
elif scale_factor < 1: # absolute coords need scale if image scales
|
||||
boxes *= scale_factor
|
||||
boxes[[0, 2]] += block_x
|
||||
boxes[[1, 3]] += block_y
|
||||
for j, box in enumerate(boxes.T):
|
||||
cls = int(classes[j])
|
||||
color = colors[cls % len(colors)]
|
||||
cls = names[cls] if names else cls
|
||||
if labels or conf[j] > 0.25: # 0.25 conf thresh
|
||||
label = '%s' % cls if labels else '%s %.1f' % (cls, conf[j])
|
||||
plot_one_box(box, mosaic, label=label, color=color, line_thickness=tl)
|
||||
|
||||
# Draw image filename labels
|
||||
if paths:
|
||||
label = Path(paths[i]).name[:40] # trim to 40 char
|
||||
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
|
||||
cv2.putText(mosaic, label, (block_x + 5, block_y + t_size[1] + 5), 0, tl / 3, [220, 220, 220], thickness=tf,
|
||||
lineType=cv2.LINE_AA)
|
||||
|
||||
# Image border
|
||||
cv2.rectangle(mosaic, (block_x, block_y), (block_x + w, block_y + h), (255, 255, 255), thickness=3)
|
||||
|
||||
if fname:
|
||||
r = min(1280. / max(h, w) / ns, 1.0) # ratio to limit image size
|
||||
mosaic = cv2.resize(mosaic, (int(ns * w * r), int(ns * h * r)), interpolation=cv2.INTER_AREA)
|
||||
# cv2.imwrite(fname, cv2.cvtColor(mosaic, cv2.COLOR_BGR2RGB)) # cv2 save
|
||||
Image.fromarray(mosaic).save(fname) # PIL save
|
||||
return mosaic
|
||||
|
||||
|
||||
def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''):
|
||||
# Plot LR simulating training for full epochs
|
||||
optimizer, scheduler = copy(optimizer), copy(scheduler) # do not modify originals
|
||||
y = []
|
||||
for _ in range(epochs):
|
||||
scheduler.step()
|
||||
y.append(optimizer.param_groups[0]['lr'])
|
||||
plt.plot(y, '.-', label='LR')
|
||||
plt.xlabel('epoch')
|
||||
plt.ylabel('LR')
|
||||
plt.grid()
|
||||
plt.xlim(0, epochs)
|
||||
plt.ylim(0)
|
||||
plt.savefig(Path(save_dir) / 'LR.png', dpi=200)
|
||||
plt.close()
|
||||
|
||||
|
||||
def plot_test_txt(): # from utils.plots import *; plot_test()
|
||||
# Plot test.txt histograms
|
||||
x = np.loadtxt('test.txt', dtype=np.float32)
|
||||
box = xyxy2xywh(x[:, :4])
|
||||
cx, cy = box[:, 0], box[:, 1]
|
||||
|
||||
fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True)
|
||||
ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0)
|
||||
ax.set_aspect('equal')
|
||||
plt.savefig('hist2d.png', dpi=300)
|
||||
|
||||
fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True)
|
||||
ax[0].hist(cx, bins=600)
|
||||
ax[1].hist(cy, bins=600)
|
||||
plt.savefig('hist1d.png', dpi=200)
|
||||
|
||||
|
||||
def plot_targets_txt(): # from utils.plots import *; plot_targets_txt()
|
||||
# Plot targets.txt histograms
|
||||
x = np.loadtxt('targets.txt', dtype=np.float32).T
|
||||
s = ['x targets', 'y targets', 'width targets', 'height targets']
|
||||
fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)
|
||||
ax = ax.ravel()
|
||||
for i in range(4):
|
||||
ax[i].hist(x[i], bins=100, label='%.3g +/- %.3g' % (x[i].mean(), x[i].std()))
|
||||
ax[i].legend()
|
||||
ax[i].set_title(s[i])
|
||||
plt.savefig('targets.jpg', dpi=200)
|
||||
|
||||
|
||||
def plot_study_txt(path='', x=None): # from utils.plots import *; plot_study_txt()
|
||||
# Plot study.txt generated by test.py
|
||||
fig, ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)
|
||||
# ax = ax.ravel()
|
||||
|
||||
fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
|
||||
# for f in [Path(path) / f'study_coco_{x}.txt' for x in ['yolor-p6', 'yolor-w6', 'yolor-e6', 'yolor-d6']]:
|
||||
for f in sorted(Path(path).glob('study*.txt')):
|
||||
y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T
|
||||
x = np.arange(y.shape[1]) if x is None else np.array(x)
|
||||
s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_inference (ms/img)', 't_NMS (ms/img)', 't_total (ms/img)']
|
||||
# for i in range(7):
|
||||
# ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8)
|
||||
# ax[i].set_title(s[i])
|
||||
|
||||
j = y[3].argmax() + 1
|
||||
ax2.plot(y[6, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8,
|
||||
label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
|
||||
|
||||
ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],
|
||||
'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet')
|
||||
|
||||
ax2.grid(alpha=0.2)
|
||||
ax2.set_yticks(np.arange(20, 60, 5))
|
||||
ax2.set_xlim(0, 57)
|
||||
ax2.set_ylim(30, 55)
|
||||
ax2.set_xlabel('GPU Speed (ms/img)')
|
||||
ax2.set_ylabel('COCO AP val')
|
||||
ax2.legend(loc='lower right')
|
||||
plt.savefig(str(Path(path).name) + '.png', dpi=300)
|
||||
|
||||
|
||||
def plot_labels(labels, names=(), save_dir=Path(''), loggers=None):
|
||||
# plot dataset labels
|
||||
print('Plotting labels... ')
|
||||
c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes
|
||||
nc = int(c.max() + 1) # number of classes
|
||||
colors = color_list()
|
||||
x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height'])
|
||||
|
||||
# seaborn correlogram
|
||||
sns.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9))
|
||||
plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200)
|
||||
plt.close()
|
||||
|
||||
# matplotlib labels
|
||||
matplotlib.use('svg') # faster
|
||||
ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel()
|
||||
ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8)
|
||||
ax[0].set_ylabel('instances')
|
||||
if 0 < len(names) < 30:
|
||||
ax[0].set_xticks(range(len(names)))
|
||||
ax[0].set_xticklabels(names, rotation=90, fontsize=10)
|
||||
else:
|
||||
ax[0].set_xlabel('classes')
|
||||
sns.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9)
|
||||
sns.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9)
|
||||
|
||||
# rectangles
|
||||
labels[:, 1:3] = 0.5 # center
|
||||
labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000
|
||||
img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255)
|
||||
for cls, *box in labels[:1000]:
|
||||
ImageDraw.Draw(img).rectangle(box, width=1, outline=colors[int(cls) % 10]) # plot
|
||||
ax[1].imshow(img)
|
||||
ax[1].axis('off')
|
||||
|
||||
for a in [0, 1, 2, 3]:
|
||||
for s in ['top', 'right', 'left', 'bottom']:
|
||||
ax[a].spines[s].set_visible(False)
|
||||
|
||||
plt.savefig(save_dir / 'labels.jpg', dpi=200)
|
||||
matplotlib.use('Agg')
|
||||
plt.close()
|
||||
|
||||
# loggers
|
||||
for k, v in loggers.items() or {}:
|
||||
if k == 'wandb' and v:
|
||||
v.log({"Labels": [v.Image(str(x), caption=x.name) for x in save_dir.glob('*labels*.jpg')]}, commit=False)
|
||||
|
||||
|
||||
def plot_evolution(yaml_file='data/hyp.finetune.yaml'): # from utils.plots import *; plot_evolution()
|
||||
# Plot hyperparameter evolution results in evolve.txt
|
||||
with open(yaml_file) as f:
|
||||
hyp = yaml.load(f, Loader=yaml.SafeLoader)
|
||||
x = np.loadtxt('evolve.txt', ndmin=2)
|
||||
f = fitness(x)
|
||||
# weights = (f - f.min()) ** 2 # for weighted results
|
||||
plt.figure(figsize=(10, 12), tight_layout=True)
|
||||
matplotlib.rc('font', **{'size': 8})
|
||||
for i, (k, v) in enumerate(hyp.items()):
|
||||
y = x[:, i + 7]
|
||||
# mu = (y * weights).sum() / weights.sum() # best weighted result
|
||||
mu = y[f.argmax()] # best single result
|
||||
plt.subplot(6, 5, i + 1)
|
||||
plt.scatter(y, f, c=hist2d(y, f, 20), cmap='viridis', alpha=.8, edgecolors='none')
|
||||
plt.plot(mu, f.max(), 'k+', markersize=15)
|
||||
plt.title('%s = %.3g' % (k, mu), fontdict={'size': 9}) # limit to 40 characters
|
||||
if i % 5 != 0:
|
||||
plt.yticks([])
|
||||
print('%15s: %.3g' % (k, mu))
|
||||
plt.savefig('evolve.png', dpi=200)
|
||||
print('\nPlot saved as evolve.png')
|
||||
|
||||
|
||||
def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
|
||||
# Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection()
|
||||
ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel()
|
||||
s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS']
|
||||
files = list(Path(save_dir).glob('frames*.txt'))
|
||||
for fi, f in enumerate(files):
|
||||
try:
|
||||
results = np.loadtxt(f, ndmin=2).T[:, 90:-30] # clip first and last rows
|
||||
n = results.shape[1] # number of rows
|
||||
x = np.arange(start, min(stop, n) if stop else n)
|
||||
results = results[:, x]
|
||||
t = (results[0] - results[0].min()) # set t0=0s
|
||||
results[0] = x
|
||||
for i, a in enumerate(ax):
|
||||
if i < len(results):
|
||||
label = labels[fi] if len(labels) else f.stem.replace('frames_', '')
|
||||
a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5)
|
||||
a.set_title(s[i])
|
||||
a.set_xlabel('time (s)')
|
||||
# if fi == len(files) - 1:
|
||||
# a.set_ylim(bottom=0)
|
||||
for side in ['top', 'right']:
|
||||
a.spines[side].set_visible(False)
|
||||
else:
|
||||
a.remove()
|
||||
except Exception as e:
|
||||
print('Warning: Plotting error for %s; %s' % (f, e))
|
||||
|
||||
ax[1].legend()
|
||||
plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
|
||||
|
||||
|
||||
def plot_results_overlay(start=0, stop=0): # from utils.plots import *; plot_results_overlay()
|
||||
# Plot training 'results*.txt', overlaying train and val losses
|
||||
s = ['train', 'train', 'train', 'Precision', 'mAP@0.5', 'val', 'val', 'val', 'Recall', 'mAP@0.5:0.95'] # legends
|
||||
t = ['Box', 'Objectness', 'Classification', 'P-R', 'mAP-F1'] # titles
|
||||
for f in sorted(glob.glob('results*.txt') + glob.glob('../../Downloads/results*.txt')):
|
||||
results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T
|
||||
n = results.shape[1] # number of rows
|
||||
x = range(start, min(stop, n) if stop else n)
|
||||
fig, ax = plt.subplots(1, 5, figsize=(14, 3.5), tight_layout=True)
|
||||
ax = ax.ravel()
|
||||
for i in range(5):
|
||||
for j in [i, i + 5]:
|
||||
y = results[j, x]
|
||||
ax[i].plot(x, y, marker='.', label=s[j])
|
||||
# y_smooth = butter_lowpass_filtfilt(y)
|
||||
# ax[i].plot(x, np.gradient(y_smooth), marker='.', label=s[j])
|
||||
|
||||
ax[i].set_title(t[i])
|
||||
ax[i].legend()
|
||||
ax[i].set_ylabel(f) if i == 0 else None # add filename
|
||||
fig.savefig(f.replace('.txt', '.png'), dpi=200)
|
||||
|
||||
|
||||
def plot_results(start=0, stop=0, bucket='', id=(), labels=(), save_dir=''):
|
||||
# Plot training 'results*.txt'. from utils.plots import *; plot_results(save_dir='runs/train/exp')
|
||||
fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True)
|
||||
ax = ax.ravel()
|
||||
s = ['Box', 'Objectness', 'Classification', 'Precision', 'Recall',
|
||||
'val Box', 'val Objectness', 'val Classification', 'mAP@0.5', 'mAP@0.5:0.95']
|
||||
if bucket:
|
||||
# files = ['https://storage.googleapis.com/%s/results%g.txt' % (bucket, x) for x in id]
|
||||
files = ['results%g.txt' % x for x in id]
|
||||
c = ('gsutil cp ' + '%s ' * len(files) + '.') % tuple('gs://%s/results%g.txt' % (bucket, x) for x in id)
|
||||
os.system(c)
|
||||
else:
|
||||
files = list(Path(save_dir).glob('results*.txt'))
|
||||
assert len(files), 'No results.txt files found in %s, nothing to plot.' % os.path.abspath(save_dir)
|
||||
for fi, f in enumerate(files):
|
||||
try:
|
||||
results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T
|
||||
n = results.shape[1] # number of rows
|
||||
x = range(start, min(stop, n) if stop else n)
|
||||
for i in range(10):
|
||||
y = results[i, x]
|
||||
if i in [0, 1, 2, 5, 6, 7]:
|
||||
y[y == 0] = np.nan # don't show zero loss values
|
||||
# y /= y[0] # normalize
|
||||
label = labels[fi] if len(labels) else f.stem
|
||||
ax[i].plot(x, y, marker='.', label=label, linewidth=2, markersize=8)
|
||||
ax[i].set_title(s[i])
|
||||
# if i in [5, 6, 7]: # share train and val loss y axes
|
||||
# ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
|
||||
except Exception as e:
|
||||
print('Warning: Plotting error for %s; %s' % (f, e))
|
||||
|
||||
ax[1].legend()
|
||||
fig.savefig(Path(save_dir) / 'results.png', dpi=200)
|
||||
|
||||
|
||||
def output_to_keypoint(output):
|
||||
# Convert model output to target format [batch_id, class_id, x, y, w, h, conf]
|
||||
targets = []
|
||||
for i, o in enumerate(output):
|
||||
kpts = o[:,6:]
|
||||
o = o[:,:6]
|
||||
for index, (*box, conf, cls) in enumerate(o.detach().cpu().numpy()):
|
||||
targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf, *list(kpts.detach().cpu().numpy()[index])])
|
||||
return np.array(targets)
|
||||
|
||||
|
||||
def plot_skeleton_kpts(im, kpts, steps, orig_shape=None):
|
||||
#Plot the skeleton and keypointsfor coco datatset
|
||||
palette = np.array([[255, 128, 0], [255, 153, 51], [255, 178, 102],
|
||||
[230, 230, 0], [255, 153, 255], [153, 204, 255],
|
||||
[255, 102, 255], [255, 51, 255], [102, 178, 255],
|
||||
[51, 153, 255], [255, 153, 153], [255, 102, 102],
|
||||
[255, 51, 51], [153, 255, 153], [102, 255, 102],
|
||||
[51, 255, 51], [0, 255, 0], [0, 0, 255], [255, 0, 0],
|
||||
[255, 255, 255]])
|
||||
|
||||
skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12],
|
||||
[7, 13], [6, 7], [6, 8], [7, 9], [8, 10], [9, 11], [2, 3],
|
||||
[1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]
|
||||
|
||||
pose_limb_color = palette[[9, 9, 9, 9, 7, 7, 7, 0, 0, 0, 0, 0, 16, 16, 16, 16, 16, 16, 16]]
|
||||
pose_kpt_color = palette[[16, 16, 16, 16, 16, 0, 0, 0, 0, 0, 0, 9, 9, 9, 9, 9, 9]]
|
||||
radius = 5
|
||||
num_kpts = len(kpts) // steps
|
||||
|
||||
for kid in range(num_kpts):
|
||||
r, g, b = pose_kpt_color[kid]
|
||||
x_coord, y_coord = kpts[steps * kid], kpts[steps * kid + 1]
|
||||
if not (x_coord % 640 == 0 or y_coord % 640 == 0):
|
||||
if steps == 3:
|
||||
conf = kpts[steps * kid + 2]
|
||||
if conf < 0.5:
|
||||
continue
|
||||
cv2.circle(im, (int(x_coord), int(y_coord)), radius, (int(r), int(g), int(b)), -1)
|
||||
|
||||
for sk_id, sk in enumerate(skeleton):
|
||||
r, g, b = pose_limb_color[sk_id]
|
||||
pos1 = (int(kpts[(sk[0]-1)*steps]), int(kpts[(sk[0]-1)*steps+1]))
|
||||
pos2 = (int(kpts[(sk[1]-1)*steps]), int(kpts[(sk[1]-1)*steps+1]))
|
||||
if steps == 3:
|
||||
conf1 = kpts[(sk[0]-1)*steps+2]
|
||||
conf2 = kpts[(sk[1]-1)*steps+2]
|
||||
if conf1<0.5 or conf2<0.5:
|
||||
continue
|
||||
if pos1[0]%640 == 0 or pos1[1]%640==0 or pos1[0]<0 or pos1[1]<0:
|
||||
continue
|
||||
if pos2[0] % 640 == 0 or pos2[1] % 640 == 0 or pos2[0]<0 or pos2[1]<0:
|
||||
continue
|
||||
cv2.line(im, pos1, pos2, (int(r), int(g), int(b)), thickness=2)
|
||||
@@ -0,0 +1,374 @@
|
||||
# YOLOR PyTorch utils
|
||||
|
||||
import datetime
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import platform
|
||||
import subprocess
|
||||
import time
|
||||
from contextlib import contextmanager
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torchvision
|
||||
|
||||
try:
|
||||
import thop # for FLOPS computation
|
||||
except ImportError:
|
||||
thop = None
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def torch_distributed_zero_first(local_rank: int):
|
||||
"""
|
||||
Decorator to make all processes in distributed training wait for each local_master to do something.
|
||||
"""
|
||||
if local_rank not in [-1, 0]:
|
||||
torch.distributed.barrier()
|
||||
yield
|
||||
if local_rank == 0:
|
||||
torch.distributed.barrier()
|
||||
|
||||
|
||||
def init_torch_seeds(seed=0):
|
||||
# Speed-reproducibility tradeoff https://pytorch.org/docs/stable/notes/randomness.html
|
||||
torch.manual_seed(seed)
|
||||
if seed == 0: # slower, more reproducible
|
||||
cudnn.benchmark, cudnn.deterministic = False, True
|
||||
else: # faster, less reproducible
|
||||
cudnn.benchmark, cudnn.deterministic = True, False
|
||||
|
||||
|
||||
def date_modified(path=__file__):
|
||||
# return human-readable file modification date, i.e. '2021-3-26'
|
||||
t = datetime.datetime.fromtimestamp(Path(path).stat().st_mtime)
|
||||
return f'{t.year}-{t.month}-{t.day}'
|
||||
|
||||
|
||||
def git_describe(path=Path(__file__).parent): # path must be a directory
|
||||
# return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe
|
||||
s = f'git -C {path} describe --tags --long --always'
|
||||
try:
|
||||
return subprocess.check_output(s, shell=True, stderr=subprocess.STDOUT).decode()[:-1]
|
||||
except subprocess.CalledProcessError as e:
|
||||
return '' # not a git repository
|
||||
|
||||
|
||||
def select_device(device='', batch_size=None):
|
||||
# device = 'cpu' or '0' or '0,1,2,3'
|
||||
s = f'YOLOR 🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string
|
||||
cpu = device.lower() == 'cpu'
|
||||
if cpu:
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False
|
||||
elif device: # non-cpu device requested
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable
|
||||
assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested' # check availability
|
||||
|
||||
cuda = not cpu and torch.cuda.is_available()
|
||||
if cuda:
|
||||
n = torch.cuda.device_count()
|
||||
if n > 1 and batch_size: # check that batch_size is compatible with device_count
|
||||
assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
|
||||
space = ' ' * len(s)
|
||||
for i, d in enumerate(device.split(',') if device else range(n)):
|
||||
p = torch.cuda.get_device_properties(i)
|
||||
s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2}MB)\n" # bytes to MB
|
||||
else:
|
||||
s += 'CPU\n'
|
||||
|
||||
logger.info(s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s) # emoji-safe
|
||||
return torch.device('cuda:0' if cuda else 'cpu')
|
||||
|
||||
|
||||
def time_synchronized():
|
||||
# pytorch-accurate time
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.synchronize()
|
||||
return time.time()
|
||||
|
||||
|
||||
def profile(x, ops, n=100, device=None):
|
||||
# profile a pytorch module or list of modules. Example usage:
|
||||
# x = torch.randn(16, 3, 640, 640) # input
|
||||
# m1 = lambda x: x * torch.sigmoid(x)
|
||||
# m2 = nn.SiLU()
|
||||
# profile(x, [m1, m2], n=100) # profile speed over 100 iterations
|
||||
|
||||
device = device or torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
|
||||
x = x.to(device)
|
||||
x.requires_grad = True
|
||||
print(torch.__version__, device.type, torch.cuda.get_device_properties(0) if device.type == 'cuda' else '')
|
||||
print(f"\n{'Params':>12s}{'GFLOPS':>12s}{'forward (ms)':>16s}{'backward (ms)':>16s}{'input':>24s}{'output':>24s}")
|
||||
for m in ops if isinstance(ops, list) else [ops]:
|
||||
m = m.to(device) if hasattr(m, 'to') else m # device
|
||||
m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m # type
|
||||
dtf, dtb, t = 0., 0., [0., 0., 0.] # dt forward, backward
|
||||
try:
|
||||
flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPS
|
||||
except:
|
||||
flops = 0
|
||||
|
||||
for _ in range(n):
|
||||
t[0] = time_synchronized()
|
||||
y = m(x)
|
||||
t[1] = time_synchronized()
|
||||
try:
|
||||
_ = y.sum().backward()
|
||||
t[2] = time_synchronized()
|
||||
except: # no backward method
|
||||
t[2] = float('nan')
|
||||
dtf += (t[1] - t[0]) * 1000 / n # ms per op forward
|
||||
dtb += (t[2] - t[1]) * 1000 / n # ms per op backward
|
||||
|
||||
s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list'
|
||||
s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list'
|
||||
p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0 # parameters
|
||||
print(f'{p:12}{flops:12.4g}{dtf:16.4g}{dtb:16.4g}{str(s_in):>24s}{str(s_out):>24s}')
|
||||
|
||||
|
||||
def is_parallel(model):
|
||||
return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)
|
||||
|
||||
|
||||
def intersect_dicts(da, db, exclude=()):
|
||||
# Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
|
||||
return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
|
||||
|
||||
|
||||
def initialize_weights(model):
|
||||
for m in model.modules():
|
||||
t = type(m)
|
||||
if t is nn.Conv2d:
|
||||
pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
|
||||
elif t is nn.BatchNorm2d:
|
||||
m.eps = 1e-3
|
||||
m.momentum = 0.03
|
||||
elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
|
||||
m.inplace = True
|
||||
|
||||
|
||||
def find_modules(model, mclass=nn.Conv2d):
|
||||
# Finds layer indices matching module class 'mclass'
|
||||
return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)]
|
||||
|
||||
|
||||
def sparsity(model):
|
||||
# Return global model sparsity
|
||||
a, b = 0., 0.
|
||||
for p in model.parameters():
|
||||
a += p.numel()
|
||||
b += (p == 0).sum()
|
||||
return b / a
|
||||
|
||||
|
||||
def prune(model, amount=0.3):
|
||||
# Prune model to requested global sparsity
|
||||
import torch.nn.utils.prune as prune
|
||||
print('Pruning model... ', end='')
|
||||
for name, m in model.named_modules():
|
||||
if isinstance(m, nn.Conv2d):
|
||||
prune.l1_unstructured(m, name='weight', amount=amount) # prune
|
||||
prune.remove(m, 'weight') # make permanent
|
||||
print(' %.3g global sparsity' % sparsity(model))
|
||||
|
||||
|
||||
def fuse_conv_and_bn(conv, bn):
|
||||
# Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/
|
||||
fusedconv = nn.Conv2d(conv.in_channels,
|
||||
conv.out_channels,
|
||||
kernel_size=conv.kernel_size,
|
||||
stride=conv.stride,
|
||||
padding=conv.padding,
|
||||
groups=conv.groups,
|
||||
bias=True).requires_grad_(False).to(conv.weight.device)
|
||||
|
||||
# prepare filters
|
||||
w_conv = conv.weight.clone().view(conv.out_channels, -1)
|
||||
w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
|
||||
fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
|
||||
|
||||
# prepare spatial bias
|
||||
b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias
|
||||
b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
|
||||
fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)
|
||||
|
||||
return fusedconv
|
||||
|
||||
|
||||
def model_info(model, verbose=False, img_size=640):
|
||||
# Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
|
||||
n_p = sum(x.numel() for x in model.parameters()) # number parameters
|
||||
n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
|
||||
if verbose:
|
||||
print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
|
||||
for i, (name, p) in enumerate(model.named_parameters()):
|
||||
name = name.replace('module_list.', '')
|
||||
print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
|
||||
(i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
|
||||
|
||||
try: # FLOPS
|
||||
from thop import profile
|
||||
stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32
|
||||
img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device) # input
|
||||
flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2 # stride GFLOPS
|
||||
img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float
|
||||
fs = ', %.1f GFLOPS' % (flops * img_size[0] / stride * img_size[1] / stride) # 640x640 GFLOPS
|
||||
except (ImportError, Exception):
|
||||
fs = ''
|
||||
|
||||
logger.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
|
||||
|
||||
|
||||
def load_classifier(name='resnet101', n=2):
|
||||
# Loads a pretrained model reshaped to n-class output
|
||||
model = torchvision.models.__dict__[name](pretrained=True)
|
||||
|
||||
# ResNet model properties
|
||||
# input_size = [3, 224, 224]
|
||||
# input_space = 'RGB'
|
||||
# input_range = [0, 1]
|
||||
# mean = [0.485, 0.456, 0.406]
|
||||
# std = [0.229, 0.224, 0.225]
|
||||
|
||||
# Reshape output to n classes
|
||||
filters = model.fc.weight.shape[1]
|
||||
model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True)
|
||||
model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True)
|
||||
model.fc.out_features = n
|
||||
return model
|
||||
|
||||
|
||||
def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
|
||||
# scales img(bs,3,y,x) by ratio constrained to gs-multiple
|
||||
if ratio == 1.0:
|
||||
return img
|
||||
else:
|
||||
h, w = img.shape[2:]
|
||||
s = (int(h * ratio), int(w * ratio)) # new size
|
||||
img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize
|
||||
if not same_shape: # pad/crop img
|
||||
h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)]
|
||||
return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean
|
||||
|
||||
|
||||
def copy_attr(a, b, include=(), exclude=()):
|
||||
# Copy attributes from b to a, options to only include [...] and to exclude [...]
|
||||
for k, v in b.__dict__.items():
|
||||
if (len(include) and k not in include) or k.startswith('_') or k in exclude:
|
||||
continue
|
||||
else:
|
||||
setattr(a, k, v)
|
||||
|
||||
|
||||
class ModelEMA:
|
||||
""" Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
|
||||
Keep a moving average of everything in the model state_dict (parameters and buffers).
|
||||
This is intended to allow functionality like
|
||||
https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
|
||||
A smoothed version of the weights is necessary for some training schemes to perform well.
|
||||
This class is sensitive where it is initialized in the sequence of model init,
|
||||
GPU assignment and distributed training wrappers.
|
||||
"""
|
||||
|
||||
def __init__(self, model, decay=0.9999, updates=0):
|
||||
# Create EMA
|
||||
self.ema = deepcopy(model.module if is_parallel(model) else model).eval() # FP32 EMA
|
||||
# if next(model.parameters()).device.type != 'cpu':
|
||||
# self.ema.half() # FP16 EMA
|
||||
self.updates = updates # number of EMA updates
|
||||
self.decay = lambda x: decay * (1 - math.exp(-x / 2000)) # decay exponential ramp (to help early epochs)
|
||||
for p in self.ema.parameters():
|
||||
p.requires_grad_(False)
|
||||
|
||||
def update(self, model):
|
||||
# Update EMA parameters
|
||||
with torch.no_grad():
|
||||
self.updates += 1
|
||||
d = self.decay(self.updates)
|
||||
|
||||
msd = model.module.state_dict() if is_parallel(model) else model.state_dict() # model state_dict
|
||||
for k, v in self.ema.state_dict().items():
|
||||
if v.dtype.is_floating_point:
|
||||
v *= d
|
||||
v += (1. - d) * msd[k].detach()
|
||||
|
||||
def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
|
||||
# Update EMA attributes
|
||||
copy_attr(self.ema, model, include, exclude)
|
||||
|
||||
|
||||
class BatchNormXd(torch.nn.modules.batchnorm._BatchNorm):
|
||||
def _check_input_dim(self, input):
|
||||
# The only difference between BatchNorm1d, BatchNorm2d, BatchNorm3d, etc
|
||||
# is this method that is overwritten by the sub-class
|
||||
# This original goal of this method was for tensor sanity checks
|
||||
# If you're ok bypassing those sanity checks (eg. if you trust your inference
|
||||
# to provide the right dimensional inputs), then you can just use this method
|
||||
# for easy conversion from SyncBatchNorm
|
||||
# (unfortunately, SyncBatchNorm does not store the original class - if it did
|
||||
# we could return the one that was originally created)
|
||||
return
|
||||
|
||||
def revert_sync_batchnorm(module):
|
||||
# this is very similar to the function that it is trying to revert:
|
||||
# https://github.com/pytorch/pytorch/blob/c8b3686a3e4ba63dc59e5dcfe5db3430df256833/torch/nn/modules/batchnorm.py#L679
|
||||
module_output = module
|
||||
if isinstance(module, torch.nn.modules.batchnorm.SyncBatchNorm):
|
||||
new_cls = BatchNormXd
|
||||
module_output = BatchNormXd(module.num_features,
|
||||
module.eps, module.momentum,
|
||||
module.affine,
|
||||
module.track_running_stats)
|
||||
if module.affine:
|
||||
with torch.no_grad():
|
||||
module_output.weight = module.weight
|
||||
module_output.bias = module.bias
|
||||
module_output.running_mean = module.running_mean
|
||||
module_output.running_var = module.running_var
|
||||
module_output.num_batches_tracked = module.num_batches_tracked
|
||||
if hasattr(module, "qconfig"):
|
||||
module_output.qconfig = module.qconfig
|
||||
for name, child in module.named_children():
|
||||
module_output.add_module(name, revert_sync_batchnorm(child))
|
||||
del module
|
||||
return module_output
|
||||
|
||||
|
||||
class TracedModel(nn.Module):
|
||||
|
||||
def __init__(self, model=None, device=None, img_size=(640,640)):
|
||||
super(TracedModel, self).__init__()
|
||||
|
||||
print(" Convert model to Traced-model... ")
|
||||
self.stride = model.stride
|
||||
self.names = model.names
|
||||
self.model = model
|
||||
|
||||
self.model = revert_sync_batchnorm(self.model)
|
||||
self.model.to('cpu')
|
||||
self.model.eval()
|
||||
|
||||
self.detect_layer = self.model.model[-1]
|
||||
self.model.traced = True
|
||||
|
||||
rand_example = torch.rand(1, 3, img_size, img_size)
|
||||
|
||||
traced_script_module = torch.jit.trace(self.model, rand_example, strict=False)
|
||||
#traced_script_module = torch.jit.script(self.model)
|
||||
traced_script_module.save("traced_model.pt")
|
||||
print(" traced_script_module saved! ")
|
||||
self.model = traced_script_module
|
||||
self.model.to(device)
|
||||
self.detect_layer.to(device)
|
||||
print(" model is traced! \n")
|
||||
|
||||
def forward(self, x, augment=False, profile=False):
|
||||
out = self.model(x)
|
||||
out = self.detect_layer(out)
|
||||
return out
|
||||
@@ -0,0 +1 @@
|
||||
# init
|
||||
@@ -0,0 +1,24 @@
|
||||
import argparse
|
||||
|
||||
import yaml
|
||||
|
||||
from wandb_utils import WandbLogger
|
||||
|
||||
WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
|
||||
|
||||
|
||||
def create_dataset_artifact(opt):
|
||||
with open(opt.data) as f:
|
||||
data = yaml.load(f, Loader=yaml.SafeLoader) # data dict
|
||||
logger = WandbLogger(opt, '', None, data, job_type='Dataset Creation')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--data', type=str, default='data/coco.yaml', help='data.yaml path')
|
||||
parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
|
||||
parser.add_argument('--project', type=str, default='YOLOR', help='name of W&B Project')
|
||||
opt = parser.parse_args()
|
||||
opt.resume = False # Explicitly disallow resume check for dataset upload job
|
||||
|
||||
create_dataset_artifact(opt)
|
||||
@@ -0,0 +1,306 @@
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import yaml
|
||||
from tqdm import tqdm
|
||||
|
||||
sys.path.append(str(Path(__file__).parent.parent.parent)) # add utils/ to path
|
||||
from utils.datasets import LoadImagesAndLabels
|
||||
from utils.datasets import img2label_paths
|
||||
from utils.general import colorstr, xywh2xyxy, check_dataset
|
||||
|
||||
try:
|
||||
import wandb
|
||||
from wandb import init, finish
|
||||
except ImportError:
|
||||
wandb = None
|
||||
|
||||
WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
|
||||
|
||||
|
||||
def remove_prefix(from_string, prefix=WANDB_ARTIFACT_PREFIX):
|
||||
return from_string[len(prefix):]
|
||||
|
||||
|
||||
def check_wandb_config_file(data_config_file):
|
||||
wandb_config = '_wandb.'.join(data_config_file.rsplit('.', 1)) # updated data.yaml path
|
||||
if Path(wandb_config).is_file():
|
||||
return wandb_config
|
||||
return data_config_file
|
||||
|
||||
|
||||
def get_run_info(run_path):
|
||||
run_path = Path(remove_prefix(run_path, WANDB_ARTIFACT_PREFIX))
|
||||
run_id = run_path.stem
|
||||
project = run_path.parent.stem
|
||||
model_artifact_name = 'run_' + run_id + '_model'
|
||||
return run_id, project, model_artifact_name
|
||||
|
||||
|
||||
def check_wandb_resume(opt):
|
||||
process_wandb_config_ddp_mode(opt) if opt.global_rank not in [-1, 0] else None
|
||||
if isinstance(opt.resume, str):
|
||||
if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
if opt.global_rank not in [-1, 0]: # For resuming DDP runs
|
||||
run_id, project, model_artifact_name = get_run_info(opt.resume)
|
||||
api = wandb.Api()
|
||||
artifact = api.artifact(project + '/' + model_artifact_name + ':latest')
|
||||
modeldir = artifact.download()
|
||||
opt.weights = str(Path(modeldir) / "last.pt")
|
||||
return True
|
||||
return None
|
||||
|
||||
|
||||
def process_wandb_config_ddp_mode(opt):
|
||||
with open(opt.data) as f:
|
||||
data_dict = yaml.load(f, Loader=yaml.SafeLoader) # data dict
|
||||
train_dir, val_dir = None, None
|
||||
if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX):
|
||||
api = wandb.Api()
|
||||
train_artifact = api.artifact(remove_prefix(data_dict['train']) + ':' + opt.artifact_alias)
|
||||
train_dir = train_artifact.download()
|
||||
train_path = Path(train_dir) / 'data/images/'
|
||||
data_dict['train'] = str(train_path)
|
||||
|
||||
if isinstance(data_dict['val'], str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX):
|
||||
api = wandb.Api()
|
||||
val_artifact = api.artifact(remove_prefix(data_dict['val']) + ':' + opt.artifact_alias)
|
||||
val_dir = val_artifact.download()
|
||||
val_path = Path(val_dir) / 'data/images/'
|
||||
data_dict['val'] = str(val_path)
|
||||
if train_dir or val_dir:
|
||||
ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml')
|
||||
with open(ddp_data_path, 'w') as f:
|
||||
yaml.dump(data_dict, f)
|
||||
opt.data = ddp_data_path
|
||||
|
||||
|
||||
class WandbLogger():
|
||||
def __init__(self, opt, name, run_id, data_dict, job_type='Training'):
|
||||
# Pre-training routine --
|
||||
self.job_type = job_type
|
||||
self.wandb, self.wandb_run, self.data_dict = wandb, None if not wandb else wandb.run, data_dict
|
||||
# It's more elegant to stick to 1 wandb.init call, but useful config data is overwritten in the WandbLogger's wandb.init call
|
||||
if isinstance(opt.resume, str): # checks resume from artifact
|
||||
if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
run_id, project, model_artifact_name = get_run_info(opt.resume)
|
||||
model_artifact_name = WANDB_ARTIFACT_PREFIX + model_artifact_name
|
||||
assert wandb, 'install wandb to resume wandb runs'
|
||||
# Resume wandb-artifact:// runs here| workaround for not overwriting wandb.config
|
||||
self.wandb_run = wandb.init(id=run_id, project=project, resume='allow')
|
||||
opt.resume = model_artifact_name
|
||||
elif self.wandb:
|
||||
self.wandb_run = wandb.init(config=opt,
|
||||
resume="allow",
|
||||
project='YOLOR' if opt.project == 'runs/train' else Path(opt.project).stem,
|
||||
name=name,
|
||||
job_type=job_type,
|
||||
id=run_id) if not wandb.run else wandb.run
|
||||
if self.wandb_run:
|
||||
if self.job_type == 'Training':
|
||||
if not opt.resume:
|
||||
wandb_data_dict = self.check_and_upload_dataset(opt) if opt.upload_dataset else data_dict
|
||||
# Info useful for resuming from artifacts
|
||||
self.wandb_run.config.opt = vars(opt)
|
||||
self.wandb_run.config.data_dict = wandb_data_dict
|
||||
self.data_dict = self.setup_training(opt, data_dict)
|
||||
if self.job_type == 'Dataset Creation':
|
||||
self.data_dict = self.check_and_upload_dataset(opt)
|
||||
else:
|
||||
prefix = colorstr('wandb: ')
|
||||
print(f"{prefix}Install Weights & Biases for YOLOR logging with 'pip install wandb' (recommended)")
|
||||
|
||||
def check_and_upload_dataset(self, opt):
|
||||
assert wandb, 'Install wandb to upload dataset'
|
||||
check_dataset(self.data_dict)
|
||||
config_path = self.log_dataset_artifact(opt.data,
|
||||
opt.single_cls,
|
||||
'YOLOR' if opt.project == 'runs/train' else Path(opt.project).stem)
|
||||
print("Created dataset config file ", config_path)
|
||||
with open(config_path) as f:
|
||||
wandb_data_dict = yaml.load(f, Loader=yaml.SafeLoader)
|
||||
return wandb_data_dict
|
||||
|
||||
def setup_training(self, opt, data_dict):
|
||||
self.log_dict, self.current_epoch, self.log_imgs = {}, 0, 16 # Logging Constants
|
||||
self.bbox_interval = opt.bbox_interval
|
||||
if isinstance(opt.resume, str):
|
||||
modeldir, _ = self.download_model_artifact(opt)
|
||||
if modeldir:
|
||||
self.weights = Path(modeldir) / "last.pt"
|
||||
config = self.wandb_run.config
|
||||
opt.weights, opt.save_period, opt.batch_size, opt.bbox_interval, opt.epochs, opt.hyp = str(
|
||||
self.weights), config.save_period, config.total_batch_size, config.bbox_interval, config.epochs, \
|
||||
config.opt['hyp']
|
||||
data_dict = dict(self.wandb_run.config.data_dict) # eliminates the need for config file to resume
|
||||
if 'val_artifact' not in self.__dict__: # If --upload_dataset is set, use the existing artifact, don't download
|
||||
self.train_artifact_path, self.train_artifact = self.download_dataset_artifact(data_dict.get('train'),
|
||||
opt.artifact_alias)
|
||||
self.val_artifact_path, self.val_artifact = self.download_dataset_artifact(data_dict.get('val'),
|
||||
opt.artifact_alias)
|
||||
self.result_artifact, self.result_table, self.val_table, self.weights = None, None, None, None
|
||||
if self.train_artifact_path is not None:
|
||||
train_path = Path(self.train_artifact_path) / 'data/images/'
|
||||
data_dict['train'] = str(train_path)
|
||||
if self.val_artifact_path is not None:
|
||||
val_path = Path(self.val_artifact_path) / 'data/images/'
|
||||
data_dict['val'] = str(val_path)
|
||||
self.val_table = self.val_artifact.get("val")
|
||||
self.map_val_table_path()
|
||||
if self.val_artifact is not None:
|
||||
self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
|
||||
self.result_table = wandb.Table(["epoch", "id", "prediction", "avg_confidence"])
|
||||
if opt.bbox_interval == -1:
|
||||
self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1
|
||||
return data_dict
|
||||
|
||||
def download_dataset_artifact(self, path, alias):
|
||||
if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
dataset_artifact = wandb.use_artifact(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias)
|
||||
assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'"
|
||||
datadir = dataset_artifact.download()
|
||||
return datadir, dataset_artifact
|
||||
return None, None
|
||||
|
||||
def download_model_artifact(self, opt):
|
||||
if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
model_artifact = wandb.use_artifact(remove_prefix(opt.resume, WANDB_ARTIFACT_PREFIX) + ":latest")
|
||||
assert model_artifact is not None, 'Error: W&B model artifact doesn\'t exist'
|
||||
modeldir = model_artifact.download()
|
||||
epochs_trained = model_artifact.metadata.get('epochs_trained')
|
||||
total_epochs = model_artifact.metadata.get('total_epochs')
|
||||
assert epochs_trained < total_epochs, 'training to %g epochs is finished, nothing to resume.' % (
|
||||
total_epochs)
|
||||
return modeldir, model_artifact
|
||||
return None, None
|
||||
|
||||
def log_model(self, path, opt, epoch, fitness_score, best_model=False):
|
||||
model_artifact = wandb.Artifact('run_' + wandb.run.id + '_model', type='model', metadata={
|
||||
'original_url': str(path),
|
||||
'epochs_trained': epoch + 1,
|
||||
'save period': opt.save_period,
|
||||
'project': opt.project,
|
||||
'total_epochs': opt.epochs,
|
||||
'fitness_score': fitness_score
|
||||
})
|
||||
model_artifact.add_file(str(path / 'last.pt'), name='last.pt')
|
||||
wandb.log_artifact(model_artifact,
|
||||
aliases=['latest', 'epoch ' + str(self.current_epoch), 'best' if best_model else ''])
|
||||
print("Saving model artifact on epoch ", epoch + 1)
|
||||
|
||||
def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
|
||||
with open(data_file) as f:
|
||||
data = yaml.load(f, Loader=yaml.SafeLoader) # data dict
|
||||
nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names'])
|
||||
names = {k: v for k, v in enumerate(names)} # to index dictionary
|
||||
self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(
|
||||
data['train']), names, name='train') if data.get('train') else None
|
||||
self.val_artifact = self.create_dataset_table(LoadImagesAndLabels(
|
||||
data['val']), names, name='val') if data.get('val') else None
|
||||
if data.get('train'):
|
||||
data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train')
|
||||
if data.get('val'):
|
||||
data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val')
|
||||
path = data_file if overwrite_config else '_wandb.'.join(data_file.rsplit('.', 1)) # updated data.yaml path
|
||||
data.pop('download', None)
|
||||
with open(path, 'w') as f:
|
||||
yaml.dump(data, f)
|
||||
|
||||
if self.job_type == 'Training': # builds correct artifact pipeline graph
|
||||
self.wandb_run.use_artifact(self.val_artifact)
|
||||
self.wandb_run.use_artifact(self.train_artifact)
|
||||
self.val_artifact.wait()
|
||||
self.val_table = self.val_artifact.get('val')
|
||||
self.map_val_table_path()
|
||||
else:
|
||||
self.wandb_run.log_artifact(self.train_artifact)
|
||||
self.wandb_run.log_artifact(self.val_artifact)
|
||||
return path
|
||||
|
||||
def map_val_table_path(self):
|
||||
self.val_table_map = {}
|
||||
print("Mapping dataset")
|
||||
for i, data in enumerate(tqdm(self.val_table.data)):
|
||||
self.val_table_map[data[3]] = data[0]
|
||||
|
||||
def create_dataset_table(self, dataset, class_to_id, name='dataset'):
|
||||
# TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging
|
||||
artifact = wandb.Artifact(name=name, type="dataset")
|
||||
img_files = tqdm([dataset.path]) if isinstance(dataset.path, str) and Path(dataset.path).is_dir() else None
|
||||
img_files = tqdm(dataset.img_files) if not img_files else img_files
|
||||
for img_file in img_files:
|
||||
if Path(img_file).is_dir():
|
||||
artifact.add_dir(img_file, name='data/images')
|
||||
labels_path = 'labels'.join(dataset.path.rsplit('images', 1))
|
||||
artifact.add_dir(labels_path, name='data/labels')
|
||||
else:
|
||||
artifact.add_file(img_file, name='data/images/' + Path(img_file).name)
|
||||
label_file = Path(img2label_paths([img_file])[0])
|
||||
artifact.add_file(str(label_file),
|
||||
name='data/labels/' + label_file.name) if label_file.exists() else None
|
||||
table = wandb.Table(columns=["id", "train_image", "Classes", "name"])
|
||||
class_set = wandb.Classes([{'id': id, 'name': name} for id, name in class_to_id.items()])
|
||||
for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)):
|
||||
height, width = shapes[0]
|
||||
labels[:, 2:] = (xywh2xyxy(labels[:, 2:].view(-1, 4))) * torch.Tensor([width, height, width, height])
|
||||
box_data, img_classes = [], {}
|
||||
for cls, *xyxy in labels[:, 1:].tolist():
|
||||
cls = int(cls)
|
||||
box_data.append({"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
|
||||
"class_id": cls,
|
||||
"box_caption": "%s" % (class_to_id[cls]),
|
||||
"scores": {"acc": 1},
|
||||
"domain": "pixel"})
|
||||
img_classes[cls] = class_to_id[cls]
|
||||
boxes = {"ground_truth": {"box_data": box_data, "class_labels": class_to_id}} # inference-space
|
||||
table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), json.dumps(img_classes),
|
||||
Path(paths).name)
|
||||
artifact.add(table, name)
|
||||
return artifact
|
||||
|
||||
def log_training_progress(self, predn, path, names):
|
||||
if self.val_table and self.result_table:
|
||||
class_set = wandb.Classes([{'id': id, 'name': name} for id, name in names.items()])
|
||||
box_data = []
|
||||
total_conf = 0
|
||||
for *xyxy, conf, cls in predn.tolist():
|
||||
if conf >= 0.25:
|
||||
box_data.append(
|
||||
{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
|
||||
"class_id": int(cls),
|
||||
"box_caption": "%s %.3f" % (names[cls], conf),
|
||||
"scores": {"class_score": conf},
|
||||
"domain": "pixel"})
|
||||
total_conf = total_conf + conf
|
||||
boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space
|
||||
id = self.val_table_map[Path(path).name]
|
||||
self.result_table.add_data(self.current_epoch,
|
||||
id,
|
||||
wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set),
|
||||
total_conf / max(1, len(box_data))
|
||||
)
|
||||
|
||||
def log(self, log_dict):
|
||||
if self.wandb_run:
|
||||
for key, value in log_dict.items():
|
||||
self.log_dict[key] = value
|
||||
|
||||
def end_epoch(self, best_result=False):
|
||||
if self.wandb_run:
|
||||
wandb.log(self.log_dict)
|
||||
self.log_dict = {}
|
||||
if self.result_artifact:
|
||||
train_results = wandb.JoinedTable(self.val_table, self.result_table, "id")
|
||||
self.result_artifact.add(train_results, 'result')
|
||||
wandb.log_artifact(self.result_artifact, aliases=['latest', 'epoch ' + str(self.current_epoch),
|
||||
('best' if best_result else '')])
|
||||
self.result_table = wandb.Table(["epoch", "id", "prediction", "avg_confidence"])
|
||||
self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
|
||||
|
||||
def finish_run(self):
|
||||
if self.wandb_run:
|
||||
if self.log_dict:
|
||||
wandb.log(self.log_dict)
|
||||
wandb.run.finish()
|
||||
Reference in New Issue
Block a user