170 lines
5.5 KiB
Python
170 lines
5.5 KiB
Python
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)
|