#Training code
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 = ‘data_views’
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=100,
shuffle=True, num_workers=24)
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(“cuda:0” if torch.cuda.is_available() else “cpu”)
model_ft = models.resnet50(pretrained=False)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 3)
model_ft = model_ft.to(device)
criterion = nn.CrossEntropyLoss()
optimizer_ft = optim.Adam(model_ft.parameters(), lr=0.001)
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
def train_model(model, criterion, optimizer, scheduler, num_epochs):
since = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
for phase in ['train', 'val']:
if phase == 'train':
scheduler.step()
model.train()
else:
model.eval()
running_loss = 0.0
running_corrects = 0
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
optimizer.zero_grad()
with torch.set_grad_enabled(phase == 'train'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
if phase == 'train':
loss.backward()
optimizer.step()
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
epoch_loss = running_loss / dataset_sizes[phase]
epoch_acc = running_corrects.double() / dataset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
torch.save(model.state_dict(), 'resnet504c.pt')
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
model.load_state_dict(best_model_wts)
return model
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=25)
#Testing Code
data_transforms = {
‘test’: 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 = ‘data_views_test’
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
data_transforms[x])
for x in [‘test’]}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=100,
shuffle=True, num_workers=24)
for x in [‘test’]}
print(dataloaders)
dataset_sizes = {x: len(image_datasets[x]) for x in [‘test’]}
class_names = image_datasets[‘test’].classes
device = torch.device(“cuda:0” if torch.cuda.is_available() else “cpu”)
best_acc = 0.0
for phase in [‘test’]:
print(“model”)
model = models.resnet50(pretrained=False)
model.load_state_dict(torch.load('resnet50_4c.pt'))
model.eval()
running_loss = 0.0
running_corrects = 0
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
with torch.set_grad_enabled(phase == ‘test’):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
loss = running_loss / dataset_sizes[phase]
acc = running_corrects.double() / dataset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, loss, acc))
time_elapsed = time.time() - since
print(‘Testing complete in {:.0f}m {:.0f}s’.format(
time_elapsed // 60, time_elapsed % 60))
print(‘Best val Acc: {:4f}’.format(acc))