Pytorch 기본기 - 4

• 참고 : pytorch

 

전이학습(Transfer Learning) 튜토리얼

• 충분한 크기의 데이터셋을 갖추는 경우가 상대적으로 어려움
  • 이를 해결하기 위해 전이학습 사용
• 2가지 전이학습 방법
  1. 합성곱 신경망의 미세조정 방법
     • 무작위 초기화 대신에 미리 학습된 신경망을 가져와 초기화 후 학습
  2. 고정 특정 추출기로써의 합성곱 신경망
     • 마지막의 완전히 연결된 계층을 제외한 모든 신경망의 가중치 고정
     • 마지막 FC는 새로운 무작위의 가중치를 갖는 계층으로 대체

 

학습할 데이터 불러오기

• 75개의 검증용 이미지
• class는 ants, bees

# 학습을 위한 데이터 증가(Augmentation)와 일반화하기
# 단지 검증을 위한 일반화하기
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])
    ]), # 해당 수치는 Imagenet에서 가장 좋았다는 정규화 수치
    '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

use_gpu = torch.cuda.is_available()

 

데이터 시각화

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


# Get a batch of training data
inputs, classes = next(iter(dataloaders['train']))

# Make a grid from batch
out = torchvision.utils.make_grid(inputs)

imshow(out, title=[class_names[x] for x in classes])

 

모델 학습 함수

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('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                scheduler.step()
                model.train(True)  # Set model to training mode
            else:
                model.train(False)  # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for data in dataloaders[phase]:
                # get the inputs
                inputs, labels = data

                # wrap them in Variable
                if use_gpu:
                    inputs = Variable(inputs.cuda())
                    labels = Variable(labels.cuda())
                else:
                    inputs, labels = Variable(inputs), Variable(labels)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                outputs = model(inputs)
                _, preds = torch.max(outputs.data, 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)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # 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('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model

• 학습 예측값 시각화 함수

def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()

    for i, data in enumerate(dataloaders['val']):
        inputs, labels = data
        if use_gpu:
            inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())
        else:
            inputs, labels = Variable(inputs), Variable(labels)

        outputs = model(inputs)
        _, preds = torch.max(outputs.data, 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('predicted: {}'.format(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)

 

합성곱 신경망 미세조정(Finetuning)

• 미리 학습한 모델을 불러와서 마지막 FC만 재설정

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_ft = model_ft.cuda()

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)
>>> Best val Acc: 0.947712

 

고정 특정 추출기로써의 합성곱 신경망

• 마지막 FC 계층을 제외한 나머지 모든 레이어 고정
• 경사도 계산 수행하지 않도록 설정
• 시간절약(대부분의 레이어에서 경사도 계산X, 순전파는 계산)

model_conv = torchvision.models.resnet18(pretrained=True)
for param in model_conv.parameters():
    param.requires_grad = False

# Parameters of newly constructed modules have requires_grad=True by default
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_conv = model_conv.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that only parameters of final layer are being optimized as
# opoosed to before.
optimizer_conv = optim.SGD(model_conv.fc.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_conv, step_size=7, gamma=0.1)




model_conv = train_model(model_conv, criterion, optimizer_conv,
                         exp_lr_scheduler, num_epochs=25)
>>> Best val Acc: 0.967320