從最后一個隱藏層提取特征 Pytorch Re.net18

Question

我正在使用Oxford Pet 數據集和預訓練的 Re.net18 CNN 實現圖像分類器。 該數據集包含 37 個類別，每個類別約有 200 張圖像。

我不想使用 CNN 的最終 fc 層作為 output 來進行預測，而是想使用 CNN 作為特征提取器來對寵物進行分類。

對於每張圖像，我想從最后一個隱藏層（應該在1000 維 output 層之前）獲取特征。 我的 model 使用 Relu 激活，所以我應該在 ReLU 之后獲取 output（因此所有值都將是非負數）

這是代碼（遵循 Pytorch 上的遷移學習教程）：

加載數據中

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                std=[0.229, 0.224, 0.225])


image_datasets = {"train": datasets.ImageFolder('images_new/train', transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        normalize
    ])), "test": datasets.ImageFolder('images_new/test', transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        normalize
    ]))
               }

dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                             shuffle=True, num_workers=4, pin_memory=True)
              for x in ['train', 'test']}

dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'test']}

train_class_names = image_datasets['train'].classes

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

火車 function

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', 'test']:
            if phase == 'train':
                scheduler.step()
                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)

            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))

            # deep copy the model
            if phase == 'test' 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

計算 SGD 交叉熵損失

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features

print("number of features: ", num_ftrs)

model_ft.fc = nn.Linear(num_ftrs, len(train_class_names))

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=24)

現在如何從我的每張圖像的最后一個隱藏層獲取特征向量？ 我知道我必須凍結前一層，這樣就不會在它們上計算梯度，但我在提取特征向量時遇到了問題。

我的最終目標是使用這些特征向量來訓練線性分類器，例如 Ridge 或類似的東西。

謝謝！

Answer 1

你可以試試下面的方法。 這適用於僅更改偏移量的任何圖層。

model_ft = models.resnet18(pretrained=True)
### strip the last layer
feature_extractor = torch.nn.Sequential(*list(model_ft.children())[:-1])
### check this works
x = torch.randn([1,3,224,224])
output = feature_extractor(x) # output now has the features corresponding to input x
print(output.shape)

火炬大小（[1, 512, 1, 1]）

Answer 2

這可能不是最好的主意，但您可以執行以下操作：

#assuming model_ft is trained now
model_ft.fc_backup = model_ft.fc
model_ft.fc = nn.Sequential() #empty sequential layer does nothing (pass-through)
# now you use your network as a feature extractor

我還檢查了fc是更改的正確屬性， 向前看

Answer 3

如果您知道層的名稱（例如 re.net 中的 layer4），則可以使用鈎子：

def get_hidden_features(x, layer):
    activation = {}

    def get_activation(name):
        def hook(m, i, o):
            activation[name] = o.detach()

        return hook

    model.register_forward_hook(get_activation(layer))
    _ = model(x)
    return activation[layer]


get_features(inputs, "layer4")

示例： https://discuss.pytorch.org/t/how-can-i-extract-intermediate-layer-output-from-loaded-cnn-model/77301/3