时间戳

首页 > 解决方案 > 使用 PyTorch 进行深度学习：对于 4 维权重 [64, 3, 7, 7] 的预期 4 维输入，但是得到了大小为 [32, 1728] 的 2 维输入

python - 使用 PyTorch 进行深度学习：对于 4 维权重 [64, 3, 7, 7] 的预期 4 维输入，但是得到了大小为 [32, 1728] 的 2 维输入

问题描述

我正在使用 PyTorch 的深度学习来做一些图像分类。每当我尝试训练我的模型时，函数 forward 都会失败。有人可以解释一下输入大小错误的原因以及如何解决这个问题吗？

这是我的模型的代码，以及我的训练损失和优化器：

model.fc = nn.Sequential(
        nn.Conv2d(1, 6, 9, padding=0),  # 64040
        nn.ReLU(),  #
        nn.AvgPool2d(2, stride=2),  # max 62020
        nn.Conv2d(6, 16, 11, padding=0),  # 161010
        nn.ReLU(),  # 161010
        nn.AvgPool2d(2, stride=2),  # 1655 = 400
        nn.Flatten(),
        nn.Linear(400, 200),
        nn.ReLU(),
        nn.Linear(200, 100),
        nn.ReLU(),
        nn.Linear(100, 3), 
        nn.LogSoftmax(dim=1))

criterion = nn.NLLLoss()
optimizer = optim.Adam(model.fc.parameters(), lr=0.003)
model.to(device)

这是验证功能：

def validation(model, val_dataloader, criterion):

val_loss = 0
accuracy = 0

for images, labels in iter(val_dataloader):

    images, labels = images.to('cuda'), labels.to('cuda')

    output = model.forward(images)
    val_loss += criterion(output, labels).item()

    probabilities = torch.exp(output)
    
    equality = (labels.data == probabilities.max(dim=1)[1])
    accuracy += equality.type(torch.FloatTensor).mean()

return val_loss, accuracy

最后，这是我的训练功能：

def train_classifier():
  epochs = 10
  steps = 0
  print_every = 40

  model.to('cuda')

  for e in range(epochs):
  
      model.train()

      running_loss = 0

      for images, labels in iter(train_dataloader):
        images = images.view(images.shape[0], -1)  #this flattens it?
        
        steps += 1

        images, labels = images.to('cuda'), labels.to('cuda')

        optimizer.zero_grad()

        # training 
        output = model.forward(images)
        loss = criterion(output, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
  
        if steps % print_every == 0:
        
            model.eval()
        
            # Turn off gradients for validation, saves memory and computations
            with torch.no_grad():
                validation_loss, accuracy = validation(model, validate_loader, criterion)
    
            print("Epoch: {}/{}.. ".format(e+1, epochs),
                  "Training Loss: {:.3f}.. ".format(running_loss/print_every),
                  "Validation Loss: {:.3f}.. ".format(validation_loss/len(validate_loader)),
                  "Validation Accuracy: {:.3f}".format(accuracy/len(validate_loader)))
    
            running_loss = 0
            model.train()
                    
train_classifier()

错误代码：

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-32-60a435d940e1> in <module>()
     49             model.train()
     50 
---> 51 train_classifier()

5 frames
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight, bias)
    438                             _pair(0), self.dilation, self.groups)
    439         return F.conv2d(input, weight, bias, self.stride,
--> 440                         self.padding, self.dilation, self.groups)
    441 
    442     def forward(self, input: Tensor) -> Tensor:

RuntimeError: Expected 4-dimensional input for 4-dimensional weight [64, 3, 7, 7], but got 2-dimensional input of size [32, 1728] instead

任何帮助表示赞赏！谢谢！

标签： pythonmachine-learningdeep-learningpytorch

解决方案

你的网络既有Conv2d层又有全连接Linear层——这是问题的根源：Conv2d期望它的输入是 4D：batch-channel-height-width。另一方面，nn.Linear“扁平化”特征的作品：batch-channel。因此，您需要“扁平化”您的数据，但不是在应用网络之前，而是在其处理期间，您有一个Flattening层。

推荐阅读