RuntimeError: mat1 and mat2 shapes cannot be multiplied (1280x5 and 6400x4096)?

Question

使用以下代码定义Alexnet，我可以训练successfully.But当我想看到每一层的输出时，会报错'RuntimeError: mat1 and mat2 shapes cannot be multiplied (1280x5 and 6400x4096 )?'

class AlexNet(nn.Module):
    def __init__(self):
      super(AlexNet, self).__init__()
      self.conv = nn.Sequential(
          nn.Conv2d(1, 96, 11, 4),
          nn.ReLU(),
          nn.MaxPool2d(3, 2),
          nn.Conv2d(96, 256, 5, 1, 2),
          nn.ReLU(),
          nn.MaxPool2d(3, 2),
          nn.Conv2d(256, 384, 3, 1, 1),
          nn.ReLU(),
          nn.Conv2d(384, 384, 3, 1, 1),
          nn.ReLU(),
          nn.Conv2d(384, 256, 3, 1, 1),
          nn.ReLU(),
          nn.MaxPool2d(3, 2)
         )
      self.fc = nn.Sequential(
          nn.Linear(256*5*5, 4096),
          nn.ReLU(),
          nn.Dropout(0.5),
          nn.Linear(4096, 4096),
          nn.ReLU(),
          nn.Dropout(0.5),
          nn.Linear(4096, 10)
        )
      
    def forward(self, img):
      feature = self.conv(img)
      output = self.fc(feature.view(img.shape[0], -1))
      return output

X=torch.randn(1,1,224,224)
for name,layer in net.named_children():
  X=layer(X)
  print(name,X.shape)

你能帮帮我吗？

Answer 1

您忘记在 for 循环中展平 self.conv 的输出数组。你可以把它分成两个循环，一个用于卷积层，一个用于全连接层。


X = torch.randn(1, 1, 224, 224)
for name, layer in net.conv.named_children():
  X = layer(X)
  print(name, X.shape)

X = X.flatten()  # or X = X.view(X.shape[0], -1)

for name, layer in net.fc.named_children():
  X = layer(X)
  print(name, X.shape)

RuntimeError: mat1 and mat2 shapes cannot be multiplied (1280x5 and 6400x4096)?

RuntimeError: mat1 and mat2 shapes cannot be multiplied (1280x5 and 6400x4096)?

matrix

deep-learning

pytorch

conv-neural-network