logo标签列表

运行时错误：给定的groups=1，大小为[64, 32, 3, 3]的权重，期望输入[128, 64, 32, 32]具有32个通道，但实际上却有64个通道。

pythonneural-networkpytorch
4

我正在尝试研究为什么我们会出现梯度消失和梯度爆炸的问题，以及为什么Resnet在避免上述两个问题方面如此有帮助。因此，我决定训练一个只有卷积层的深度网络，以了解为什么当我使用多达20层时模型的LOSS会增加。但是，在某些时候，我遇到了这个错误，虽然我不知道可能出现了什么问题，但我知道这是由于我的模型架构造成的。

images.shape: torch.Size([128, 3, 32, 32])
---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-80-0ad7109b33c1> in <module>
      1 for images, labels in train_dl:
      2     print('images.shape:', images.shape)
----> 3     out = model(images)
      4     print('out.shape:', out.shape)
      5     print('out[0]:', out[0])

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

<ipython-input-78-81b21c16ed79> in forward(self, xb)
     31 
     32     def forward(self, xb):
---> 33         return self.network(xb)

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
    115     def forward(self, input):
    116         for module in self:
--> 117             input = module(input)
    118         return input
    119 

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input)
    421 
    422     def forward(self, input: Tensor) -> Tensor:
--> 423         return self._conv_forward(input, self.weight)
    424 
    425 class Conv3d(_ConvNd):

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
    418                             _pair(0), self.dilation, self.groups)
    419         return F.conv2d(input, weight, self.bias, self.stride,
--> 420                         self.padding, self.dilation, self.groups)
    421 
    422     def forward(self, input: Tensor) -> Tensor:

RuntimeError: Given groups=1, weight of size [64, 32, 3, 3], expected input[128, 64, 32, 32] to have 32 channels, but got 64 channels instead

我的模型架构是

class Cifar10CnnModel(ImageClassificationBase):
    def __init__(self):
        super().__init__()
        self.network = nn.Sequential(
            nn.Conv2d(3, 32, kernel_size=3, padding=1),
            nn.Conv2d(32, 32, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2, 2), # output: 64 x 16 x 16

            nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2, 2), # output: 128 x 8 x 8

            nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2, 2), # output: 256 x 4 x 4

            nn.Flatten(), 
            nn.Linear(256*4*4, 1024),
            nn.ReLU(),
            nn.Linear(1024, 512),
            nn.ReLU(),
            nn.Linear(512, 10))
        
    def forward(self, xb):
        return self.network(xb)

for images, labels in train_dl:
    print('images.shape:', images.shape)
    out = model(images)
    print('out.shape:', out.shape)
    print('out[0]:', out[0])
    break
1个回答
4
我看到模型，似乎你在sequential的第四个卷积块上打错了字。 你写成了：
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),

然而，您已经将图像转换为64个通道，然后将其作为具有32个通道的图像传递到下一个卷积块中，这导致了上述错误。
请将其更正为：
self.network = nn.Sequential(
            nn.Conv2d(3, 32, kernel_size=3, padding=1),
            nn.Conv2d(32, 32, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),

            # Change this from 32 to now 64 like I did here.
            nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2, 2), # output: 64 x 16 x 16

萨塔克·贾恩

1
是的，你说得对，那是个打字错误。我把输入通道从32改成了64，现在它正常工作了。谢谢。 - chuky pedro
网页内容由stack overflow 提供, 点击上面的
可以查看英文原文，
原文链接