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

user_11131258 0
Viewed 8752

I am trying to experiment with why we have a Vanishing & exploding gradient, and why Resnet is so helpful in avoiding the two problems above. So I decided to train a plain Convolution network with many layers just to know why the model LOSS increases as I train with many layers e.g 20 layers. but I am getting this error at some point, I can figure out what might be the issue, but I know it is from my model Architecture.

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

My model Architecture is

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
pytorch neural-network python
1 Answers

I can see by the model, it looks like you made a typo on the 4th conv block in your sequential. You have

nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),

However, you already convert the image to 64 channels and you then pass it in to the next conv block as an image with 32 channels which results in the error you have above.

Fix this to:

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

Sarthak Jain

user_143470220
Related