I am trying to train a U-Net which looks like this
`class UNet(nn.Module):
def __init__(self, imsize):
super(UNet, self).__init__()
self.imsize = imsize
self.activation = F.relu
self.pool1 = nn.MaxPool2d(2)
self.pool2 = nn.MaxPool2d(2)
self.pool3 = nn.MaxPool2d(2)
self.pool4 = nn.MaxPool2d(2)
self.conv_block1_64 = UNetConvBlock(4, 64)
self.conv_block64_128 = UNetConvBlock(64, 128)
self.conv_block128_256 = UNetConvBlock(128, 256)
self.conv_block256_512 = UNetConvBlock(256, 512)
self.conv_block512_1024 = UNetConvBlock(512, 1024)
self.up_block1024_512 = UNetUpBlock(1024, 512)
self.up_block512_256 = UNetUpBlock(512, 256)
self.up_block256_128 = UNetUpBlock(256, 128)
self.up_block128_64 = UNetUpBlock(128, 64)
self.last = nn.Conv2d(64, 1, 1)`
The loss function i am using is
`class BCELoss2d(nn.Module):
def __init__(self, weight=None, size_average=True):
super(BCELoss2d, self).__init__()
self.bce_loss = nn.BCELoss(weight, size_average)
def forward(self, logits, targets):
probs = F.sigmoid(logits)
probs_flat = probs.view(-1)
targets_flat = targets.view(-1)
return self.bce_loss(probs_flat, targets_flat)`
The input image tensor is [1,1,68,68] and labels are also of the same shape
I get this error:
<ipython-input-72-270210759010> in forward(self, x)
75
76 block4 = self.conv_block256_512(pool3)
---> 77 pool4 = self.pool4(block4)
78
79 block5 = self.conv_block512_1024(pool4)
/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py in _ _call__(self, *input, **kwargs)
323 for hook in self._forward_pre_hooks.values():
324 hook(self, input)
325 result = self.forward(*input, **kwargs)
326 for hook in self._forward_hooks.values():
327 hook_result = hook(self, input, result)
/usr/local/lib/python3.5/dist-packages/torch/nn/modules/pooling.py in forward(self, input)
141 return F.max_pool2d(input, self.kernel_size, self.stride,
142 self.padding, self.dilation, self.ceil_mode,
--> 143 self.return_indices)
144
145 def __repr__(self):
/usr/local/lib/python3.5/dist-packages/torch/nn/functional.py in max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode, return_indices)
332 See :class:`~torch.nn.MaxPool2d` for details.
333 """
--> 334 ret = torch._C._nn.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
335 return ret if return_indices else ret[0]
336
RuntimeError: Given input size: (128x1x1). Calculated output size: (128x0x0). Output size is too small at /pytorch/torch/lib/THCUNN/generic/SpatialDilatedMaxPooling.cu:69
I'm guessing I'm making a mistake in my channel size or pooling size but i'm not sure where exactly is the mistake.
Your problem is that before the Pool4 your image has already reduced to a 1x1
pixel size image. So you need to either feed an much larger image of size at least around double that (~134x134) or remove a pooling layer in your network.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With