it seems a bug in build_cliquenet(pytorch)

[zhaoying9105]

my input size is 1, 3, 128,128

after output = self.pool(output), I got an error:

Traceback (most recent call last):
  File "D:/projects/machine_learning/gta5/train/clique_train.py", line 176, in <module>
    Net()
  File "D:/projects/machine_learning/gta5/train/clique_train.py", line 38, in Net
    out = model.forward(x)
  File "D:\projects\machine_learning\gta5\model\pytorch\cliquenet.py", line 70, in forward
    feature_I_list.append(self.list_gb[i](block_feature_I))
  File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "D:\projects\machine_learning\gta5\model\pytorch\utils.py", line 65, in forward
    output = self.pool(output)
  File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "D:\Anaconda3\lib\site-packages\torch\nn\modules\pooling.py", line 547, in forward
    self.padding, self.ceil_mode, self.count_include_pad)
RuntimeError: Given input size: (152x32x32). Calculated output size: (152x0x0). Output size is too small at c:\programdata\miniconda3\conda-bld\pytorch_1524549877902\work\aten\src\thcunn\generic/SpatialAveragePooling.cu:63

[Joyies]

I also meet the problem.my input size is 64x3x32x32.

[Joyies]

have you solved the problem?

[zhaoying9105]

not really, just give up and change to densenet

[Yibo Yang]

Sorry for late reply. Did you resize and crop the images in train/val data loader? If you are using your own dataset, you should pre-process them into the input size required by any classification model you use. As an alternative, you can also modify the model to make it work on your dataset.