RuntimeError: Given input size: (128x16x16)

[zyyhl]

File "/home/btbu/tz/SKNet-master/sknet.py", line 45, in forward fea_s = self.gap(fea_U).squeeze_() File "/home/btbu/anaconda3/envs/tz/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(*input, **kwargs) File "/home/btbu/anaconda3/envs/tz/lib/python3.5/site-packages/torch/nn/modules/pooling.py", line 547, in forward self.padding, self.ceil_mode, self.count_include_pad) RuntimeError: Given input size: (128x16x16). Calculated output size: (128x0x0). Output size is too small at /pytorch/aten/src/THCUNN/generic/SpatialAveragePooling.cu:63

Hello, I encountered the following problems when running the SKnet network, can you help me solve it?thanks

[pppLang]

Oh, I am very sorry to see your message so late. But I can't reproduce this problem. I think maybe you made some mistakes in the settings, or the problems caused by the different versions of pytorch.

If you need further help, please provide the code snippet you are running.

sorry again.