search

Want2Vanish / FBMSNet

This is the PyTorch implementation of the FBMSNet architecture for EEG-MI classification.
30 stars 7 forks source link

About the exceeds dimension runtime error #2

Open ttanad opened 1 year ago

ttanad commented 1 year ago

Hi sir, I've made it to run the ho.py successfully, but there's a runtime error for dimension size when I try t o run the cv.py. It will be extremely appreciated if you'd like to help me with this problem.

f47dd2b7bb30d1c7b602aad67fe2208

File "C:\Data\EEG\FBMSNet\codes\centralRepo\baseModel.py", line 364, in _trainOE centerloss=centerloss,optimzer4center=optimzer4center,Lambda=0.0005)) File "C:\Data\EEG\FBMSNet\codes\centralRepo\baseModel.py", line 502, in trainOneEpoch output,f = self.net(d['data'].unsqueeze(1).to(self.device)) File "C:\Users\ttana\anaconda3\envs\FBMSNet\lib\site-packages\torch\nn\modules\module.py", line 541, in call result = self.forward(*input, kwargs) File "C:\Data\EEG\FBMSNet\codes\centralRepo\networks.py", line 274, in forward y = self.mixConv2d(x) File "C:\Users\ttana\anaconda3\envs\FBMSNet\lib\site-packages\torch\nn\modules\module.py", line 541, in call result = self.forward(*input, *kwargs) File "C:\Users\ttana\anaconda3\envs\FBMSNet\lib\site-packages\torch\nn\modules\container.py", line 92, in forward input = module(input) File "C:\Users\ttana\anaconda3\envs\FBMSNet\lib\site-packages\torch\nn\modules\module.py", line 541, in call result = self.forward(input, kwargs) File "C:\Data\EEG\FBMSNet\codes\centralRepo\networks.py", line 229, in forward x_split = torch.split(x, self.splits, 1) File "C:\Users\ttana\anaconda3\envs\FBMSNet\lib\site-packages\torch\functional.py", line 77, in split return tensor.split(split_size_or_sections, dim) File "C:\Users\ttana\anaconda3\envs\FBMSNet\lib\site-packages\torch\tensor.py", line 345, in split return super(Tensor, self).split_with_sizes(split_size, dim) RuntimeError: start (0) + length (3) exceeds dimension size (1).