You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The step x = F.elu(self.fc1(inputs)) has error. When using the forward in MLP class, the error says "mat1 and mat2 shapes cannot be multiplied (640*16 and 196*512)".
The text was updated successfully, but these errors were encountered:
Hi Sherry,
Did you use the older version of PyTorch we developed the code in? maybe this caused the issue
Will I've tried to switch the version to 0.2. However, it still has an error. args.timesteps * args.dims = 49*4=196 is in_dim by default, but the input dimension is 128*5*4
*4 also 640*16, which is not dimension with 196.
Should I change the arguments from default? Or better way to change the code?
The step x = F.elu(self.fc1(inputs)) has error. When using the forward in MLP class, the error says "mat1 and mat2 shapes cannot be multiplied (640*16 and 196*512)".
The text was updated successfully, but these errors were encountered: