New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Switch to PyTorch API (computational graph is broken!) #1

Open

Nikronic opened this issue Nov 7, 2021 · 0 comments

Assignees

Labels

bug

Owner

Nikronic commented Nov 7, 2021

Deep-Halftoning/utils/losses.py

Lines 136 to 138 in f968d28

    
           patch_loss = np.sum( 
        
               [self.MSE_loss(self.gram_matrix(self.get_patch(ly)), self.gram_matrix(self.get_patch(lp))) 
        
                for ly, lp in zip(y_vgg, details_outputs_vgg)])

Why on earth there is a numpy function during the forward pass of computing loss? Switch to pytorch and get rid of for-loop.

Nikronic added the bug label

Nikronic self-assigned this

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment