CeShine Lee
Results
2
comments of
CeShine Lee
Hi there, Yes, perceptual loss involves more computation as it takes intermediate activations from different layers, calculates the gram matrices, and back-propagation on the MSE of the differences between two...
That fork is really old (2+ years). You most likely need to downgrade PyTorch to make it work. Perhaps try the main repo and see if it works?