Cyberpunk2077

Gradient of self.mnemonics is None after backward in mnemonics_train.py

1

Hi, I run the experiment with the following command `"python main.py --nb_cl_fg=50 --nb_cl=2 --nb_protos 20 --resume --imprint_weights"`. I find that the gradient of `self.mnemonics` in mnemonics_train.py is _None_ after `q_loss.backward()`,...

Can you provide the number of parameters used for ImageNet and ImageNet subset?

1

Hi, I've noticed that you offer the number of parameters used for CIFAR100 on the newest version of the paper. Can you also provide the it on the ImageNet and...