search

MingiJi / FRSKD

Official implementation for (Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation, CVPR-2021)
Apache License 2.0
96 stars 25 forks source link

The question about num_features #8

Open wnma3mz opened 3 years ago

wnma3mz commented 3 years ago

When Training with FRSKD,

In train, the first feat has been deleted in feat_lst.

https://github.com/MingiJi/FRSKD/blob/bed26010383cbf4b8ae3a5d38c414d052c68a6ed/classification/utils.py#L60-L61

But, in model bifpn forward, it still deletes the first feat.

https://github.com/MingiJi/FRSKD/blob/bed26010383cbf4b8ae3a5d38c414d052c68a6ed/classification/models/bifpn.py#L27-L28

My guess, based on network_channels, is that only one delete operation is required.

https://github.com/MingiJi/FRSKD/blob/bed26010383cbf4b8ae3a5d38c414d052c68a6ed/classification/main.py#L75-L76

So, the following line should also be deleted

https://github.com/MingiJi/FRSKD/blob/bed26010383cbf4b8ae3a5d38c414d052c68a6ed/classification/models/bifpn.py#L28