search

blackfeather-wang / ISDA-for-Deep-Networks

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.
582 stars 93 forks source link

Understanding number of features? #1

Closed eric-tc closed 4 years ago

eric-tc commented 4 years ago

Hi thanks for sharing the code. I had a look and i cannot understand why in ./networks/resnet.py at line 169 the value of self.feature_num=64 is the same for all model and instead for wideresnet and other networks the value is different.

Thanks

blackfeather-wang commented 4 years ago

Hi, thanks for visiting this repository.

Self.feature_num corresponds to the number of dimensions of deep features obtained from the network, which is usually determined by the width of the model, and differs among different network structures. Basic ResNets for CIFAR share the same width while differ in depth. That's why self.feature_num remains the same.

Sincerely, Yulin Wang.

eric-tc commented 4 years ago

ok now it is clear.

Thanks