search

zhilin007 / FFA-Net

FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
601 stars 141 forks source link

attention map #3

Closed wushunshun closed 4 years ago

wushunshun commented 4 years ago

Hello, how to print the channel-wise and pixel-wise feature weights map of the Group Structure output? Can it be printed in training the dataset or after training the dataset? Thank you very much!

zhilin007 commented 4 years ago

You need to use 'register_forward_hook' function to get middle result of the model.