How to register_hook on Conv2d?

[spanev (Serge Panev)]

Hi @Umair_Javaid,

Simply create a hook function and register it to the by calling register_forward_hook.

Display intermediate features

There are two things to do: get the intermediate features, display them. First, uou will need to use register_forward_hook on the concerned convolution. To create it you have to write: def hook(module, input, output): # output is the [N, 64, 30, 30] Tensor containing your features model.concerned_conv.register_forward_hook(hook) Then depending on your display method, you will have. You can use torchvision and Tensorboard to do so. The hook body would be something like: def hook(module,…