How to find if the layer is convolutional and linear from the entire network, and then read its parameters?

1

I want to find if the layer is convolutional and linear from the entire network. If it is one of them, then I want to read the shape and parameters of the layer. I have found a solution to check if the module is convolutional or linear here. But I don’t find a way to read the parameters and shape of the corresponding layer. Would you please suggest a solution?

2

The posted condition would be the right approach and once the condition is met you could use e.g. layer.weight and layer.bias or layer.parameters() depending on your use case.

3

@Ajinkya.Bankar
Do you want to know the number of parameters & shape, or just copy/read the weights of each layer?

4

layer.weight.data worked for me. Thank you.