RuntimeError: Given weight of size [9, 3, 3, 3], expected bias to be 1-dimensional with 9 elements, but got bias of size [128] instead about network-slimming

[Coderx7]

Thanks to God, I found the issue. in each step the model is altered and a new instance of the model is reinstantiated and the pruning goes on. I had to also add the capability of instantiating the model based on an input cfg. (like the way vgg is constructed) when I did that everything started to work flawlessly.
Thanks again