Hi, this is my first post here. I am trying to implement a paper which modifies the resent18. I started fastai course a few days back and I wanted to see how the modified model works for the pets data Jeremy showed in lecture 1. The modified model can use the pre-trained weights. Anyway I can do this or I will have to do it with pytorch?
I don’t know, if it makes sense, to set the “known layers” to the learned weights, but it is also possible to assign a layer of your new model the weights of a learned old layer with the same shape.