Pytorch: a shared conv layer

[jmandivarapu1 (Jaya Krishna Mandivarapu)]

you can look at this thread or you can copy the weights of convolutional layer from one to another whenever you make a change to any one of them like model.conv1.weight=model2.conv1.weight

How can I run 2 parallel CNN on same data then combine outputs at FC layer?

I want to have a CNN architecture with the below pipeline: [DeepInsightArchitecture] I’ve done normal CNN using PyTorch before. Can someone please suggest if there’s a feature in PyTorch that let’s me easily split as above? Thanks so much in advance. @ptrblck Please help