How to split Autoencoder to two NNs?

1

I have an autoencoder with 2 submodules (trained and ready). How to split it to two separate NNs each with its own weights and forward method?

2

How did you define your current model?
If both submodules are instances of nn.Sequential, you could recreate them separately outside of your current model and just load the state_dicts into them.

If your modules and forward is more complicated, you could still redefine the submodules, but would most likely have to filter out unwanted keys from the state_dict of the complete model before loading it into the submodels.

1 Like
3

Thank you ptrblck . I figured if my ultimate goal is to split the AE, then the best thing is build two different NNs for encoder and decoder, and then combine them in a third one for training purpose.

1 Like
4

That sounds like the best idea! :slight_smile: