Struggling to load a pre-trained PyTorch model into Julia

Hi all,
I am coming back to this unsolved problem.
The background is that I have trained a reinforcement learning agent and I want to load the pre-trained model (pytorch) into Julia for inference (it is much faster to evaluate the performance which costs lots of time in python).

Can anyone have a similar experience please share a small demo of how to achieve this?
Thank you in advance!

Metalhead.jl has some scripts to load weights from torchision models, you can try adapting one of those

https://github.com/FluxML/Metalhead.jl/tree/master/scripts

Thanks for pointing out this. I will try to see if it works.