Load model for Transfer Learning

[WittmannF]

Hello! First of all, thank you very much for sharing your code! Congrats on your project! :)

I'm new in PyTorch and I was wondering if it is possible to load the pre-trained models (for example resnext-101) using model = torch.load(PATH), for example? I wanted to use their conv layers for this kaggle contest https://www.kaggle.com/c/youtube8m-2019. If you have any hint on where to start I would really appreciate :)

Thank you and congratulations again!

[priyanka-chaudhary]

@WittmannF : I am trying to do the same? Did you figure it out? Thanks!