how to load robust loss parameters

jonbarron / robust_loss_pytorch

A pytorch port of google-research/google-research/robust_loss/

Apache License 2.0

656 stars 88 forks source link

how to load robust loss parameters #26

Open 1171000410 opened 3 years ago

1171000410 commented 3 years ago

Hello, thank you very much for your elegant code. I want to use robust loss to train the model in the first stage and load the pre-trained model in the second stage. I am confused about how to save and load the parameters of AdaptiveLossFunction.

jonbarron commented 3 years ago

It should be the same as loading/saving the parameters of any pytorch module. I can't really help you more than that, as I don't use pytorch --- all of the pytorch code I've ever written is in this repository.