Xiyu Wang

Official support for finetune-based methods, e.g., vit adapter, and multi-GPU training with DataParallel.

1

The implementation of the gradient update in faa_model.py seems to be very constrainted at best. It does not factor in the case where I want to obtain the policy for...

While the work is impressive, this repo hasn't been updated for years and the most important part, i.e., how to generate the dataset, is not published. Can the authors consider...