Hakjin Lee
Hakjin Lee
**Describe the feature** Support returning the main function of 'train', and 'test' scripts like `mim.train(return_function=True)(args)`. **Motivation** Currently, `mim.train` and `mim.test` works as running the script as a subprocess. In addition...
First of all, thank you for providing these precious works. Although I could find the pre-trained models in `MODELHUB.md`, but couldn't find the configuration files for `Swin-Huge` and `Swin-Giant`. Can...
Currently, `Transformer` registry or class does not exist in `mmdet==3.x`. I think it should be modified as `BaseModule` instead of `Transformer`.
## Add GradScaler for ZeroOptim Numerical Precision is not tested yet. ## Description Test Script ```python import os import torch, time, gc import torch.multiprocessing as mp import torch.distributed as dist...
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...