LeoXing1996

[Feature] Support saving and loading npz file in offline evaluation mode.

2

Time cost comparison |Model| Offline | Offline w save_npz| online| |:-:|:-:|:-:|:-:| |SAGAN-128| 14:56.74 | 6:57.43 | 5:19.90| This feature can greatly speed up sampling result saving and metric evaluation.

[Fix] Disbale gpu fuser on pt19

1

Refers to [clean-fid](https://github.com/GaParmar/clean-fid/blob/5e1e84cdea9654b9ac7189306dfa4057ea2213d8/cleanfid/inception_torchscript.py#L9).

Question about total variation regularization and training strategy of appearance generative network

1

Thanks for this great work, however, I still have some questions about training strategy and loss term. The training code of appearance generative network in `train.sh` is as below: https://github.com/JDAI-CV/Down-to-the-Last-Detail-Virtual-Try-on-with-Detail-Carving/blob/85cc6636450af2653e46e157644641aa9ad36665/train.sh#L8...

[Bug] Mac M1 raise architecture incompatible error after install

2

When I preview `Dockerfile` after typing `c`, the following error is raised. Then I manually call `:TSUninstall dockerfile` and `:TSInstall dockerfile`, the error disappeared.

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...

[Enhancement] Adopt `BaseModule` for some models

1

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...

[Feature] Add Typehint for MMEditing-1.x

2

### What's the feature? MMEditing-1. x will be released soon, and we are adding type hints to MMRotate-1.x now, PRs from the community are welcome. You can refer to [mmdet](https://github.com/open-mmlab/mmdetection/tree/dev-3.x/docs)....

### What's the feature? [MMEval](https://github.com/open-mmlab/mmeval) has been released, and we are adding metrics in MMEditing-1.x to MMEval now, PRs from the community are welcome. You can refer to [SSIM](https://github.com/open-mmlab/mmeval/blob/main/mmeval/metrics/ssim.py), [PSNR](https://github.com/open-mmlab/mmeval/blob/main/mmeval/metrics/psnr.py),...

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...