Kai Hu

[Refactor] demo

1

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily got feedback. If you do not understand...

Hi, I wanted to reproduce the results in your fixup paper. (Figure 3: Depth of residual networks versus test accuracy at the first epoch for various methods on CIFAR-10 with...

[Fix] fix a bug in UT

1

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily got feedback. If you do not understand...

Can be reviewed, but do not merge util `mmdet` supporting `FastRCNN` model in the 3.x branch.

The training results will be added in a next PR.

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily got feedback. If you do not understand...

Validation by iteration causes model.training=False to continue until the end of an epoch

3

See https://github.com/open-mmlab/mmaction2/issues/1781 Thanks @makecent for this issue.

Request for missing videos.

1

Hi, I submitted a missing video request on February 13, 2023. But after a week I don't get the link to the missing videos. Can you check if my request...

[Feature] Support ActivityNetMeanAR

5

WIP

Thanks for the interesting code! I am not able to find the training scripts or the hyper-parameter details for AmpleGCG. Can you kindly clarify? From the paper, I guess the...