Ming Li

Will the code for objects365 pretrain open source?

4

Hi, @SuperHenry2333 @SlongLiu @FengLi-ust Thanks for your contribution, could you please open source the code that support objects365?

Dist training failed due to FileNotFoundError

1

Hi, @BIGWangYuDong @ZwwWayne , Thanks for your help and I appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. I have...

Introducing mmselfsup.core in mmdet leads to unexpected results.

8

Hi @ZwwWayne @BIGWangYuDong @RangiLyu @jbwang1997 @hhaAndroid @chhluo , happy mid-Autumn Festival (🐶)~ This issue also open in [mmselfsup](https://github.com/open-mmlab/mmselfsup/issues/479) Thanks for reporting the unexpected results and we appreciate it a lot....

Introducing mmselfsup.core in mmdet leads to unexpected results.

4

Hi @fangyixiao18 @Jiahao000 @YuanLiuuuuuu @scnuhealthy, happy mid-Autumn Festival~ Thanks for reporting the unexpected results and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get...

Could you please provide the Baidu Disk link?

1

Due to some reasons, I cannot download the extracted features from google driven, especially for thumos, so could you please provide the baidu disk link for extracted features? Thanks very...

Hi @kaidic, thank you for your contribution. Have you tried to combine the two methods of LDAM and HAR?

How to keep image description in HumanArt dataset when loading this dataset?

1

### What is the feature? I tried to load HumanArt dataset by: ``` from mmpose.datasets.datasets.body import HumanArtDataset train_dataset = HumanArtDataset( ann_file='annotations/training_humanart.json', data_prefix=dict(img=''), data_root="data/HumanArt", data_mode="bottomup" ) ``` Then I print `train_dataset[0].keys()`,...