Hao Wang

[Fix] Support MaskFormer.

3

## Motivation Add MaskFormer to mmseg. ## Modification * add 'ToMask' formatting operator to train pipeline to generate the 'gt_masks' and 'gt_labels'. * change 'DefaultFormatBundle' class to adapt to new...

Request for Training & Evaluation Code

5

Could you leave the code of training and evaluation? Thanks a lot.

"dataloader.test.batch_size" > 1 when evaluation is not supported!

11

Hi: I want to set "dataloader.test.batch_size = 16" (default is 1) to accelerate the evaluation speed. But, I get a much smaller mAP results, e.g. 0.59 vs 41.5 mAP. Is...

Update checkpoint_hook.py

4

Add create_symlink function to create symlink of latest checkpoint. Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and...

Try OV-DINO, a more powerful open-vocabulary detector.

1

Thanks for the awesome Grounding-DINO, I share our recent work 🦖OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion. * OV-DINO is a novel unified open vocabulary detection approach that offers...

Try OV-DINO, a more powerful open-vocabulary detector.

2

Thanks for the awesome YOLO-World, I share our recent work 🦖OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion. * OV-DINO is a novel unified open vocabulary detection approach that offers...

Raise issue in English first, please!

2

Hello, guys. To help everyone (especially those outside of China) to find solution from issues, please consider raise the issue in English first. Thank you!

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...

Enhance LLaVA dataset processing with optional text preprocessing

1

Dear XTuner Contributors, Thank you for providing the open-source code for MLLM. I noticed that the process_hf_dataset function in the LLaVADataset takes several minutes to preprocess text data each time...