Size Wu (吴思泽)

[Refactor] disentangle the 2d keypoint head from `DetectAndRegress` in multiview pose

6

## Motivation The backbone in multiview_pose.[DetectAndRegress ](https://github.com/open-mmlab/mmpose/blob/master/mmpose/models/detectors/multiview_pose.py)consists a 2d keypoint_head (e.g. a deconvhead), which should be split out. ## Modification mmpose/models/detectors/multiview_pose.py ## BC-breaking (Optional) ## Use cases (Optional) ## Checklist...

[Fix] Devide-and-integerize operation for torch.Tensor

5

## Motivation Resolve pytorch warning in voxelpose_head.py for divison operation. ## Modification ## BC-breaking (Optional) ## Use cases (Optional) ## Checklist **Before PR**: - [ ] I have read and...

In the paper and official code of CenterPoint, there are two approaches -- single-stage and two-stage. The two-stage uses the pre-trained model in the first stage and uses several fc...

How did you get 2d poses

5

Would you please give more details about your 2D model? Is it a top-down approach? If yes, are the bboxs gt or detected?

Get stuck after one epoch of training (Multi GPU DDP) See this!

33

When training with multiple gpus, the programme stops at "INFO - finding looplift candidates" after one epoch of training? This info sentence might come from numba, but I am not...

[Enhance] Reform multiviewpose

2

## Motivation Reformulate "DetectAndRegress" so that it has similar structure with a bottom-up method ## Modification ## BC-breaking (Optional) ## Use cases (Optional) ## Checklist **Before PR**: - [ ]...

Support Demo on Campus/Shelf datasets

2

## Motivation Add demo script for VoxelPose on Campus/Shelf datasets. ## Modification ## BC-breaking (Optional) ## Use cases (Optional) ## Checklist **Before PR**: - [ ] I have read and...

Hi, Great work! Can you provide the vision-language models in Pytorch.

## ❓ Questions and Help Hi! I am trying to reproduce your work using newer version of Pytorch and MMDet. For now I have problems in reproducing the performance reported...

Thanks for sharing your models and datasets! May I know what is the difference between `LRV Instruction` and `LRV Instruction(More)`?