Jiahao Wang

images from lsp extend dataset

1

Hi, how did you pre-process the images from Leeds Sports Pose Extended Training Dataset? I downloaded images on its website (https://sam.johnson.io/research/lspet.html), but they are .jpg, not .png as used in...

Add "forward chamfer distance" in pytorch3d.loss.chamfer

3

## 🚀 Feature Forward chamfer distance (chamfer distance only from source to target) ## Motivation Currently, in pytorch3d.loss.chamfer, the chamfer_distance function can returns "cham_dist = cham_x + cham_y". However, in...

[Bug] After running inferencer_demo.py with --num-instances=2, the output video cannot play

4

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmpose/issues) and [Discussions](https://github.com/open-mmlab/mmpose/discussions) but cannot get the expected help. - [X] The bug has not been fixed in the latest version(https://github.com/open-mmlab/mmpose). ### Environment...

SART algorithm stuck in "set_w" when the input image is large

13

## Behavior When I ran iterative methods like SART on a CT scan (512×512×463, can be downloaded [here](https://drive.google.com/file/d/1BGGxrHR984JRAF0AYlLAWksPivCU9hKw/view?usp=drive_link)), it was stuck in "set_w" (w=Ax(...)) when initializing IterativeReconAlg class ([link to...

(ddp) multi gpu training error: unused parameters

4

Thanks for the nice work! Currently, I have a problem when I train HMR2 on Slurm with 8 GPUs using: `python train.py exp_name=hmr2 data=mix_all experiment=hmr_vit_transformer launcher=slurm trainer=ddp` I got an...