mmpose icon indicating copy to clipboard operation
mmpose copied to clipboard

OpenMMLab Pose Estimation Toolbox and Benchmark.

Results 432 mmpose issues
Sort by recently updated
recently updated
newest added
trafficstars

I would like to use pretrained voxelpose model with custom data from 4 cameras. My setup and experiments: To the inference I supply 4 frames and 4 sets of camera...

will you provide more 3d pose method, now mmpose only support simplebaseline and videopose

question

Thanks for your open-sourcing smoothnet! I already read the smoothnet paper, and find it inputs the pose data produced by SPIN/VIBE. So, I want to how to retrain smoothnet in...

enhancement

Thanks for your feature request and we will review and plan for it when necessary. If you feel we have helped you, give us a STAR! :satisfied: **Steps** 1. Check...

I firstly trained the model on servers and now I try to load it on desktop (Windows with 3090 CUDA11.4 pytorch1.10) I ran the demo and it was stuck at...

Awaiting response

Hi, I have annotated a custom dataset in COCO Format with keypoints. It's a square object where the keypoints are the corners. My simple question is how do I use...

doc need improvement

Hi, I'm trying to lift 2D pose to 3D using custom model and custom data. My 2D pose estimation model outputs the 17 COCO keypoints in [0,1] interval. My model...

Awaiting response

Dear, I am now trying to fine-tune model of 2d hand pose. However, I found that mmpose didn't train too much deeppose 2d hand pose. I want to use Hrnet_W48...

Awaiting response

This is our iteration plan for MMPose v0.26.0 ### Algorithms - [ ] Support [Residual Log-likelihood Estimation](https://arxiv.org/abs/2107.11291) (ICCV'21, Oral) @Indigo6 #1259 - [ ] Support [Swin-Pose](https://arxiv.org/abs/2201.07384) (arXiv'22) @yumendecc #1230 -...

Config: "configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrnet_w32_coco_256x192.py", model: "https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_coco_256x192-c78dce93_20200708.pth" FPS: 3-4 torch 1.10.1+cu113 CUDA 11.3 GPU: Nvidia Geforce GTX 1660 Ti According to this [Link](https://mmpose.readthedocs.io/en/latest/inference_speed_summary.html ) I should get at least 6-7 FPS. @piercus Help...