mmpose

mmpose copied to clipboard

[Feature] Support ViTPose

1

## Motivation Add implementation of ViTPose on MMPose 1.0 ## Modification - Add six config files - Add layer decay optimizer - In `HeatmapHead`, add parameter `upsample`, default to zero...

LareinaM

multi-gpu video inference

1

Can I use multiple Gpus for pose-estimation model inference on video? I want to use the VIPNAS model. Looking forward to your reply.

bulingda

多人背景下只保留单人姿态关键点（检测框最大），怎么实现啊

6

If you feel we have helped you, give us a STAR! :satisfied: **Notice** There are several common situations in the reimplementation issues as below 1. Reimplement a model in the...

zzzwwb

Different results when dataset channel is changed

4

Hello, thank you for the great toolbox! I am getting two different results when I use ``` channel_cfg = dict( num_output_channels=17+14, dataset_joints=14, dataset_channel=[0,1,2,3,4,5,6,7,8,9,10,11,12,13], inference_channel=[0,1,2,3,4,5,6,7,8,9,10,11,12,13] ) ``` and ``` channel_cfg =...

kinglr

HOW TO INFERENCE ONNX MODEL ABOUT HRNET POSE ESTIMATION

4

I convert model hrnet of pose estimation: hrnet_w32_coco_256x192.py with checkpoint: hrnet_w32_coco_256x192-c78dce93_20200708.pth to onnx model. Can you tell me how to inference model onnx?

lamhust2008

How to finetune Voxelpose?

5

Thanks for the great work! I'd like to finetune Voxelpose to get the 3d pose estimation from multiple views but I'm new to this. May I ask if there is...

Camila641

AssertionError: MMCV==2.0.0rc3 is used but incompatible. Please install mmcv>=1.3.8, <=1.8.0.

7

I should use `--save-predictions` for get predict result, so I created new conda env and installed mmpose 1.0 followed [here](https://mmpose.readthedocs.io/en/1.x/installation.html) Then I tried to `import mmpose` but I received this...

Jeong-Bin

Thanks for the great work. This feature is asked for multiple times and I see most of the reported issues marked as closed, yet I miss to find a single...

nghorbani

Request training log for `simplebaseline3d_mpi-inf-3dhp_20210603.log.json`

2

关于使用mpi-inf-3dhp数据集训练simplebaseline3d网络用于body 2d点lift到3d点的训练日志打不开，请问可以更新一下吗？ 

jiwei-dot

how to extract inference info from PoseDataSample

1

my question is that: my project inference a image,got keypoints info ,which typedata as PoseSample.How to solve PoseSample ?

yjdqk