mmpose

mmpose copied to clipboard

implentation for ZoomNet

2

Is any way I can use ZoomNet in mmpose repo directly?

lutianhao

LiteHRNet Pytorch2onnx.py fails

5

This issue was closed (https://github.com/open-mmlab/mmpose/issues/820#issue-954613454) but the conversion still errors out. Was there more code changes required?

astaranowicz

Inference using VoxelPose

1

Hi guys, Thanks for the great tool. I want to inference with VoxelPose using my own data, but I am a bit confused. With which function do I need to...

gokcergun

det 2d cpn

5

Hi,when I draw keypoints from joint_2d_det_files/cpn_ft_h36m_dbb_test.npy and annotation_body3d/fps50/h36m_test.npz, I found that the 2D keypoints from cpn is more accurate than gt from h36m_test.npz like following（the green points are gt keypoints...

flynnamy

Modelzoo Requests

6

From time to time, there are requests for more checkpoints. Considering that enriching the model zoo is a good thing, we collect requests for checkpoints here. Please post the detailed...

innerlee

Batch Top Down Pose Inference

2

**Describe the feature** Ability to perform top down pose estimation on a batch of images at once. **Motivation** It is inconvenient when trying to perform pose estimation on a video...

edybk

what's the purpose of the line "dict(name='right_shoulder',id=3,color=[0, 255, 0],type='upper',swap='left_shoulder')"?

3

the code below: ` dict( name='left_eye', id=1, color=[51, 153, 255], type='upper', swap='right_eye'), ` left_eye swap right_eye?why?what does it do?

zssure-thu

bottom up

5

Is the bottom - up network similar to openpose ? Because I get the onnx model output is [1,34,128,128] for (512,512,3) image. Is the 34 compose of 17 keypoints and...

alicera

onnx model output node shape is incorrect

4

Thanks for your error report and we appreciate it a lot. If you feel we have helped you, give us a STAR! :satisfied: **Checklist** 1. I have searched related issues...

canghaiyunfan

Why mmpose utilizes all CPU processors by default when training in GPU mode?

3

I trained pose estimation model SimpleBaseLine on a single GPU, where I set the num_workers parameter in pytorch Dataloader to be 4, however, all the CPU cores in my computer...

August0424