mmpose

mmpose copied to clipboard

How to obtain a file that appears in the configuration file

2

I want to use the CMU panoptic dataset to train voxelpose, and the corresponding configuration file is configs/body/3d_kpt_mview_rgb_img/voxelpose/panoptic/voxelpose_prn64x64x64_cpn80x80x20_panoptic_cam5.py. When defining the model, I need to load pre trained weight (pretrained='checkpoints/resnet_50_deconv.pth.tar'),...

912267428

SSL Certificate Error while using mim install

3

Hi, I came across a SSL Certificate Error with using "mim install" command. I could avoid this error with "--trusted-host pypi.org --trusted-host files.pythonhosted.org" while using "pip install" command, but this...

peterpark12

Two label for a single keypoints

3

I have my custom dataset that is 2d grid kind of object, but in a single image part of the object is visible. I trained Hrmet_256x256, and I am getting...

MotiBaadror

您好，一个关于用test.py的问题

1

python tools/test.py configs/body/3d_kpt_mview_rgb_img/voxelpose/campus/voxelpose_prn64x64x64_cpn80x80x20_campus_cam3.py checkpoints/voxelpose_prn64x64x64_cpn80x80x20_campus_cam3-d8decbf7_20220323.pth --out h1.json 我是这样做的，就是用tools/test.py去测试voxelpose，数据集是campus，可是我发现，无论我怎么改变数据集里面的照片数量，他输出的永远都是一样的文件（大小内容都相同）。我从configs文件找，也没有找到在哪里更改输入的路径，找了好久，麻烦帮个忙，谢谢

graceforlife

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...

wusize

Using RLE loss train on custom data

2

Hi,I am trying to train a model that will generate keypoints(my own data on upper-body) depending on body-deeppose res50_coco_256x192_rle .When I start training the model, I get good acc_pose values...

annnnt

error of raise type(e)(f'{obj_cls.__name__}: {e}') and TypeError: Excavator2Dataset: string indices must be integers

8

**Checklist** 1. I have searched related issues but cannot get the expected help. yes 2. The bug has not been fixed in the latest version. yes I try to train...

alaa-shubbak

no output when testing body3d_multiview_detect_and_regress_img_demo.py on custom images

4

Hello, when I try to test body3d_multiview_detect_and_regress_img_demo.py on custom images, there is no output of the skeleton. I've followed the tutorial (https://mmpose.readthedocs.io/en/latest/demo.html#d-multiview-human-pose-demo) to organize my data and rewrote the camera_parameters.json...

leonhard-yu-zhang

### What is the feature? Hi team, I want to track individual human in the mmpose detection model topdown_demo_with_mmdet.py along different frames, so is there any predefined libraries used for...

rohitacharyams

## Motivation Update mmcv version in requirements. https://github.com/open-mmlab/mmcv/releases/tag/v2.2.0 ## Modification - requirements/mminstall.txt ## BC-breaking (Optional) ## Use cases (Optional) ## Checklist **Before PR**: - [ ] I have read and...

xiexinch