HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.2.102 new Hand-Keypoints Pose Estimation Dataset (#16489)

Browse source 
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Muhammad Rizwan Munawar 2024-09-27 05:42:12 +05:00 • committed by GitHub
parent f3d557e3f2
commit 03dc859c8e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 144 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

9
docs/en/datasets/pose/index.md
View file

@ -118,6 +118,15 @@ This section outlines the datasets that are compatible with Ultralytics YOLO for
- **Usage**: Great for animal pose or any other pose that is not human-based.
- [Read more about Tiger-Pose](tiger-pose.md)
### Hand Keypoints
- **Description**: Hand keypoints pose dataset comprises nearly 26K images, with 18776 images allocated for training and 7992 for validation.
- **Label Format**: Same as Ultralytics YOLO format as described above, but with 21 keypoints for human hand and visible dimension.
- **Number of Classes**: 1 (Hand).
- **Keypoints**: 21 keypoints.
- **Usage**: Great for human hand pose estimation.
- [Read more about Hand Keypoints](hand-keypoints.md)
### Adding your own dataset
If you have your own dataset and would like to use it for training pose estimation models with Ultralytics YOLO format, ensure that it follows the format specified above under "Ultralytics YOLO format". Convert your annotations to the required format and specify the paths, number of classes, and class names in the YAML configuration file.