https://github.com/v-sekai/v-sekai.mediapipe-labeler

https://github.com/v-sekai/v-sekai.mediapipe-labeler

Last synced: 10 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/v-sekai/v-sekai.mediapipe-labeler
• Owner: V-Sekai
• License: mit
• Created: 2023-09-02T21:23:18.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-01-10T21:40:08.000Z (4 months ago)
• Last Synced: 2025-03-30T06:31:57.305Z (about 1 month ago)
• Language: Python
• Size: 5.79 MB
• Stars: 2
• Watchers: 4
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Mediapipe Skeleton to COCO JSON

[![All Contributors](https://img.shields.io/badge/all_contributors-1-orange.svg?style=flat-square)](#contributors-)

**WORK IN PROGRESS**

This is a Mediapipe workflow that writes the Mediapipe skeleton, including hands, into a COCO-style JSON format. The workflow utilizes the Mediapipe framework, which provides a flexible and efficient infrastructure for building multimodal applied machine learning models.

[Now on replicate -- live.](https://replicate.com/fire/v-sekai.mediapipe-labeler)

 

**Model File**: [Link to Model Card Blendshape V2.pdf](https://storage.googleapis.com/mediapipe-assets/Model%20Card%20Blendshape%20V2.pdf)

**COCO Keypoints File**: https://roboflow.com/formats/coco-keypoint

# Install

```zsh

sudo curl -o /usr/local/bin/cog -L https://github.com/replicate/cog/releases/latest/download/cog_`uname -s`_`uname -m`

sudo chmod +x /usr/local/bin/cog

# Generate COCO-style JSON with Mediapipe skeleton and hands.

cog predict -i image_path=@./thirdparty/image.jpg

```

## Contributors ✨

Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):

  

    

      
K. S. Ernest (iFire) Lee
🔬 💻

    

  

This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!