Skip to content

HYPC-Net combines deep convolutional neural networks with classical machine learning techniques to achieve superior accuracy in classifying yoga poses. This project includes a comprehensive analysis of model performance using the Yoga-82 dataset, offering a comparative study against state-of-the-art CNN models.

License

Notifications You must be signed in to change notification settings

protyayofficial/hypc-net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

HYPCNet: A Hybrid Yoga Pose Classification Neural Network

This project aims to be a benchmark on classifying yoga poses using pure Convolutional Neural Networks (CNN) and without using any specialized technique. This is achieved by using a novel idea of using ConvNext as a backbon to extract metafeatures from images and using conventional classifying machine learning techniques to correcty predict yoga poses with higher accuracy.

Directory Structure

📦 HYPCNet
├─ train.py
utils.py
├─ yoga82
│  ├─ yoga_train
│  │  ├─ class_6
│  │  ├─ class_20
│  │  └─ class_82
│  └─ yoga_test
│     ├─ class_6
│     ├─ class_20
│     └─ class_82
└─ out
   ├─ models
   ├─ test_{class_name}.csv
   ├─ {model}_{class_name}_training_metrics.csv
   └─ models
      └─ {model}_{class_name}_new_best_model.pth

©generated by Project Tree Generator

Features

  • Hybrid Model Architecture: Integration of ConvNeXt with traditional ML models like XGboost, RandomForest etc.
  • Few Shot Like Learning Abilities: Metafeatures extraction helps in classifying classes with limitations.
  • Extensive Assesment: Detailed metrics comparisions with other STOA models and contemporary models.

Download the Dataset

To download the dataset: https://forms.gle/tzVHwzbzCEYzZd9W8

More details about the dataset: https://sites.google.com/view/yoga-82/home

Kindly give proper citation to the original authors

Acknowledgments

We would like to thank the authors of the Yoga-82 repository for providing a solid foundation for our work. Their initial framework was essential in developing our enhanced model.

License

This project is licensed under the MIT License.

About

HYPC-Net combines deep convolutional neural networks with classical machine learning techniques to achieve superior accuracy in classifying yoga poses. This project includes a comprehensive analysis of model performance using the Yoga-82 dataset, offering a comparative study against state-of-the-art CNN models.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages