{"id":20727830,"url":"https://github.com/protyayofficial/hypc-net","last_synced_at":"2026-04-18T20:05:01.217Z","repository":{"id":255384503,"uuid":"843051817","full_name":"protyayofficial/hypc-net","owner":"protyayofficial","description":"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.","archived":false,"fork":false,"pushed_at":"2024-08-28T14:50:39.000Z","size":9,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-11T09:28:51.908Z","etag":null,"topics":["hybrid-transfer-learning","image-classification","image-processing","meta-features","yoga-pose-classification"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/protyayofficial.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-15T17:17:16.000Z","updated_at":"2024-08-29T14:48:37.000Z","dependencies_parsed_at":"2024-08-29T17:49:09.425Z","dependency_job_id":null,"html_url":"https://github.com/protyayofficial/hypc-net","commit_stats":null,"previous_names":["protyayofficial/hypc-net"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/protyayofficial/hypc-net","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protyayofficial%2Fhypc-net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protyayofficial%2Fhypc-net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protyayofficial%2Fhypc-net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protyayofficial%2Fhypc-net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/protyayofficial","download_url":"https://codeload.github.com/protyayofficial/hypc-net/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protyayofficial%2Fhypc-net/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":27576899,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-12-07T02:00:07.896Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["hybrid-transfer-learning","image-classification","image-processing","meta-features","yoga-pose-classification"],"created_at":"2024-11-17T04:34:21.739Z","updated_at":"2025-12-07T20:03:56.688Z","avatar_url":"https://github.com/protyayofficial.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HYPCNet: A Hybrid Yoga Pose Classification Neural Network\n\nThis 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.\n\n## Directory Structure\n\n```\n📦 HYPCNet\n├─ train.py\nutils.py\n├─ yoga82\n│  ├─ yoga_train\n│  │  ├─ class_6\n│  │  ├─ class_20\n│  │  └─ class_82\n│  └─ yoga_test\n│     ├─ class_6\n│     ├─ class_20\n│     └─ class_82\n└─ out\n   ├─ models\n   ├─ test_{class_name}.csv\n   ├─ {model}_{class_name}_training_metrics.csv\n   └─ models\n      └─ {model}_{class_name}_new_best_model.pth\n```\n\n©generated by [Project Tree Generator](https://woochanleee.github.io/project-tree-generator)\n\n## Features\n\n- **Hybrid Model Architecture**: Integration of ConvNeXt with traditional ML models like XGboost, RandomForest etc.\n- **Few Shot Like Learning Abilities**: Metafeatures extraction helps in classifying classes with limitations.\n- **Extensive Assesment**: Detailed metrics comparisions with other STOA models and contemporary models.\n\n## Download the Dataset\n\nTo download the dataset: https://forms.gle/tzVHwzbzCEYzZd9W8\n\nMore details about the dataset: https://sites.google.com/view/yoga-82/home\n\nKindly give proper citation to the original authors\n\n## Acknowledgments\n\nWe 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.\n\n## License\n\n\u003cp\u003eThis project is licensed under the \u003ca href=\"LICENSE\"\u003eMIT License\u003c/a\u003e.\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprotyayofficial%2Fhypc-net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprotyayofficial%2Fhypc-net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprotyayofficial%2Fhypc-net/lists"}