{"id":13586434,"url":"https://github.com/smellslikeml/ActionAI","last_synced_at":"2025-04-07T15:32:05.060Z","repository":{"id":39734865,"uuid":"169527185","full_name":"smellslikeml/ActionAI","owner":"smellslikeml","description":"Real-Time Spatio-Temporally Localized Activity Detection by Tracking Body Keypoints","archived":false,"fork":false,"pushed_at":"2023-09-23T19:24:24.000Z","size":209372,"stargazers_count":697,"open_issues_count":34,"forks_count":186,"subscribers_count":34,"default_branch":"actionai-cli","last_synced_at":"2024-02-14T21:27:59.524Z","etag":null,"topics":["classifier","edgetpu","human-action-recognition","human-activity-recognition","jetson-nano","lstm","machinelearning","pose-estimation","raspberry-pi","scikit-learn","tensorflow2"],"latest_commit_sha":null,"homepage":"https://www.hackster.io/actionai/actionai-custom-tracking-multiperson-activity-recognition-fa5cb5","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/smellslikeml.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","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":"2019-02-07T06:09:11.000Z","updated_at":"2024-08-01T16:32:30.445Z","dependencies_parsed_at":"2024-08-01T16:42:41.462Z","dependency_job_id":null,"html_url":"https://github.com/smellslikeml/ActionAI","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smellslikeml%2FActionAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smellslikeml%2FActionAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smellslikeml%2FActionAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smellslikeml%2FActionAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/smellslikeml","download_url":"https://codeload.github.com/smellslikeml/ActionAI/tar.gz/refs/heads/actionai-cli","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247679612,"owners_count":20978085,"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","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":["classifier","edgetpu","human-action-recognition","human-activity-recognition","jetson-nano","lstm","machinelearning","pose-estimation","raspberry-pi","scikit-learn","tensorflow2"],"created_at":"2024-08-01T15:05:34.136Z","updated_at":"2025-04-07T15:32:05.054Z","avatar_url":"https://github.com/smellslikeml.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# ActionAI 🤸\n\n[![Python 3.x](https://img.shields.io/badge/python-3.x-blue.svg)](https://www.python.org/downloads/release/python-370/) [![Join the chat at https://gitter.im/action-ai/community](https://badges.gitter.im/action-ai/community.svg)](https://gitter.im/action-ai/community?utm_source=badge\u0026utm_medium=badge\u0026utm_campaign=pr-badge\u0026utm_content=badge)\n![stars](https://img.shields.io/github/stars/smellslikeml/ActionAI)\n![forks](https://img.shields.io/github/forks/smellslikeml/ActionAI)\n![license](https://img.shields.io/github/license/smellslikeml/ActionAI)\n![twitter](https://img.shields.io/twitter/url?style=social\u0026url=https%3A%2F%2Fgithub.com%2Fsmellslikeml%2FActionAI)\n\nActionAI is a python library for training machine learning models to classify human action. It is a generalization of our [yoga smart personal trainer](https://www.hackster.io/yogai/yogai-smart-personal-trainer-f53744), which is included in this repo as an example.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/smellslikeml/ActionAI/blob/master/assets/ActionAI_main.gif\"\u003e\n\u003c/p\u003e\n\n## Getting Started \nThese instructions will show how to prepare your image data, train a model, and deploy the model to classify human action from image samples. See deployment for notes on how to deploy the project on a live stream.\n\n### Installation\n\nAdd the smellslikeml PPA and install with the following:\n```\nsudo add-apt-repository ppa:smellslikeml/ppa\nsudo apt update\n\n# Install with:\nsudo apt-get install actionai\n```\n\nMake sure to configure the working directory with:\n```\nactionai configure\n```\n\n### Using the CLI\n\nOrganize your training data in subdirectories like the example below. The `actionai` cli will automatically create a dataset from subdirectories of videos where each subdirectory is a category label.\n\n```\n.\n└── dataset/\n    ├── category_1/\n    │   └── *.mp4\n    ├── category_2/\n    │   └── *.mp4\n    ├── category_3/\n    │   └── *.mp4\n    └── ...\n```\n\nThen you can train a model with:\n```\nactionai train --data=/path/to/your/data/dir --model=/path/to/your/model/dir\n```\n\nAnd then run inference on a video with:\n```\nactionai predict --model=/path/to/your/model/dir --video=/path/to/your/video.mp4\n```\n\nView the default `config.ini` file included in this branch for additional configurations. You can pass your own config file using the `--cfg` flag.\n\n\n## Contributing\n\nPlease read [CONTRIBUTING.md](CONTRIBUTING.md) for details on our code of conduct, and the process for submitting pull requests to us.\n\n## License\n\nThis project is licensed under the GNU General Public License v3.0 - see the [LICENSE.md](LICENSE.md) file for details\n\n## References\n\n* [Hackster post](https://www.hackster.io/yogai/yogai-smart-personal-trainer-f53744)\n* [YogAI article](https://www.raspberrypi.org/blog/yoga-training-with-yogai-and-a-raspberry-pi-smart-mirror-the-magpi-issue-80/)\n* [Convolutional Pose Machine](https://arxiv.org/pdf/1602.00134.pdf)\n* [Pose estimation for mobile](https://github.com/edvardHua/PoseEstimationForMobile)\n* [Pose estimation tensorflow implementation](https://github.com/ildoonet/tf-pose-estimation)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmellslikeml%2FActionAI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsmellslikeml%2FActionAI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmellslikeml%2FActionAI/lists"}