{"id":19874949,"url":"https://github.com/adistrim/emovision","last_synced_at":"2026-02-23T23:09:34.141Z","repository":{"id":231012461,"uuid":"733569854","full_name":"adistrim/EmoVision","owner":"adistrim","description":"👀 EmoVision is a real-time emotion recognition project. It captures video frames from a camera, detects faces, and predicts emotions in real-time.","archived":false,"fork":false,"pushed_at":"2024-10-23T09:43:45.000Z","size":130762,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-18T19:30:05.366Z","etag":null,"topics":["computer-vision","neural-networks"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/adistrim.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":"2023-12-19T16:14:25.000Z","updated_at":"2025-05-27T13:05:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"828c7d7e-6f5b-400f-949f-eced35d72fec","html_url":"https://github.com/adistrim/EmoVision","commit_stats":null,"previous_names":["adistrim/emovision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/adistrim/EmoVision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adistrim%2FEmoVision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adistrim%2FEmoVision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adistrim%2FEmoVision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adistrim%2FEmoVision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adistrim","download_url":"https://codeload.github.com/adistrim/EmoVision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adistrim%2FEmoVision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29760138,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-23T21:02:23.375Z","status":"ssl_error","status_checked_at":"2026-02-23T20:58:31.539Z","response_time":90,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["computer-vision","neural-networks"],"created_at":"2024-11-12T16:26:06.919Z","updated_at":"2026-02-23T23:09:34.098Z","avatar_url":"https://github.com/adistrim.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EmoVision\n\nEmoVision is a real-time emotion recognition project using deep learning. It captures video frames from a camera, detects faces, and predicts emotions in real-time.\n\n## Features\n\n- Real-time face detection and emotion recognition.\n- Uses a trained deep learning model for accurate emotion predictions.\n- Simple integration with OpenCV for video capture.\n\n## Dataset\n\nThe model is trained on the [Face Expression Recognition Dataset](https://www.kaggle.com/datasets/jonathanoheix/face-expression-recognition-dataset) from Kaggle, which consists of 35 thousand images with labeled emotions.\n\n**Processed Data can be downloaded from here: [emovision-google-drive](https://drive.google.com/drive/folders/1MIwS0kAWUqcRxHqpXzoPqQ73AsBSCPWy?usp=sharing)**\n\n## Model Training\n\nThe model was trained for 100 epochs, and the final epoch's metrics are as follows:\n\n- Training loss: 0.7405\n- Training accuracy: 73.07%\n- Validation loss: 1.0369\n- Validation accuracy: 63.08%\n\nThe training process took a total of 6 hours and 34 minutes on a [2020 M1 MacBook Air](https://en.wikipedia.org/wiki/MacBook_Air_(Apple_silicon)).\n\n**Trained Models can be downloaded from here: [emovision-google-drive](https://drive.google.com/drive/folders/1MIwS0kAWUqcRxHqpXzoPqQ73AsBSCPWy?usp=sharing)**\n\n### GPU Training\nGPU: NVIDIA RTX 3070\n- cuDNN version 8.9.7.29 \n- CUDA 11.8\n- nvidia-driver-560\n- Tensorflow version 2.12.0\n\nOS: Ubuntu 22.0.4\n\n### Training insights\n![Training insights](plot/Figure_1.png)\n\n## Getting Started\n\n**Dependency: `python 3.11.9` others are mentioned in the `requirements.txt` file**\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/adistrim/EmoVision.git\n```\n2. Setup virtual environment:\n```bash\ncd EmoVision\npython3 -m venv .venv               # python or python3 depending on the system config\nsource .venv/bin/activate           # For Linux and macOS\n```\n\n3. Install required libraries:\n```bash\npip3 install -r requirements.txt    # pip or pip3 depending on the system config\n```\n4. Execute the realtime.ipynb file.\n\n5. Press 'Q' to end the program.\n\n## License\nThis project is licensed under the [MIT License](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadistrim%2Femovision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadistrim%2Femovision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadistrim%2Femovision/lists"}