{"id":22733983,"url":"https://github.com/mhw32/face-to-emotion","last_synced_at":"2026-04-24T16:40:04.738Z","repository":{"id":82938154,"uuid":"100816607","full_name":"mhw32/face-to-emotion","owner":"mhw32","description":"Deep Learning Model to Predict Emotion Probabilities from Face-Cropped Images","archived":false,"fork":false,"pushed_at":"2017-08-29T20:47:44.000Z","size":1137,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-02-05T04:33:00.035Z","etag":null,"topics":["deep-learning","emotion","face-recognition","flask"],"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/mhw32.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":"2017-08-19T19:23:56.000Z","updated_at":"2017-10-11T06:23:01.000Z","dependencies_parsed_at":"2023-03-08T23:30:43.396Z","dependency_job_id":null,"html_url":"https://github.com/mhw32/face-to-emotion","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/mhw32%2Fface-to-emotion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mhw32%2Fface-to-emotion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mhw32%2Fface-to-emotion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mhw32%2Fface-to-emotion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mhw32","download_url":"https://codeload.github.com/mhw32/face-to-emotion/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246266244,"owners_count":20749754,"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":["deep-learning","emotion","face-recognition","flask"],"created_at":"2024-12-10T20:17:11.469Z","updated_at":"2026-04-24T16:39:59.715Z","avatar_url":"https://github.com/mhw32.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Face2Emotion\n\nDeep convolutional net to predict coarse emotions from image frames.\n\nThe architecture is modeled after the technical report **Real-time Convolutional Neural Networks for Emotion and Gender Classification** by Octavio Arriaga and Paul G. Ploger.\n\nThe authors designed a Xception-based model that combines residual blocks (as in ResNet [[1](https://arxiv.org/abs/1512.03385)]) and depth-wise separable convolutions (as in the traditional Xception [[2](https://arxiv.org/abs/1611.05431)]).\n\nThe model is trained on the FER2013 dataset [[3](https://arxiv.org/abs/1307.0414)] and reaches 66% accuracy. See `models/` for Keras code and see `frozen` for trained weights.\n\n## Flask Application\n\nThere's also a folder in `app/` that stores a vanilla web application with a single endpoint that reads a base64 encoded string representing an image and outputs a map of emotion probabilities per face.\n\n**Note**: This assumes that incoming requests will also pass coordinates for facial objects in the scene. In our instance, we used the [True Face API](http://trueface.ai/). We use the coordinates to pre-crop our image before sending it to our model.\n\n## Additional Info\n\nThis project was entered in the TrueFace.ai hackathon (1st place winner). A Heroku instance is currently up at [https://face2emotionapp.herokuapp.com/](https://face2emotionapp.herokuapp.com/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmhw32%2Fface-to-emotion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmhw32%2Fface-to-emotion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmhw32%2Fface-to-emotion/lists"}