{"id":15009050,"url":"https://github.com/akimach/gestureai","last_synced_at":"2025-04-09T16:23:30.510Z","repository":{"id":181837311,"uuid":"104737547","full_name":"akimach/GestureAI","owner":"akimach","description":"RNN(Recurrent Nerural network) model which recognize hand-gestures drawing 5 figures.","archived":false,"fork":false,"pushed_at":"2017-09-28T08:37:14.000Z","size":5131,"stargazers_count":24,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-23T18:39:14.638Z","etag":null,"topics":["coreml","dataset","deep-learning","deep-neural-networks","demo","ios","keras","keras-models","keras-tensorflow","machine-learning","python","python-2","recurrent-nerural-network","rnn","tensorflow"],"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/akimach.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}},"created_at":"2017-09-25T10:43:24.000Z","updated_at":"2023-08-15T22:31:11.000Z","dependencies_parsed_at":"2023-07-17T20:56:30.021Z","dependency_job_id":null,"html_url":"https://github.com/akimach/GestureAI","commit_stats":null,"previous_names":["akimach/gestureai"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akimach%2FGestureAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akimach%2FGestureAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akimach%2FGestureAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akimach%2FGestureAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/akimach","download_url":"https://codeload.github.com/akimach/GestureAI/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248065863,"owners_count":21041982,"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":["coreml","dataset","deep-learning","deep-neural-networks","demo","ios","keras","keras-models","keras-tensorflow","machine-learning","python","python-2","recurrent-nerural-network","rnn","tensorflow"],"created_at":"2024-09-24T19:22:42.622Z","updated_at":"2025-04-09T16:23:30.494Z","avatar_url":"https://github.com/akimach.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GestureAI\n\n[![MIT License](http://img.shields.io/badge/license-MIT-blue.svg?style=flat)](LICENSE)\n\n`GestureAI` is a RNN(Recurrent Nerural network) model which recognize hand-gestures drawing 5 figures(Circl, Rectangle, Triangle, Cross and the other). This dataset of hand-motion drawing 5 figures is sequences of 3-axis accelerations captured by iPhone. Example to implement RNN in Keras gets 90.8% accuracy by Cross-validation.\n\n## Demo\n\nTrained Neural Network deployed on [GestureAI-iOS, iOS 11 app using CoreML](https://github.com/akimach/GestureAI-iOS) :\n\n![demo](images/demo.gif)\n\n## Get the Dataset\n\nYou can use direct links to download the dataset.\n\n|Name|Examples|Size|Link|MD5 Checksum|\n|:-:|:-:|:-:|:-:|:-:|\n|`gesture-3axis-accel.tar.gz`|1,000|338 KBytes|[Download](https://github.com/akimach/GestureAI/blob/master/datasets/gesture-3axis-accel.tar.gz?raw=true)|`37664771fd60e930033fb24387fb1601 `|\n\n## Labels\n\nThe dataset consists of 1,000 3-axis acceleration sequences of 5 gesture classes, which are defined by motions drawing 5 figures. We don't set a specific rule about stroke order for drawing a figure by hand.\n\n|Label|Description|Examples|Figure|\n|:-:|:-:|:-:|:-:|\n|0|Circle|200|![Circle](images/circle.jpg)|\n|1|Rectangle|200|![Rectangle](images/rectangle.jpg)|\n|2|Triangle|200|![Triangle](images/triangle.jpg)|\n|3|Cross|200|![Cross](images/cross.jpg)|\n|4|Other|200||\n\n## Requirement\n\n* Python (2.7+)\n* numpy (1.12.1+)\n* protobuf (3.1.0+)\n* Keras (1.2.2)\n* TensorFlow (1.2.1)\n* Scikit-learn (0.15+)\n* coremltools (0.6.3)\n\n## Install\n\n```\n$ virtualenv venv\n$ source venv/bin/activate\n$ git clone https://github.com/akimach/GestureAI.git\n$ cd GestureAI\n$ pip install -r requirements.txt\n```\n\n## Examples\n\nTry with Jupyter notebook!\n\n* Loading datasets\n* Tuning hyper-parameters with Grid Search\n* Training RNN with Early-stopping\n\n## Licence\n\n[MIT](https://github.com/akimach/GestureAI/blob/master/LICENSE)\n\n## Author\n\n[Akimasa KIMURA](https://github.com/akimach)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakimach%2Fgestureai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fakimach%2Fgestureai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakimach%2Fgestureai/lists"}