{"id":16861410,"url":"https://github.com/shiffman/tensorflow-js-examples","last_synced_at":"2025-07-02T07:33:56.072Z","repository":{"id":139338208,"uuid":"131058541","full_name":"shiffman/Tensorflow-JS-Examples","owner":"shiffman","description":"Working on some new examples with tensorflow.js and p5.js","archived":false,"fork":false,"pushed_at":"2019-09-22T18:57:50.000Z","size":853,"stargazers_count":168,"open_issues_count":5,"forks_count":31,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-03-10T21:53:14.828Z","etag":null,"topics":["javascript","machine-learning","ml5","p5js","tensorflow","tensorflow-js"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shiffman.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2018-04-25T20:14:49.000Z","updated_at":"2024-07-02T18:30:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"799d1930-729a-4edd-8820-25a82a8925b7","html_url":"https://github.com/shiffman/Tensorflow-JS-Examples","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/shiffman%2FTensorflow-JS-Examples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shiffman%2FTensorflow-JS-Examples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shiffman%2FTensorflow-JS-Examples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shiffman%2FTensorflow-JS-Examples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shiffman","download_url":"https://codeload.github.com/shiffman/Tensorflow-JS-Examples/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243846986,"owners_count":20357296,"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":["javascript","machine-learning","ml5","p5js","tensorflow","tensorflow-js"],"created_at":"2024-10-13T14:31:53.120Z","updated_at":"2025-03-17T05:32:26.856Z","avatar_url":"https://github.com/shiffman.png","language":"JavaScript","readme":"# TensorFlow.js Examples\n\n## XOR vanilla neural network\n\n## Doodle Classifier\nThis repo is experimental and in progress. It is an \"MNIST\"-style classification example using the [Google QuickDraw dataset](https://quickdraw.withgoogle.com/data), [p5js](https://p5js.org/), and [tensorflow.js](https://js.tensorflow.org). It is loosely based on the [tfjs MNIST example](https://github.com/tensorflow/tfjs-examples/tree/master/mnist).\n\n### Reference\n* [JS Doodle Classifier video tutorials](https://www.youtube.com/watch?v=pqY_Tn2SIVA\u0026list=PLRqwX-V7Uu6Zs14zKVuTuit6jApJgoYZQ)\n* [ml4a ofx Doodle Classifier](https://ml4a.github.io/guides/DoodleClassifier/)\n\n### RoadMap\n* [ ] Simplify model removing convolutional layers. The idea is for this to be a dropdead simple example that I can use to explain tensorflow.js and the layers API. I'd like to cover convolutional neural networks as a secondary example.\n* [ ] Incorporate testing data. At the moment [no any validation / testing data](https://github.com/shiffman/Tensorflow-JS-Doodle-Classifier/blob/master/classifier.js#L53) is included during training. For clarity of the example I might like to run the testing as a separate function. What do the results mean me if I give it `null` data?\n* [ ] Guess user drawings in real-time.\n* [ ] Train with a much larger dataset.\n* [ ] Save model using local storage or to JSON file.\n* [ ] Bring the idea of a higher level `Classifier` class that wraps keras layers into [ml5](https://ml5js.github.io/).\n\n### Neuro-Evolution\n* [Flappy Bird Demo: Learning](https://shiffman.github.io/Tensorflow-JS-Examples/04_neuro_evolution_flappy/) \n* [Flappy Bird Demo: Loading Saved Model](https://shiffman.github.io/Tensorflow-JS-Examples/04_neuro_load_flappy/) \n* [Steering Ecosystem Simulation Demo](https://shiffman.github.io/Tensorflow-JS-Examples/05_neuro_evolution_steering/) ","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshiffman%2Ftensorflow-js-examples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshiffman%2Ftensorflow-js-examples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshiffman%2Ftensorflow-js-examples/lists"}