Novo no aprendizado de máquina? Assista a um curso em vídeo para obter conhecimento prático de ML usando tecnologias da Web
Ver série
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
O TensorFlow.js é uma biblioteca para machine learning no JavaScript
Desenvolva modelos de ML em JavaScript e use ML diretamente no navegador ou no Node.js.
Executar modelos existentes
Use modelos do JavaScript prontos ou converta modelos do TensorFlow em Python para que sejam executados no navegador ou pelo Node.js.
Treinar novamente modelos existentes
Treine modelos de ML pré-existentes com seus próprios dados.
Desenvolva ML com JavaScript
Use APIs intuitivas e flexíveis para criar e treinar modelos diretamente em JavaScript.
RNN de desempenho
Assista a uma apresentação de piano em tempo real de uma rede neural.
Holobooth
Viaje para uma praia tropical, o espaço sideral ou qualquer outro lugar com o poder do ML para a Web.
[[["Fácil de entender","easyToUnderstand","thumb-up"],["Meu problema foi resolvido","solvedMyProblem","thumb-up"],["Outro","otherUp","thumb-up"]],[["Não contém as informações de que eu preciso","missingTheInformationINeed","thumb-down"],["Muito complicado / etapas demais","tooComplicatedTooManySteps","thumb-down"],["Desatualizado","outOfDate","thumb-down"],["Problema na tradução","translationIssue","thumb-down"],["Problema com as amostras / o código","samplesCodeIssue","thumb-down"],["Outro","otherDown","thumb-down"]],[],[],[],null,["# TensorFlow.js | Machine Learning for JavaScript Developers\n\nTensorFlow.js is a library for machine learning in JavaScript\n=============================================================\n\nDevelop ML models in JavaScript, and use ML directly in the browser or in Node.js. \n[See tutorials](/js/tutorials)\n\n\nTutorials show you how to use TensorFlow.js with complete, end-to-end examples.\n[See models](/js/models)\n\n\nPre-trained, out-of-the-box models for common use cases.\n[See demos](/js/demos)\n\n\nLive demos and examples run in your browser using TensorFlow.js. \n\nHow it works\n------------\n\n#### Run existing models\n\nUse off-the-shelf JavaScript models or convert Python TensorFlow models to run in the browser or under Node.js. \n[Use official TensorFlow.js models](/js/models) [Convert Python models](/js/tutorials#convert_pretained_models_to_tensorflowjs) \n\n#### Retrain existing models\n\nRetrain pre-existing ML models using your own data. \n[Use Transfer Learning to customize models](/js/tutorials/transfer/what_is_transfer_learning) \n\n#### Develop ML with JavaScript\n\nBuild and train models directly in JavaScript using flexible and intuitive APIs. \n[Get started with TensorFlow.js](/js/tutorials) \n\nDemos\n-----\n\n[Performance RNN](https://magenta.tensorflow.org/demos/performance_rnn/index.html#2%7C2,0,1,0,1,1,0,1,0,1,0,1%7C1,1,1,1,1,1,1,1,1,1,1,1%7C1,1,1,1,1,1,1,1,1,1,1,1%7Cfalse) \nEnjoy a real-time piano performance by a neural network. \n[Explore demo](https://magenta.tensorflow.org/demos/performance_rnn/index.html#2%7C2,0,1,0,1,1,0,1,0,1,0,1%7C1,1,1,1,1,1,1,1,1,1,1,1%7C1,1,1,1,1,1,1,1,1,1,1,1%7Cfalse) [View code](https://github.com/tensorflow/magenta-demos/tree/master/performance_rnn) \n[Webcam Controller](https://storage.googleapis.com/tfjs-examples/webcam-transfer-learning/dist/index.html) \nPlay Pac-Man using images trained in your browser. \n[Explore demo](https://storage.googleapis.com/tfjs-examples/webcam-transfer-learning/dist/index.html) [View code](https://github.com/tensorflow/tfjs-examples/tree/master/webcam-transfer-learning) \n[Holobooth](https://holobooth.flutter.dev/) \nTransport yourself to a tropical beach, outer space, and elsewhere with the power of web ML. \n[Explore demo](https://holobooth.flutter.dev/) [View code](https://github.com/flutter/holobooth) \n[See all demos](/js/demos) \n\nNews \\& announcements\n---------------------\n\nCheck out our [blog](https://blog.tensorflow.org/search?label=TensorFlow.js&max-results=20) for additional updates, and subscribe to our TensorFlow newsletter to get the latest announcements sent directly to your inbox. \n[Sign up](/subscribe) \n\nCommunity participation\n-----------------------\n\nSee more ways to participate in the TensorFlow community. \n[Community](/community) \n[Made with TensorFlow.js demos](https://www.youtube.com/playlist?list=PLQY2H8rRoyvzSZZuF0qJpoJxZR1NgzcZw) \n[TensorFlow.js on GitHub](https://github.com/tensorflow/tfjs) \n[Ask a question on TensorFlow Forum](https://discuss.ai.google.dev/c/tensorflow/21) \n[Stack Overflow](https://stackoverflow.com/questions/tagged/tensorflow.js) \n[Issues, bug reports, and feature requests](https://github.com/tensorflow/tfjs/issues) \n[Announcement-only mailing list](https://groups.google.com/a/tensorflow.org/forum/#!forum/tfjs-announce) \n[Join the TF.js Special Interest Group](https://github.com/tensorflow/community/blob/master/sigs/tf.js/CHARTER.md) \n[Explore Dev Library community projects](https://devlibrary.withgoogle.com/products/ml) \n\nGet started with TensorFlow.js\n------------------------------\n\n[Explore tutorials](/js/tutorials)"]]