# tensorflow-nodejs **Repository Path**: mirrors_yorkie/tensorflow-nodejs ## Basic Information - **Project Name**: tensorflow-nodejs - **Description**: TensorFlow Node.js provides idiomatic JavaScript language bindings and a high layer API for Node.js users. TensorFlow Node.js provides idiomatic JavaScript language bindings and a high layer API for Node.js users. - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-11-23 - **Last Updated**: 2026-05-17 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # TensorFlow for Node.js | NPM | Dependency | Build | Coverage | |-----|------------|-------|----------| |[![NPM version][npm-image]][npm-url]|[![Dependency Status][david-image]][david-url]|[![Build Status][travis-image]][travis-url]|[![Coverage][coveralls-image]][coveralls-url] [npm-image]: https://img.shields.io/npm/v/tensorflow2.svg?style=flat-square [npm-url]: https://npmjs.org/package/tensorflow2 [travis-image]: https://img.shields.io/travis/yorkie/tensorflow-nodejs.svg?style=flat-square [travis-url]: https://travis-ci.org/yorkie/tensorflow-nodejs [david-image]: http://img.shields.io/david/yorkie/tensorflow-nodejs.svg?style=flat-square [david-url]: https://david-dm.org/yorkie/tensorflow-nodejs [coveralls-image]: https://img.shields.io/codecov/c/github/yorkie/tensorflow-nodejs.svg?style=flat-square [coveralls-url]: https://codecov.io/github/yorkie/tensorflow-nodejs?branch=master This library wraps [Tensorflow][] Python for Node.js developers, it's powered by [@pipcook/boa](https://github.com/alibaba/pipcook/blob/master/docs/manual/intro-to-boa.md). **Notice:** This project is still under active development and not guaranteed to have a stable API. This is especially true because the underlying TensorFlow C API has not yet been stabilized as well. ## Installation ```sh $ npm install tensorflow2 --save ``` ## Usage ```js const tf = require('tensorflow2'); // load mnist dataset. const dataset = tf.keras.dataset.mnist(); // { // train: { x: [Getter], y: [Getter] }, // test: { x: [Getter], y: [Getter] } // } // create model. const model = tf.keras.models.Sequential([ tf.keras.layers.Flatten({ input_shape: [28, 28] }), tf.keras.layers.Dense(128, { activation: 'relu' }), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10) ]); model.summary(); // compile the model. const loss_fn = tf.keras.losses.SparseCategoricalCrossentropy({ from_logits: true }); model.compile({ optimizer: 'adam', loss: loss_fn, metrics: [ 'accuracy' ], }); // train the model. model.fit(dataset.train.x, dataset.train.y, { epochs: 5 }); // save the model model.save('your-model.h5'); ``` See [example/mnist.js](./example/mnist.js) for complete example. ## Tests ```sh $ npm test ``` ## License [MIT](./LICENSE) licensed @ 2020 [TensorFlow]: http://tensorflow.org