A JavaScript library for training and deploying ML models in the browser and on Node.js.
Setup Tensorflow.js on Mac
In order to run tensorflow.js in node.js on Mac, you should install tensorflow.js as following:
$ npm install @tensorflow/tfjs-node > @tensorflow/tfjs-node@0.1.20 install /Users/kurapa/node_modules/@tensorflow/tfjs-node > node scripts/install.js * Downloading libtensorflow [==============================] 5852094/bps 100% 0.0s * Building TensorFlow Node.js bindings > protobufjs@6.8.8 postinstall /Users/kurapa/node_modules/protobufjs > node scripts/postinstall npm WARN saveError ENOENT: no such file or directory, open '/Users/kurapa/package.json' npm notice created a lockfile as package-lock.json. You should commit this file. npm WARN enoent ENOENT: no such file or directory, open '/Users/kurapa/package.json' npm WARN kurapa No description npm WARN kurapa No repository field. npm WARN kurapa No README data npm WARN kurapa No license field. + @tensorflow/tfjs-node@0.1.20 added 48 packages from 52 contributors and audited 61 packages in 20.808s found 0 vulnerabilities
If your system NVIDIA GPU, it will be recommended to install below package as well.
$ npm install @tensorflow/tfjs-node-gpu
The below is the example of tensorflow.js based on node.js
const tf = require('@tensorflow/tfjs'); // Load the binding: require('@tensorflow/tfjs-node'); // Use '@tensorflow/tfjs-node-gpu' if running with GPU. // Train a simple model: const model = tf.sequential(); model.add(tf.layers.dense({units: 100, activation: 'relu', inputShape: [10]})); model.add(tf.layers.dense({units: 1, activation: 'linear'})); model.compile({optimizer: 'sgd', loss: 'meanSquaredError'}); const xs = tf.randomNormal([100, 10]); const ys = tf.randomNormal([100, 1]); model.fit(xs, ys, { epochs: 100, callbacks: { onEpochEnd: async (epoch, log) => { console.log(`Epoch ${epoch}: loss = ${log.loss}`); } } });
Reference URL: https://js.tensorflow.org/