cyrildiagne / tfjs-examples

Examples built with TensorFlow.js

Home Page:https://js.tensorflow.org/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

TensorFlow.js Examples

This repository contains a set of examples implemented in TensorFlow.js.

Each example directory is standalone so the directory can be copied to another project.

Overview of Examples

Example name Demo link Input data type Task type Model type Training Inference API type Save-load operations
addition-rnn πŸ”— Text Sequence-to-sequence RNN: SimpleRNN, GRU and LSTM Browser Browser Layers
baseball-node Numeric Multiclass classification Multilayer perceptron Node.js Node.js Layers
boston-housing πŸ”— Numeric Regression Multilayer perceptron Browser Browser Layers
cart-pole πŸ”— Reinforcement learning Policy gradient Browser Browser Layers IndexedDB
custom-layer πŸ”— (Illustrates how to define and use a custom Layer subtype) Browser Layers
data-csv πŸ”— How to build and work with a tf.data.Dataset from a remote CSV.
data-generator πŸ”— How to build and work with a tf.data.Dataset using the generator API. Regression Multilayer perceptron Browser Layers
date-conversion-attention πŸ”— Text Text-to-text conversion Attention mechanism, RNN Node Browser and Node Layers Saving to filesystem and loading in browser
iris πŸ”— Numeric Multiclass classification Multilayer perceptron Browser Browser Layers
iris-fitDataset πŸ”— Numeric Multiclass classification Multilayer perceptron Browser Browser Layers
jena-weather πŸ”— Sequence Sequence-to-prediction MLP and RNNs Browser and Node Browser Layers
lstm-text-generation πŸ”— Text Sequence prediction RNN: LSTM Browser Browser Layers IndexedDB
mnist πŸ”— Image Multiclass classification Convolutional neural network Browser Browser Layers
mnist-acgan πŸ”— Image Generative Adversarial Network (GAN) Convolutional neural network; GAN Node.js Browser Layers Saving to filesystem from Node.js and loading it in the browser
mnist-core πŸ”— Image Multiclass classification Convolutional neural network Browser Browser Core (Ops)
mnist-node Image Multiclass classification Convolutional neural network Node.js Node.js Layers Saving to filesystem
mnist-transfer-cnn πŸ”— Image Multiclass classification (transfer learning) Convolutional neural network Browser Browser Layers Loading pretrained model
mobilenet πŸ”— Image Multiclass classification Convolutional neural network Browser Layers Loading pretrained model
polynomial-regression πŸ”— Numeric Regression Shallow neural network Browser Browser Layers
polynomial-regression-core πŸ”— Numeric Regression Shallow neural network Browser Browser Core (Ops)
sentiment πŸ”— Text Sequence-to-binary-prediction LSTM, 1D convnet Node.js Browser Layers Loading model converted from Keras and tfjs-node
simple-object-detection πŸ”— Image Object detection Convolutional neural network (transfer learning) Node.js Browser Layers Save a trained model from tfjs-node and load it in the browser
translation πŸ”— Text Sequence-to-sequence LSTM encoder and decoder Browser Layers Loading model converted from Keras
tsne-mnist-canvas Dimension reduction and data visualization tSNE Browser Browser Core (Ops)
webcam-transfer-learning πŸ”— Image Multiclass classification (transfer learning) Convolutional neural network Browser Browser Layers Loading pretrained model
website-phishing πŸ”— Numeric Binary classification Multilayer perceptron Browser Browser Layers

Dependencies

Except for getting_started, all the examples require the following dependencies to be installed.

How to build an example

cd into the directory

If you are using yarn:

cd mnist-core
yarn
yarn watch

If you are using npm:

cd mnist-core
npm install
npm run watch

Details

The convention is that each example contains two scripts:

  • yarn watch or npm run watch: starts a local development HTTP server which watches the filesystem for changes so you can edit the code (JS or HTML) and see changes when you refresh the page immediately.

  • yarn build or npm run build: generates a dist/ folder which contains the build artifacts and can be used for deployment.

Contributing

If you want to contribute an example, please reach out to us on Github issues before sending us a pull request as we are trying to keep this set of examples small and highly curated.

ezoic increase your site revenue

About

Examples built with TensorFlow.js

https://js.tensorflow.org/

License:Apache License 2.0


Languages

Language:JavaScript 44.6%Language:CSS 41.3%Language:HTML 8.2%Language:Python 3.9%Language:Shell 1.9%