AI for everyone

Generic is a showcase for simple experiments that make it easier for anyone to start exploring machine learning, through picture, drawings, language, music and more.

Arbitrary Style Transfer

Artistic

This repository contains an implementation of arbitrary style transfer running fully inside the browser using TensorFlow.js.

Teachable Machine

Enlightenment

Teachable Machine is an experiment that makes it easier for anyone to explore machine learning, live in the browser – no coding required.

Digit Recognizer Live!

Elightenment

Recognizing Digits using TensorFlow.js in Google Chrome.

Translation for English -> French

Communication

TensorFlow.js Example: Sequence-to-Sequence English-French Translation.

Quick Drawing

Enlightenment

A game where a neural net tries to guess what you’re drawing.

Thing translator

Enlightenment

Take a picture of something to hear how to say it in a different language.

Sound maker

Music

Make unusual new sounds with machine learning.

Emotion recognition

Observation

Emotion recognition on face.

Image classification(Caffe)

Elightenment

Have Fun with Machine Learning: A Guide for Beginners.

Image classification
(SqueezeNet)

Elightenment

Inspire children's ability to identify objects.

Move mirror

Funny

Real-time Human Pose Estimation in the Browser with TensorFlow.js.

Emoji Scavenger Hunt

Funny

A web based game that makes use of TensorFlow.js to identify objects.

Scrying Pen

Funny

A realtime implementation of SketchRNN which predicts future strokes while you draw.

Sketch-RNN Demos

Funny

Draw together with a neural network.

Sketch-RNN Drawing

Funny

A Generative Model for Vector Drawings.

Image Caption Generator

Observation

Show and Tell: A Neural Image Caption Generator.

IBM Image Caption Generator

Observation

Create a web app to interact with machine learning generated image captions.

Deep Reinforcement Learning for Keras

Observation

Based on current status and training this player, the fighting the diamond is getting clever.

Voice Conversion with Non-Parallel Data

Speech

Using DNN to build one model and present style for different person but say same sentense.

MuseGAN

Music

Music generation that is built GAN model by tensorflow. Based on different model and generate musics.

Clara: A Neural Net Music Generator

Music

Using an AWD-LSTM network from the FastAI library as the generator model then input music sheet and generate music.

Virtual Fit for glasses

Funny

A glasses shop that have take photo via web camera, inference what's kind of glass is the fitness.

Deep Speech

Funny

A TensorFlow implementation of Baidu's DeepSpeech architecture.

Semantic Image Synthesis with SPADE

Funny

Image segmentation by GAN. Semantic Image Synthesis with Spatially-Adaptive Normalization.

TOP