An open API service indexing awesome lists of open source software.

https://github.com/edezhic/fashion-generator

In-browser GPU-accelerated Generative Adversarial Network trained on Fashion-MNIST dataset (tensorflow + deeplearn.js)
https://github.com/edezhic/fashion-generator

browser-game deep-learning generative-adversarial-network

Last synced: about 1 year ago
JSON representation

In-browser GPU-accelerated Generative Adversarial Network trained on Fashion-MNIST dataset (tensorflow + deeplearn.js)

Awesome Lists containing this project

README

          

# Fashion Generator

GAN model trained in Tensorflow and then ported to browsers using GPU-accelarated framework [deeplearn.js](https://github.com/PAIR-code/deeplearnjs) which is now the core of tensorflow.js

You can repeat the whole experiment in 3 steps:
- Run train.​py to get ./weights folder
- Build generator.ts
- Run node server and open index.html
- You are awesome!

##### ./model contents:
- train.​py - creates and trains the model, saves generator weights
- GAN.​py - model definition (originated from [this repo](https://github.com/hwalsuklee/tensorflow-generative-model-collections))
- yellowfin.​py - powerful custom TF optimizer, [original repo](https://github.com/JianGoForIt/YellowFin). Not really required, just a nice thing.
- ops.​py and utils.​py - simplified TF operations and other utility functions

##### ./browser contents:
- generator.ts - downloads weights and defines generator model
- index.html - simple wrapper
- other configs