GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → tayden → VAE-Latent-Space-Explorer

tayden / VAE-Latent-Space-Explorer

Licence: MIT license
Interactive exploration of MNIST variational autoencoder latent space with React and tensorflow.js.

Programming Languages

Jupyter Notebook
11667 projects
javascript
184084 projects - #8 most used programming language

Labels

reactd3mnistvariational-autoencodertensorflow-js

Projects that are alternatives of or similar to VAE-Latent-Space-Explorer

Tensorflow Mnist Cvae
Tensorflow implementation of conditional variational auto-encoder for MNIST
Stars: ✭ 139 (+363.33%)
Mutual labels:  mnist, variational-autoencoder
VAE-Gumbel-Softmax
An implementation of a Variational-Autoencoder using the Gumbel-Softmax reparametrization trick in TensorFlow (tested on r1.5 CPU and GPU) in ICLR 2017.
Stars: ✭ 66 (+120%)
Mutual labels:  mnist, variational-autoencoder
playing with vae
Comparing FC VAE / FCN VAE / PCA / UMAP on MNIST / FMNIST
Stars: ✭ 53 (+76.67%)
Mutual labels:  mnist, variational-autoencoder
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+12516.67%)
Mutual labels:  mnist, variational-autoencoder
Tensorflow Mnist Vae
Tensorflow implementation of variational auto-encoder for MNIST
Stars: ✭ 422 (+1306.67%)
Mutual labels:  mnist, variational-autoencoder
Disentangling Vae
Experiments for understanding disentanglement in VAE latent representations
Stars: ✭ 398 (+1226.67%)
Mutual labels:  mnist, variational-autoencoder
haskell-vae
Learning about Haskell with Variational Autoencoders
Stars: ✭ 18 (-40%)
Mutual labels:  mnist, variational-autoencoder
Deep Generative Models
Deep generative models implemented with TensorFlow 2.0: eg. Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Deep Boltzmann Machine (DBM), Convolutional Variational Auto-Encoder (CVAE), Convolutional Generative Adversarial Network (CGAN)
Stars: ✭ 34 (+13.33%)
Mutual labels:  mnist, variational-autoencoder
Vae Cvae Mnist
Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch
Stars: ✭ 229 (+663.33%)
Mutual labels:  mnist, variational-autoencoder
kotlin-js-D3js-example
A simple example of a D3 JavaScript program in Kotlin
Stars: ✭ 13 (-56.67%)
Mutual labels:  d3
tensorflow-image-recognition-chrome-extension
Chrome browser extension for using TensorFlow image recognition on web pages
Stars: ✭ 88 (+193.33%)
Mutual labels:  tensorflow-js
ddplot
Create D3 based SVG graphics easily from R
Stars: ✭ 43 (+43.33%)
Mutual labels:  d3
MIDI-VAE
No description or website provided.
Stars: ✭ 56 (+86.67%)
Mutual labels:  variational-autoencoder
kanji-recognition
ichisadashioko.github.io/kanji-recognition/
Stars: ✭ 21 (-30%)
Mutual labels:  tensorflow-js
MNIST-CoreML
Predict handwritten digits with CoreML
Stars: ✭ 63 (+110%)
Mutual labels:  mnist
digitRecognition
Implementation of a digit recognition using my Neural Network with the MNIST data set.
Stars: ✭ 21 (-30%)
Mutual labels:  mnist
Freecodecamp
freeCodeCamp.org's open-source codebase and curriculum. Learn to code for free.
Stars: ✭ 339,510 (+1131600%)
Mutual labels:  d3
Netwulf
Interactive visualization of networks based on Ulf Aslak's d3 web app.
Stars: ✭ 254 (+746.67%)
Mutual labels:  d3
labs-migration-viz
A single-page interactive visualization of historic U.S. Census migration data for New York City
Stars: ✭ 18 (-40%)
Mutual labels:  d3
soft-intro-vae-pytorch
[CVPR 2021 Oral] Official PyTorch implementation of Soft-IntroVAE from the paper "Soft-IntroVAE: Analyzing and Improving Introspective Variational Autoencoders"
Stars: ✭ 170 (+466.67%)
Mutual labels:  variational-autoencoder
View All Similar Projects ➔

VAE Latent Space Explorer

demo

Try the demo!

About

This application is a toy visualization that allows you to generate new images of 28x28 numerical digits using a variational autoencoder in the browser.

Implementation details

The variational autoencoder was implemented using Keras and the relevant code is located in the scripts directory in a Jupyter notebook. Once the model is trained, the architecture and weights are saved in a format that can be ingested by tensorflow-js. Tensorflow-js handles implementing the model architecture and loading the weight in the browser. By leveraging WebGL, the model can efficient generate new image samples when given an appropriate latent space vector in the client browser.

The application uses React.js for interface updates along with html Canvas to draw the image matrices. D3.js was used to generate the scatterplot and handle hover events.

Created by Taylor Denouden (April 2018)

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].