This examples lets you train a MNIST Autoencoder using a Fully Connected Neural Network (also known as a DenseNet) in written in Tfjs

You can select the structure for the DenseNet and see the performance of the model.
The MNIST dataset is used as training data.

Set latent space dimension to 2 for 2d Exploration of the latent space. Otherwise set it high for accurate autoencoding
Visualization scale determines the scale of 2d pane

Training Parameters

N hidden layers in encoder and decoder

Output dimension of each layer

Hidden code dimension (Set it to 2 for graph visualization)

# Batch size:

# LearnRate:

# Training epochs:

# Visualization scale

Training Parameters

This will show the examples of autoencoder once it its trained

This is for 2d plot visualization of latent space of autoencoder.
Drag in the 2d Pane below slowly

This is for autoencoding your drawing on the canvas

Training Parameters

This will show the examples of autoencoder once it its trained

This is for 2d plot visualization of latent space of autoencoder. Drag in the 2d Pane below slowly

This is for autoencoding your drawing on the canvas

This is for 2d plot visualization of latent space of autoencoder.
Drag in the 2d Pane below slowly