Autoencoder

Name	Name	Last commit message	Last commit date
parent directory ..
Control2d.js	Control2d.js	Update Control2d.js	Jul 1, 2020
README.md	README.md	Update README.md	Jul 17, 2020
datas.js	datas.js	adding autoencoder training	Jun 1, 2020
index.html	index.html	Update index.html	Jul 21, 2020
index.js	index.js	Update index.js	Jul 21, 2020
package.json	package.json	adding autoencoder training	Jun 1, 2020
three.min.js	three.min.js	Add files via upload	Jun 5, 2020
ui.js	ui.js	adding autoencoder training	Jun 1, 2020
yarn.lock	yarn.lock	adding autoencoder training	Jun 1, 2020

README.md

Train a model to autoencode handwritten digits from the MNIST database using the tf.layers api. The MNIST dataset is used as training data.

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

-You can select the structure for the DenseNet and see the performance of the model.

-You can also 2d Visualize the encoded space

-You can also autoencode your drawing