Lossy image autoencoders with convolution and deconvolution networks in Tensorflow

Requirements

(Trained with CIFAR-10 dataset (with 50000 samples) and a code length equal to 128)

First row: original images, second row: lossy reconstructions

Possible improvements include:

Adding a flag (using a placeholder) to use the model for both training and prediction. In the former mode, the input is an image batch, while in the latter is a code batch
Using L1 (and/or L2) code regularization

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
.gitignore		.gitignore
LICENSE		LICENSE
Lossy Image Autoencoder.ipynb		Lossy Image Autoencoder.ipynb
README.md		README.md