This is the code for this video on Youtube by Siraj Raval as part of the Deep Learning Nanodegree with Udacity. We're going to build a variational autoencoder that generates MNIST digits after training on them. We could extend the code to generate any type of image, just replace the training data with your choice of dataset.
- tensorflow
- numpy
Run jupyter notebook in temrinal and the code will appear in the browser
Install jupyter here
Credits go to bluebelmont. I've merely created a wrapper to get people started.