We'll build a Variational Autoencoder using Tensorflow to generate images. We'll go through several examples including digit images and pokemon images. VAE's allow us to generate, compress, denoise, and even fuse images together. They are an incredibly powerful tool and we'll go over the implementation details (math included) in this live session.
Code: https://github.com/llSourcell/how_to_generate_images_with_tensorflow_LIVE
Please Subscribe! And like. And comment. That's what keeps me going.
More Learning resources:
https://arxiv.org/abs/1606.05908
https://github.com/stitchfix/fauxtograph
http://deeplearning.jp/cvae/
https://ift6266h17.wordpress.com/2017/03/26/q3-reparameterization-trick-of-variational-autoencoder/
https://www.quora.com/What-is-the-latent-loss-in-variational-autoencoders
https://www.slideshare.net/ShaiHarel/variational-autoencoder-talk
Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/
And please support me on Patreon:
https://www.patreon.com/user?u=3191693
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
