Discrete Representation Learning with VQ-VAE and TensorFlow Probability
This article is originally published at https://blogs.rstudio.com/tensorflow/Mostly when thinking of Variational Autoencoders (VAEs), we picture the prior as an isotropic Gaussian. But this is by no means a necessity. The Vector Quantised Variational Autoencoder (VQ-VAE) described in van den Oord et al's "Neural Discrete Representation Learning" features a discrete latent space that allows to learn impressively concise latent representations. In this post, we combine elements of Keras, TensorFlow, and TensorFlow Probability to see if we can generate convincing letters resembling those in Kuzushiji-MNIST.
Thanks for visiting r-craft.org
This article is originally published at https://blogs.rstudio.com/tensorflow/
Please visit source website for post related comments.