Posts

This post is presented in noteworthy - the journal blog. Hi everybody! Today, we will continue the series about autoregressive models. Summary Autoregressive models — PixelCNN Modelling coloured images PixelCNN’s blind spot in the receptive field Fixing the blind spot — Gated PixelCNN Conditional generation with Gated PixelCNN Gated PixelCNN with cropped convolutions Improving performance — PixelCNN++ Improving sampling time — Fast PixelCNN++ Using attention mechanisms — PixelSNAIL Generating Diverse High-Fidelity Images — VQ-VAE 2 For each topic, we implemented the models that are available in this repository.

This post is presented in towardsdatascience.com. Hi everybody! This is our first post of a series about modern autoregressive models. Here are the topics we are going to cover in this series: