WritingOpenAIOpenAIpublished Jan 19, 2017seen 6d

PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications

Open original ↗

Captured source

source ↗

PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications | OpenAI

January 19, 2017

PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications

Loading…

Share

Abstract

PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at this https URL⁠. Our implementation contains a number of modifications to the original model that both simplify its structure and improve its performance. 1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training. 2) We condition on whole pixels, rather than R/G/B sub-pixels, simplifying the model structure. 3) We use downsampling to efficiently capture structure at multiple resolutions. 4) We introduce additional short-cut connections to further speed up optimization. 5) We regularize the model using dropout. Finally, we present state-of-the-art log likelihood results on CIFAR-10 to demonstrate the usefulness of these modifications.

Authors

Tim Salimans, Andrej Karpathy, Xi Chen, Durk Kingma

Related articles

Hierarchical text-conditional image generation with CLIP latentsPublicationApr 13, 2022

DALL·E: Creating images from textMilestoneJan 5, 2021

Image GPTPublicationJun 17, 2020