PixelCNN

Published

Jun 16, 2016

PixelCNN is an AI model developed by Google DeepMind (United States), first published in June 2016. It works in the vision domain, on tasks such as image generation.

Epoch AI has no training-compute estimate for this model. It was trained on roughly 15.7B datapoints.

The reference paper has 3,079 citations.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Vision
Task: Image generation
Dataset size: 15.7B
Chips used: 32
Training time: 60 h
Citations: 3,079