Pixel Recurrent Neural Networks

Code

• github.com/apple/ml-tarflow
  pytorch★ 330
• github.com/encoreus/gs-jacobi_for_tarflow
  pytorch★ 15
• github.com/EugenHotaj/pytorch-generative/blob/master/pytorch_generative/models/autoregressive/pixel_cnn.py
  pytorch★ 0
• github.com/anordertoreclaim/PixelCNN
  pytorch★ 0
• github.com/a-imamshah/pixelcnn.jl
  none★ 0
• github.com/eyalbetzalel/pytorch-generative
  pytorch★ 0
• github.com/kamenbliznashki/pixel_models
  pytorch★ 0
• github.com/ardapekis/pixel-rnn
  pytorch★ 0
• github.com/singh-hrituraj/PixelCNN-Pytorch
  pytorch★ 0
• github.com/jzbontar/pixelcnn-pytorch
  pytorch★ 0

Abstract

Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image. Architectural novelties include fast two-dimensional recurrent layers and an effective use of residual connections in deep recurrent networks. We achieve log-likelihood scores on natural images that are considerably better than the previous state of the art. Our main results also provide benchmarks on the diverse ImageNet dataset. Samples generated from the model appear crisp, varied and globally coherent.

Tasks

Benchmark Results

Reproductions