Counting 3,542 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Feb. 19, 2019
Sep. 11, 2018

PyTorch implementation of Neural Processes (NP) by Garnelo et al

MNIST image completion

The task is to complete an image given some number [1;784] of context points (coordinates) at which we know the greyscale pixel intensity [0;1].


The first row shows the observed greyscale context points. Unobserved pixels are in blue. The five rows below show realisations of different samples of the global latent variable z given the context points above. Compare with Figure 4 in the paper.

10 context points

10 context points

100 context points

100 context points

300 context points

300 context points

784 context points (full image)

784 context points

How to run

python produces the results above. The script saves examples of reconstructed images at the end of every epoch in results/.


  • Python 3
  • PyTorch 0.4.1 or later (tested with 1.0.1)

Other NP implementations

R + TensorFlow -