pytorch/examples

VAE reconstruction loss (BCE)

Open

#460 opened on Dec 1, 2018

View on GitHub
 (2 comments) (3 reactions) (0 assignees)Python (9,429 forks)batch import
good first issue

Repository metrics

Stars
 (21,634 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

The current implementation uses

F.binary_cross_entropy(recon_x, x.view(-1, 784), reduction='sum')

as the reconstruction loss. The image x has pixel values in [0,1]. This is not the same as Bernoulli log likelihood. The images would have to binarized.

In Ladder Variational Autoencoders by Sonderby et al, they binarize the images as a Bernoulli sample after each epoch.

Contributor guide

Research direction
Investigate how to binarize images in the VAE example and modify the training loop to binarize images after each epoch as described in the Ladder VAE paper.
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorchVariational Autoencoders
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65