pytorch / pytorch/vision

How to load indexed images (color maps) using dataset loader

Open
#622 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

The dataset loader returns image loaded as rgb. Which is great for all other purposes, but loading an indexed image for example segmentation mask is a pain.

This is the line :
https://github.com/pytorch/vision/blob/master/torchvision/datasets/folder.py#L161

The PIL module does load images by default if they are just color maps, can we not just return without conversion to rgb or pass a flag to convert to rgb ?

OR is there any other better way of creating a dataloader with the masks folder ?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start at torchvision/datasets/folder.py line 161 and inspect how the dataset loader converts images through PIL. Compare the current RGB behavior with the needs of indexed segmentation masks and determine whether preserving the source mode or adding an option is appropriate. Done means the loader can support masks without losing their indexed color-map values.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.