pytorch / pytorch/vision

Supporting more target_type for Cityscapes

Open
#2,395 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi,

as the Cityscapes dataset also provides extra training data e.g. disparity upon request, I was wondering if they should be added also to the target_type argument for ease of use as well?

one straightforward extension could be:

dataset = Cityscapes('./data/cityscapes', split='train', target_type='disparity')

cc @pmeier

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 the Cityscapes dataset entry point and inspect how the target_type argument currently handles available targets. Determine how disparity should be represented and validated; done means the example target_type='disparity' is supported consistently with the existing dataset interface.

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
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.