pytorch/vision

Accounting for class_id in cityscapes dataset

Open

#1,064 opened on Jun 28, 2019

View on GitHub
 (6 comments) (0 reactions) (0 assignees)Python (6,858 forks)batch import
enhancementhelp wantedmodule: datasetsneeds discussion

Repository metrics

Stars
 (15,050 stars)
PR merge metrics
 (Avg merge 12d 8h) (14 merged PRs in 30d)

Description

Hi,

In the dataset class for Cityscapes, the classes with their meta-data is mentioned as a namedtuple. However, this information is not used anywhere. Especially for semantic segmenation, the train_id should be used to convert the pixel value (of the label image) to the training label.

Is this planned to be added anytime soon?

Edit: There seems to have been a commit that does something like this and that hasn't been merged. https://github.com/pytorch/vision/pull/1025/commits/39a7a2fb6015792b6c32fd7ee3eeac9774f712a4

Contributor guide

Research direction
Implement the missing mapping from pixel values to training labels using the train id field of the class metadata in the Cityscapes dataset class. Refer to the unmerged commit at https://github.com/pytorch/vision/pull/1025/commits/39a7a2fb6015792b6c32fd7ee3eeac9774f712a4 for guidance.
Tech stack
python
Domain
machine learning
Issue type
Feature
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.
Half day
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
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60