pytorch/vision

Accounting for class_id in cityscapes dataset

Open

#1,064 opened on 2019年6月28日

GitHub で見る
 (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
 (平均マージ 12d 8h) (30d で 14 merged PRs)

説明

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

コントリビューターガイド