pytorch/vision

Accounting for class_id in cityscapes dataset

Open

#1.064 geöffnet am 28. Juni 2019

Auf GitHub ansehen
 (6 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Python (6.858 Forks)batch import
enhancementhelp wantedmodule: datasetsneeds discussion

Repository-Metriken

Stars
 (15.050 Stars)
PR-Merge-Metriken
 (Durchschn. Merge 12T 8h) (14 gemergte PRs in 30 T)

Beschreibung

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