pytorch/vision

Accounting for class_id in cityscapes dataset

Open

#1,064 创建于 2019年6月28日

在 GitHub 查看
 (6 评论) (0 反应) (0 负责人)Python (6,858 fork)batch import
enhancementhelp wantedmodule: datasetsneeds discussion

仓库指标

Star
 (15,050 star)
PR 合并指标
 (平均合并 12天 8小时) (30 天内合并 14 个 PR)

描述

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

贡献者指南