fyu / dilation

Dilated Convolution for Semantic Image Segmentation

Home Page:https://www.vis.xyz/pub/dilation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Get label images for evaluation

Timo-hab opened this issue · comments

Hi Fisher

Thanks for that great repository! Could you still tell me, how to convert the color images to label images, where each pixel has an ID that represents the ground truth label? Is there already a script? Thanks in advance!

Best
Timo

Which dataset are you talking about?

I am talking about cityscapes dataset.

The CityScapes team provides scripts that can parse the label images and convert the labels: https://github.com/mcordts/cityscapesScripts

What is the best way to convert the CamVid dataset output to single channel results (same issue, different dataset)?