LoveDA icon indicating copy to clipboard operation
LoveDA copied to clipboard

Why the mask is all black pic

Open Tracy-git opened this issue 3 years ago • 4 comments

thank for your great works. but why the mask is all black pic, i use the weights you provide to test ,output is also a black pic. could u tell me how to use this weigth to predict ? thanks

Tracy-git avatar Dec 21 '21 18:12 Tracy-git

Category labels: background – 1, building – 2, road – 3, water – 4, barren – 5,forest – 6, agriculture – 7. And the no-data regions were assigned 0 which should be ignored. Hence, the labels are in low contrast stored in PNGs.

Junjue-Wang avatar Dec 22 '21 00:12 Junjue-Wang

How can I get the high-contrast pictures?

Sixsheepdad avatar Oct 25 '23 05:10 Sixsheepdad

https://github.com/Junjue-Wang/LoveDA/blob/master/Semantic_Segmentation/render.py

Junjue-Wang avatar Oct 25 '23 05:10 Junjue-Wang

Thanks!!

Sixsheepdad avatar Oct 25 '23 09:10 Sixsheepdad