Semantic-Segment-Anything icon indicating copy to clipboard operation
Semantic-Segment-Anything copied to clipboard

Published 20 hours ago • verified publisher icon fudan-zvg

i am confusing about lower evaluation result with segformer method

Open dongshenhan opened this issue 1 year ago • 2 comments

why the segformer result is lower than segformer paper display? is the different with evaluation metircs? i think the paper miou arrive to 84% , but the result you pointed out was 71% thanks~

dongshenhan avatar Jun 05 '23 04:06 dongshenhan

the same problem, have you solved it?

lchen1019 avatar Jun 04 '24 07:06 lchen1019

I solved it, they didn't do BGR2RGB, when load image.

lchen1019 avatar Jun 06 '24 10:06 lchen1019