HRNet/HRNet-Semantic-Segmentation

some confusing problems in testval and validate

AlanCSU opened this issue · 0 comments

Im grateful for your free code and your job in tech!
And in tools/test.py , i got a function named testval and then i got test_dataset.multi_scale_inference().
so i wanna know the reason why the pred gotten in test_dataset.multi_scale_inference is much worse than validate,which confuse me for a long time.I will be appreciated if you could answer this question.
Have a good day, thank :)