Domain-Adaptive-Faster-RCNN-PyTorch icon indicating copy to clipboard operation
Domain-Adaptive-Faster-RCNN-PyTorch copied to clipboard

Published 20 hours ago • verified publisher icon krumo

Why I only got 0.12(AP50)?

Open xiangxiangtao opened this issue 3 years ago • 2 comments

Hello, I used cityscapes and foggy_cityscapes dataset to train the model according to the example usage,after 70000 iter ,the AP50 index obtained is only 0.12. I would like to ask where there may be a problem.

xiangxiangtao avatar Oct 02 '21 07:10 xiangxiangtao

Hello, can you please tell me which version of pytorch and torchvision did you compile successfully? I tried many times and the compilation failed, thank you very much.

life97 avatar Dec 18 '21 13:12 life97

Hi, recently I rerun this repo and also get the reported number on Cityscapes->Foggy Cityscapes task. Would you mind providing more details about how you run the code?

krumo avatar Mar 23 '22 11:03 krumo