Why I only got 0.12(AP50)?

krumo / Domain-Adaptive-Faster-RCNN-PyTorch

Domain Adaptive Faster R-CNN in PyTorch

MIT License

304 stars 68 forks source link

Why I only got 0.12(AP50)? #30

Open xiangxiangtao opened 2 years ago

xiangxiangtao commented 2 years ago

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.

life97 commented 2 years ago

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.

krumo commented 2 years ago

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?