Hana

About image preprocessing

2

If I want to implement deeplabv2 in my own task，should the image preprocessing be same？like no padding，just resize

about grid_num=14

2

I don't understand why grid_num is 14 in code , and why is it divided by 14 in yoloLoss.py line 88?

about proto_tower

2

proto_tower is stacked by 32 convolutions according to your code (fcos/modeling/fcos/fcos.py Line 166). Did you try less number convolutions? I have also recently combined yolact and fcos, but my accuracy...

I install pytorch 1.4.0 which is not compatible with the current detectron2's version It remind me "ModuleNotFoundError: No module named 'torch.utils.hipify" So I want to know your detectron2's version

About mean and std in transfrom

2

Thanks for your great work! I have a question about how to get the normalized parameters like ‘train_y_mean’ and ‘train_y_std’？