Thanks for your great work! I wonder if the mAP 42.52 of dab-detr is trained via the exact config file "configs/detection/dab_detr/dab_detr_r50_8x2_50ecoco.py"?
If so, I see that you use dropout = 0.0_ in DABDetrTransformer instead of the default dropout value 0.1. Is there a performance gain by setting dropout value to 0.0?
Thanks for your great work! I wonder if the mAP 42.52 of dab-detr is trained via the exact config file "configs/detection/dab_detr/dab_detr_r50_8x2_50ecoco.py"? If so, I see that you use dropout = 0.0_ in DABDetrTransformer instead of the default dropout value 0.1. Is there a performance gain by setting dropout value to 0.0?