NOTE that apply_nms is replaced with the torchvision nms function. This is incomplete because nms doesn't come with the pre- and post-top_k filtering in the original apply_nms. The eval_predcls constrained mR@50 I have reproduced after training is 18.88 (a little less than 19.3) but I suspect the pre-k and post-k could be one reason. If I have time down the road I will try to replicate that function exactly.
NOTE that apply_nms is replaced with the torchvision nms function. This is incomplete because nms doesn't come with the pre- and post-top_k filtering in the original apply_nms. The eval_predcls constrained mR@50 I have reproduced after training is 18.88 (a little less than 19.3) but I suspect the pre-k and post-k could be one reason. If I have time down the road I will try to replicate that function exactly.