chenyuntc / simple-faster-rcnn-pytorch

A simplified implemention of Faster R-CNN that replicate performance from origin paper
Other
3.97k stars 1.14k forks source link

nms #229

Open nana33 opened 3 years ago

nana33 commented 3 years ago

I think that the code does not use nms to discard the repetitive bboxes, which reduces mAP. But in the demo, nms is utilized before visualizing predicted bboxes. I want to know if it is reasonable to use nms before calculating mAP ?