论文中提到，在进行inference的时候，对FPN上的box进行了过滤@qjadud1994
inference involves simply forwarding an image through the network. To improve speed, we only decode box predictions from at most 1k top-scoring predictions per FPN level, after thresholding detector confidence at 0.05. The top predictions from all levels are merged and non-maximum suppression with a
threshold of 0.5 is applied to yield the final detections.
qjadud1994
commented
5 years ago
论文中提到，在进行inference的时候，对FPN上的box进行了过滤@qjadud1994 inference involves simply forwarding an image through the network. To improve speed, we only decode box predictions from at most 1k top-scoring predictions per FPN level, after thresholding detector confidence at 0.05. The top predictions from all levels are merged and non-maximum suppression with a threshold of 0.5 is applied to yield the final detections.