I am trying to speed up SSD family of object detectors in PyTorch. Most implementations use a CUDA-based non-maximum suppression (NMS) for efficiency, but the implementation (from Fast/er R-CNN) is image-based. If we have batch size larger than 1, the post processing & NMS becomes the bottleneck, as…

hello there, using the awesome idea from torchvision “batched_nms”, this following code can decode for several images / several classes at once, it works because batched_nms offsets boxes according to their category, so you never perform a wrong suppression. I also tried to accelerate box encoding…

Batch non-maximum suppression on the GPU

vision

Tony-Y January 9, 2019, 8:34am 7

This comment is helpful.