Darkflow uses slim BN. For now, it passes "is_training" parameter to slim BN as a tensor.
This introduce many control flow ops, which seriously limited the performance.
My tests shows that, if passing a constant "is_training", we can get 12.7% performance improvement on NVIDIA P100 and 40% performance improvement on Intel Xeon Platinum 8180.
(cfg/yolo-voc.cfg, Pascal VOC2007, BS 16)
Darkflow uses slim BN. For now, it passes "is_training" parameter to slim BN as a tensor. This introduce many control flow ops, which seriously limited the performance. My tests shows that, if passing a constant "is_training", we can get 12.7% performance improvement on NVIDIA P100 and 40% performance improvement on Intel Xeon Platinum 8180. (cfg/yolo-voc.cfg, Pascal VOC2007, BS 16)