Closed LukeAI closed 4 years ago
@LukeAI
yolov4 is larger than yolov3-spp.
NMS is on CPU.
Thanks for your interests!
@wang-xinyu I found yolov3 with 416 dimension much faster than yolov4 with 416 dimension running on C++ TensorRT implementation. Is this an expected output because of unoptimized mish activation function or I should get faster results for yolov4?
@lavinan26 are you using the newest codes? What's the specific latency did you get for yolov4 and yolov3? and what's the GPU are you using?
yolov3 is expected to be slightly faster than yolov4 at the same resolution. but not much. would be good to know your results?
@LukeAI For the yolov4 FPS test result, you can refer to https://github.com/AlexeyAB/darknet/pull/5453#issuecomment-624116856,
On my machine, GTX1080, yolov4 608x608, I got 20fps in darknet, and got about 40fps in my tensorrt implementation.
@wang-xinyu @LukeAI I am just using a virtual machine with Tesla K80 GPU. The average latency I get for yolov4 416x416 with FP16 precision is 71 ms (14 FPS) and for yolov3 with same dimensions and precision Is 58 ms (17.3 FPS).
@LukeAI I just rechecked the graph in yolov4 paper and found that for same dimension, yolov4 is supposed to be a little bit slower. Thanks.
why is yolov4 slower than yolov3-spp in this repo?
Is the NMS being done on the cpu, rather than the GPU?
(thanks for this really interesting and educational repo.!)