Open fused-byte opened 4 years ago
Time is the same, because python just use C++ library for detection and post-processing.
Does detection depend upon the input resolution of the image? My network is trained on 640x192. I asked this question because the Pytorch implementation of YOLOv3 is doing detection in 26ms while the darknet based yolo-tiny is doing detection in 47ms.
Yes, it does. Such big difference is strange, did you compiled Darknet with CUDA=1, OPENCV=1, CUDNN=1 in makefile?
Yes. I checked my GPU usage as well.
@fused-byte Do you solved this issue? I have 37 FPS
with darknet binary run and about 30FPS
when ruining code from python. Maybe problem is in my python code which uses opencv video reader/decoder not compiled for GPU?
Is darknet.py optimised to run in minimal time? Is it slower than the usual detection time?