Windows 10
cuda 10.0
cudnn 7.5
TensorRT 5.1.5.0
caffe yolov3
I created the int8 engine file for yolov3 detection and it cost about 90ms one image, that is 60ms on GTX 960.What is the reason?
Hi,
Can you share your code/script and model file so I can try to reproduce this or further debug?
Thanks