How to use tensorRT in Yolov5?

Question

I want to optimize my trained model in Yolov5 using tensorRT. But am unable to find a proper way of doing so.Can any body tell show me how to do so?

score 1 · Answer 1 · answered Mar 20 '21 at 13:15

1

You can refer to this repository for Yolo-V5. It has a section dedicated to tensorrt deployment.

You can also learn about tensorrt inference using C++ and Python

answered Mar 20 '21 at 13:15

Jitesh Malipeddi

score 0 · Answer 2 · edited Dec 17 '22 at 09:53

0

would you try:

python benchmarks.py --weights yolov5s.pt --imgsz 640 --device 0

edited Dec 17 '22 at 09:53

answered Dec 17 '22 at 09:01

score 0 · Answer 3 · answered Dec 18 '22 at 09:12

0

Benchmark is used for exporting and evaluating ALL export frameworks. Even the ones that has nothing to do with TenosrRT. Use:

python export.py --weights yolov5s.pt --include engine

for exporting your Yolov5 model to TensorRT

answered Dec 18 '22 at 09:12

Mike B

3 Answers3