YOLOv8-TensorRT

YOLOv8 using TensorRT accelerate !

Preprocessed ONNX model

You can dowload the onnx model which is pretrained by https://github.com/ultralytics .

YOLOv8-n

YOLOv8-s

YOLOv8-m

YOLOv8-l

YOLOv8-x

Build TensorRT engine by ONNX

1. By TensorRT Python api

You can export TensorRT engine by build.py .

Usage:

python3 build.py --onnx yolov8s_nms.onnx --device cuda:0 --fp16

Description of all arguments

• --onnx : The ONNX model you download.
• --device : The CUDA deivce you export engine .
• --half : Whether to export half-precision model.

2. By trtexec tools

You can export TensorRT engine by trtexec tools.

Usage:

/usr/src/tensorrt/bin/trtexec --onnx=yolov8s_nms.onnx --saveEngine=yolov8s_nms.engine --fp16

If you installed TensorRT by a debian package, then the installation path of trtexec is /usr/src/tensorrt/bin/trtexec

If you installed TensorRT by a tar package, then the installation path of trtexec is under the bin folder in the path you decompressed

Infer images by the engine which you export

You can infer images with the engine by infer.py .

Usage:

python3 infer.py --engine yolov8s_nms.engine --imgs data --show --out-dir outputs --device cuda:0

Description of all arguments

• --engine : The Engine you export.

• --imgs : The images path you want to detect.

• --show : Whether to show detection results.

• --out-dir : Where to save detection results images. It will not work when use --show flag.

• --device : The CUDA deivce you use.

• --profile : Profile the TensorRT engine.

If you want to profile the TensorRT engine:

Usage:

python3 infer.py --engine yolov8s_nms.engine --profile