https://github.com/xiaohaoo/yolo_tensorrt
Deploy the YOLOv8 model for inference using OpenCV and TensorRT in C/C++.
https://github.com/xiaohaoo/yolo_tensorrt
c cuda opencv tensorrt yolov8
Last synced: 11 months ago
JSON representation
Deploy the YOLOv8 model for inference using OpenCV and TensorRT in C/C++.
- Host: GitHub
- URL: https://github.com/xiaohaoo/yolo_tensorrt
- Owner: xiaohaoo
- Created: 2023-07-10T19:23:32.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-07-16T21:55:54.000Z (almost 3 years ago)
- Last Synced: 2025-04-14T20:22:52.082Z (about 1 year ago)
- Topics: c, cuda, opencv, tensorrt, yolov8
- Language: C++
- Homepage:
- Size: 29.4 MB
- Stars: 4
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Yolov8 TensorRT
Deploy the [YOLOV8](https://github.com/ultralytics/ultralytics) model for object detection using OpenCV and [TensorRT](https://github.com/NVIDIA/TensorRT).
## Overview
## Dependencies
- CMAKE
- Microsoft Visual Studio
- CUDA: Only [download](https://github.com/xiaohaoo/Yolo_TensorRT/releases/download/v1.0.0/lib.zip) the required runtime library.
- OpenCV: Only [download](https://github.com/xiaohaoo/Yolo_TensorRT/releases/download/v1.0.0/lib.zip) the required runtime library.
## Installation
```bash
git clone git@github.com:xiaohaoo/Yolo_TensorRT.git
cd Yolo_TensorRT
cmake -DCMAKE_BUILD_TYPE:STRING=Release -B build -G "Visual Studio 16 2019" -A x64
cmake --build build --config Release --target install -j 22
# run app
cd build\output
.\yolo.exe
```