Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/yinguobing/yolov5-trt
YOLO v5 inference with TensorRT (C++)
https://github.com/yinguobing/yolov5-trt
cpp cuda nvidia opencv tensorrt yolov5
Last synced: 2 days ago
JSON representation
YOLO v5 inference with TensorRT (C++)
- Host: GitHub
- URL: https://github.com/yinguobing/yolov5-trt
- Owner: yinguobing
- License: gpl-3.0
- Created: 2022-06-21T12:07:32.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-09-19T03:48:07.000Z (about 2 years ago)
- Last Synced: 2023-03-10T14:20:38.878Z (over 1 year ago)
- Topics: cpp, cuda, nvidia, opencv, tensorrt, yolov5
- Language: C++
- Homepage:
- Size: 30.3 KB
- Stars: 3
- Watchers: 1
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# yolov5-trt
Minimal code for YOLO v5 inference with TensorRT (C++).
Tutorial: https://yinguobing.com/a-quick-tutorial-for-yolov5-tensorrt-cpp-inference/
## Prerequisites
To build and run this program, the following items are required.
- a CUDA compatible GPU card
- NVIDIA driver: 470.82.01 or higher
- NVIDIA CUDA: 11.4.3
- NVIDIA cuDNN: 8.2.1
- NVIDIA TensorRT: 8.2.5.1
- OpenCV: 4.5.4
- cmake: 3.16 or higher
- an exported yolov5s TensorRT engine file
## Install
Clone this repo:
```bash
git clone https://github.com/yinguobing/yolov5-trt.git
```
## Build
Build with cmake:
```bash
cd yolov5-trt
mkdir build && cd build
cmake ..
make
```
## Run
Run inference with a sample image:
```bash
yolov5 yolov5s.engine input.jpg
```
.. then checkout the output image.
## Authors
Yin Guobing (尹国冰) - [yinguobing](https://yinguobing.com)
## License
This project is licensed under the GPL-3.0 license - see the [LICENSE](LICENSE) file for details
## Acknowledgments
* https://github.com/cyrusbehr/tensorrt-cpp-api