https://github.com/we0091234/yolov8-tensorrt

yolov8 tensorrt 加速
https://github.com/we0091234/yolov8-tensorrt

pytorch tensorrt yolov8 yolov8-tensorrt

Last synced: 4 days ago
JSON representation

yolov8 tensorrt 加速

• Host: GitHub
• URL: https://github.com/we0091234/yolov8-tensorrt
• Owner: we0091234
• Created: 2023-01-06T09:19:02.000Z (almost 2 years ago)
• Default Branch: master
• Last Pushed: 2023-01-16T07:56:39.000Z (almost 2 years ago)
• Last Synced: 2024-08-02T01:20:01.640Z (3 months ago)
• Topics: pytorch, tensorrt, yolov8, yolov8-tensorrt
• Language: C++
• Homepage:
• Size: 13.2 MB
• Stars: 49
• Watchers: 1
• Forks: 10
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-yolo-object-detection - we0091234/yolov8-tensorrt - tensorrt?style=social"/> : yolov8 tensorrt 加速. (Lighter and Deployment Frameworks)
• awesome-yolo-object-detection - we0091234/yolov8-tensorrt - tensorrt?style=social"/> : yolov8 tensorrt 加速. (Lighter and Deployment Frameworks)
• awesome-cuda-and-hpc - we0091234/yolov8-tensorrt - tensorrt?style=social"/> : yolov8 tensorrt 加速. (Applications)
• awesome-cuda-and-hpc - we0091234/yolov8-tensorrt - tensorrt?style=social"/> : yolov8 tensorrt 加速. (Applications)

README

        
# yolov8 TensorRT

The Pytorch implementation is [https://github.com/ultralytics/ultralytics](https://github.com/ultralytics/ultralytics).

## onnx model

step1. install yolov8

```

 pip install ultralytics

```

step2. download yolov8 model from [https://github.com/ultralytics/assets/releases](https://github.com/ultralytics/assets/releases)

step3. convert yolov8 model  to onnx

```

yolo mode=export model=yolov8n.pt format=onnx simplify=True

```

or you can download  onnx model from here [z16b](https://pan.baidu.com/s/1KzJ3-15LrPnWjavnqeWsTg)

## How to Run, yolov8n as example

1. Modify the tensorrt cuda opencv path in CMakeLists.txt

   ```

   #cuda 

   include_directories(/mnt/Gu/softWare/cuda-11.0/targets/x86_64-linux/include)

   link_directories(/mnt/Gu/softWare/cuda-11.0/targets/x86_64-linux/lib)

   #tensorrt 

   include_directories(/mnt/Gpan/tensorRT/TensorRT-8.2.0.6/include/)

   link_directories(/mnt/Gpan/tensorRT/TensorRT-8.2.0.6/lib/)

   ```

2. build

   ```

   1. mkdir build

   2. cd build

   3. cmake ..

   4. make

   ```

3. onnx  to tensorrt model

   ```

   ./onnx2trt/onnx2trt  ../onnx_model/yolov8n.onnx ./yolov8n.trt  1

   ```

4. inference

   ```

   ./yolov8 ./yolov8n.trt  ../samples/

   ```

   The results are saved in the build folder.

   ![image](result/zidane.jpg)

## contact

Tencent qq group:  871797331