HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

PyCharm Docs Inspect fixes (#18432)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Muhammad Rizwan Munawar 2024-12-29 23:19:05 +05:00 • committed by GitHub
parent ef16c56c99
commit f7b9009c91
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 52 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/YOLOv8-CPP-Inference/README.md
View file

@ -1,6 +1,6 @@
# YOLOv8/YOLOv5 Inference C++
This example demonstrates how to perform inference using YOLOv8 and YOLOv5 models in C++ with OpenCV's DNN API.
This example demonstrates how to perform inference using YOLOv8 and YOLOv5 models in C++ with OpenCV DNN API.
## Usage
@ -27,13 +27,13 @@ make
To export YOLOv8 models:
```commandline
```bash
yolo export model=yolov8s.pt imgsz=480,640 format=onnx opset=12
```
To export YOLOv5 models:
```commandline
```bash
python3 export.py --weights yolov5s.pt --img 480 640 --include onnx --opset 12
```
@ -45,6 +45,6 @@ yolov5s.onnx:
![image](https://user-images.githubusercontent.com/40023722/217357005-07464492-d1da-42e3-98a7-fc753f87d5e6.png)
This repository utilizes OpenCV's DNN API to run ONNX exported models of YOLOv5 and YOLOv8. In theory, it should work for YOLOv6 and YOLOv7 as well, but they have not been tested. Note that the example networks are exported with rectangular (640x480) resolutions, but any exported resolution will work. You may want to use the letterbox approach for square images, depending on your use case.
This repository utilizes OpenCV DNN API to run ONNX exported models of YOLOv5 and YOLOv8. In theory, it should work for YOLOv6 and YOLOv7 as well, but they have not been tested. Note that the example networks are exported with rectangular (640x480) resolutions, but any exported resolution will work. You may want to use the letterbox approach for square images, depending on your use case.
The **main** branch version uses Qt as a GUI wrapper. The primary focus here is the **Inference** class file, which demonstrates how to transpose YOLOv8 models to work as YOLOv5 models.