onnx detect about ultralytics HOT 2 OPEN

👋 Hello @2516455367, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.

Install

Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

Environments

YOLOv8 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

from ultralytics.

@2516455367 hello! Thanks for your willingness to contribute with a PR! Here's a simple demo outline for using a YOLOv8 ONNX model in Python, Go, and C++. For full examples, you might need to adapt the code based on your specific setup and environment.

Python

from ultralytics import YOLO

# Load the ONNX model
model = YOLO("yolov8n.onnx")

# Run inference
results = model("path/to/image.jpg")
print(results.pandas().xyxy[0])  # print predictions

C++

You'll need to use an ONNX Runtime C++ API. Here's a very basic snippet:

#include <onnxruntime_cxx_api.h>

int main() {
    Ort::Env env(ORT_LOGGING_LEVEL_WARNING, "test");
    Ort::SessionOptions session_options;
    session_options.SetIntraOpNumThreads(1);

    Ort::Session session(env, "yolov8n.onnx", session_options);

    // Add code to prepare input tensor and run session
    // Print outputs

    return 0;
}

Go

For Go, you'll need a Go binding for ONNX Runtime. Here's a pseudo-code:

package main

import (
    "github.com/owulveryck/onnx-go"
    "gonum.org/v1/gonum/mat"
)

func main() {
    backend := onnx.NewTensorRTBackend()
    model := onnx.NewModel(backend)
    
    // Load the model
    model.UnmarshalBinary("yolov8n.onnx")

    // Prepare input and run
    // Print the output
}

These are just starting points. You'll need to handle data preprocessing and output parsing according to the YOLOv8 model's requirements. Good luck with your PR! 🚀

from ultralytics.