YOLOv10x Open-Source Object Detection Model - Free Deployment, Efficient Inference, and High Detection Accuracy!

Home

Yolov10x

Developed by onnx-community

YOLOv10 is a real-time end-to-end object detection model with efficient inference speed and high detection accuracy.

Object Detection

Transformers

#Real-time object detection #End-to-end inference #High-precision recognition

Downloads 23

Release Time : 5/24/2024

Model Overview

YOLOv10 is an object detection model based on the YOLO series, focusing on real-time performance and end-to-end capabilities, suitable for various object detection tasks.

Model Features

Real-time end-to-end detection

The model supports real-time object detection with end-to-end processing capabilities, suitable for applications requiring quick responses.

High-precision detection

While maintaining real-time performance, the model provides high object detection accuracy, capable of accurately identifying multiple objects.

ONNX support

The model is provided in ONNX format, facilitating deployment and usage across different platforms and frameworks.

Model Capabilities

Object detection

Real-time inference

Multi-object recognition

Use Cases

Smart surveillance

Traffic monitoring

Used for real-time detection of vehicles and pedestrians on roads, aiding traffic management and safety monitoring.

Capable of accurately identifying vehicles and pedestrians with confidence levels exceeding 90%.

Autonomous driving

Environmental perception

Used in autonomous driving systems to detect objects in the surrounding environment, such as vehicles, pedestrians, and obstacles.

Capable of real-time detection of multiple objects, providing reliable environmental perception data for autonomous driving.

🚀 YOLOv10: Real-Time End-to-End Object Detection

This project provides ONNX weights for the YOLOv10 object detection model from https://github.com/THU-MIG/yolov10, enabling real-time end - to - end object detection.

Trade - off Visualizations

Latency - accuracy trade - offs	Size - accuracy trade - offs

🚀 Quick Start

📦 Installation

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @xenova/transformers

💻 Usage Examples

Basic Usage

import { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';

// Load model
const model = await AutoModel.from_pretrained('onnx-community/yolov10x', {
    // quantized: false,    // (Optional) Use unquantized version.
})

// Load processor
const processor = await AutoProcessor.from_pretrained('onnx-community/yolov10x');

// Read image and run processor
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/city-streets.jpg';
const image = await RawImage.read(url);
const { pixel_values, reshaped_input_sizes } = await processor(image);

// Run object detection
const { output0 } = await model({ images: pixel_values });
const predictions = output0.tolist()[0];

const threshold = 0.5;
const [newHeight, newWidth] = reshaped_input_sizes[0]; // Reshaped height and width
const [xs, ys] = [image.width / newWidth, image.height / newHeight]; // x and y resize scales
for (const [xmin, ymin, xmax, ymax, score, id] of predictions) {
    if (score < threshold) continue;

    // Convert to original image coordinates
    const bbox = [xmin * xs, ymin * ys, xmax * xs, ymax * ys].map(x => x.toFixed(2)).join(', ');
    console.log(`Found "${model.config.id2label[id]}" at [${bbox}] with score ${score.toFixed(2)}.`);
}
// Found "car" at [559.30, 472.72, 799.58, 598.15] with score 0.95.
// Found "car" at [221.91, 422.56, 498.09, 521.85] with score 0.94.
// Found "bicycle" at [1.59, 646.99, 137.72, 730.35] with score 0.92.
// Found "bicycle" at [561.25, 593.65, 695.01, 671.73] with score 0.91.
// Found "person" at [687.74, 324.93, 739.70, 415.04] with score 0.89.
// ...

📄 License

This project is licensed under the AGPL - 3.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご