# Introduction to YOLOv10: Real-time Object Detection
## Abstract
Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the architectural designs, optimization objectives, data augmentation strategies, and others for YOLOs, achieving notable progress. However, the reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs and adversely impacts the inference latency. Besides, the design of various components in YOLOs lacks the comprehensive and thorough inspection, resulting in noticeable computational redundancy and limiting the model's capability. It renders the suboptimal efficiency, along with considerable potential for performance improvements. In this work, we aim to further advance the performance-efficiency boundary of YOLOs from both the post-processing and the model architecture. To this end, we first present the consistent dual assignments for NMS-free training of YOLOs, which brings the competitive performance and low inference latency simultaneously. Moreover, we introduce the holistic efficiency-accuracy driven model design strategy for YOLOs. We comprehensively optimize various components of YOLOs from both the efficiency and accuracy perspectives, which greatly reduces the computational overhead and enhances the capability. The outcome of our effort is a new generation of YOLO series for real-time end-to-end object detection, dubbed YOLOv10. Extensive experiments show that YOLOv10 achieves the state-of-the-art performance and efficiency across various model scales. For example, our YOLOv10-S is 1.8$\times$ faster than RT-DETR-R18 under the similar AP on COCO, meanwhile enjoying 2.8$\times$ smaller number of parameters and FLOPs. Compared with YOLOv9-C, YOLOv10-B has 46\% less latency and 25\% fewer parameters for the same performance.
![image](https://github.com/denghv/Vegetables_Fruit_Detection/assets/137135014/a41a0866-c716-40d0-9d4d-e1f41d01aba7)
##
## Citation
```python
@article{wang2024yolov10,
title={YOLOv10: Real-Time End-to-End Object Detection},
author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
journal={arXiv preprint arXiv:2405.14458},
year={2024}
}
```
# Using YOLOv10 for Real-time Vegetables & Fruit Detection
## Introduction
This is our Machine Learning's project. At the beginning, we used YOLOv8 with fine-tuning technologies to build our model but the output we gained is not highly accurate. So we decided to use YOLOv10 instead and its performance was much better than we expected.
## About dataset
We built our own dataset by manual-annotation and data-argumention with Roboflow. You are welcomed to use our dataset by following this link: https://universe.roboflow.com/ai-projects-rulo4/vegetables-fruit-detection/dataset/2
Our dataset has more than 700 images including five classes of vegetables and fruit: banana, apple, watermelon, chili, carrot.
## Installation
Clone project
```
git clone https://github.com/denghv/Vegetables_Fruit_Detection.git
```
```conda``` virtual environment is recommended.
```python
conda create -n yolov10 python=3.9
conda activate yolov10
pip install -r requirements.txt
pip install -e .
```
## Demo
```
--webcam_inference.py
```
Thanks for great implementations!
生活家小毛.
- 粉丝: 6050
- 资源: 9295
最新资源
- 盐城市2005-2024年近20年历史气象数据下载
- 泰州市2005-2024年近20年历史气象数据下载
- 深度强化学习电气工程复现文章,适合小白学习 关键词:能量管理 深度学习 强化学习 深度强化学习 能源系统 优化调度 编程语言:python平台 主题:用于能源系统优化调度的深度强化学习算法的性能比较
- 开源基于51单片机的多功能智能闹钟设计
- C#连接sap NCO组件 X64版
- 1.电力系统短路故障引起电压暂降 2.不对称短路故障分析 包括:共两份自编word+相应matlab模型 1.短路故障的发生频次以及不同类型短路故障严重程度,本文选取三类典型的不对称短路展开研究
- python基础知识源码,涵盖全面,有源码有教程,200多个源文件,规范工整,打牢基础,Python入门基础课必备
- 医护人员检测23-YOLOv8数据集合集.rar
- 面向能源系统深度强化学习算法的性能比较 最优调度(代码)
- 2025元旦和新年春节倒计时
- 线控转向系统路感模拟及路感力矩控制 通过参数拟合设计线控转向路感模拟算法,在simulink中建立仿真模型 模型建立后,验证双纽线工况和中心区工况的路感力矩 通过PID,模
- ks滑块加密算法与源代码
- shap分析代码案例,多个机器学习模型+shap解释性分析的案例,做好的多个模型和完整的shap分析拿去直接运行,含模型之间的比较评估 类别预测和数值预测的案例代码都有,类别预测用到的6个模型是(
- 医疗骨折摄像检测29-YOLO(v5至v9)、COCO、CreateML、Darknet、Paligemma数据集合集.rar
- 基于FPGA的CAN通信,FPGA驱动SJA1000T芯片代码,实现标准帧与扩展帧的通信驱动,已上板调通 品牌型号 CAN SJA1000T 与世面上的不同,代码不是SJA1000T芯片代码,而是驱
- 捕鱼达人1.exe捕鱼达人2.exe捕鱼达人3.exe
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈