当前位置:网站首页>Simple implementation of YOLOv7 pre-training model deployment based on OpenVINO toolkit
Simple implementation of YOLOv7 pre-training model deployment based on OpenVINO toolkit
2022-08-05 01:58:00 【Intel Edge Computing Community】
●一、YOLOv7简介●
官方版的YOLOv7相同体量下比YOLOv5精度更高,速度快120%(FPS),比 YOLOX 快180%(FPS),比 Dual-Swin-T 快1200%(FPS),比 ConvNext 快550%(FPS),比 SWIN-L快500%(FPS).在5FPS到160FPS的范围内,无论是速度或是精度,YOLOv7都超过了目前已知的检测器,并且在GPU V100上进行测试, 精度为56.8% AP的模型可达到30 FPS(batch=1)以上的检测速率,与此同时,这是目前唯一一款在如此高精度下仍能超过30FPS的检测器.
论文链接:https://arxiv.org/abs/2207.02696
代码链接:https://github.com/WongKinYiu/yolov7
●二、预训练模型准备●
模型权重下载
可以从官方githubThe link provided in the repository is based on the downloadCOCO数据集的YOLOv7预训练模型权重.
Model | Test Size | APtest | AP50test | AP75test | batch 1 fps | batch 32 average time |
YOLOv7 | 640 | 51.4% | 69.7% | 55.9% | 161 fps | 2.8 ms |
YOLOv7-x | 640 | 53.1% | 71.2% | 57.8% | 114 fps | 4.3ms |
YOLOv7-W6 | 1280 | 54.9% | 72.6% | 60.1% | 84 fps | 7.6 ms |
YOLOv7-E6 | 1280 | 56.0% | 73.5% | 61.2% | 56 fps | 12.3 ms |
YOLOv7-D6 | 1280 | 56.6% | 74.0% | 61.8% | 44 fps | 15.0 ms |
YOLOv7-E6E | 1280 | 56.8% | 74.4% | 62.1% | 36 fps | 18.7 ms |
模型转换
可以从官方githubThe link provided in the repository is based on the downloadCOCO数据集的YOLOv7预训练模型权重.
# 下载YOLOv7官方仓库:
$ git clone [email protected]:WongKinYiu/yolov7.git
$ cd yolov7/models
$ python export.py --weights yolov7.pt
●三、模型部署●
通过Netron工具打开yolov7.onnx文件后可以看到,The official pre-trained modeloutputThe section contains the prediction results of the three feature layers,Therefore, it needs to be based on the prior box of each layer(anchor)After adjusting the output data,再进行堆叠.
由于YOLOv7The model pre- and post-processing basic sumsYOLOv5一致,Most data processing modules can be reused directly.话不多说直接上代码:
●六、运行结果●
运行python示例后,会在本地dataGenerate code in the directorybounding box以及label的图片,Here we use the horse data attached to the official repository for testing,具体结果如下:
# 运行代码
$ python YOLOV7.py -i horse.jpg -m yolov7.onnx
Github地址:
https://github.com/OpenVINO-dev-contest/YOLOv7_OpenVINO
--END--
边栏推荐
- JZ搜索引擎solr研究-从数据库创建索引
- .Net C# Console Create a window using Win32 API
- 测试工作这么难找吗?今年32,失业2个月,大龄测试工程师接下来该拿什么养家?
- 10年测试经验,在35岁的生理年龄面前,一文不值
- 树形查找(二叉查找树)
- 超越YOLO5-Face | YOLO-FaceV2正式开源Trick+学术点拉满
- iNFTnews | 对体育行业和球迷来说,NFT可以带来什么?
- How to simply implement the quantization and compression of the model based on the OpenVINO POT tool
- day14--postman interface test
- 程序员失眠时的数羊列表 | 每日趣闻
猜你喜欢
随机推荐
Domain Driven Design - MDD
How to simply implement the quantization and compression of the model based on the OpenVINO POT tool
Exploding the circle of friends, Alibaba produced billion-level concurrent design quick notes are too fragrant
【TA-霜狼_may-《百人计划》】图形4.3 实时阴影介绍
Day Fourteen & Postman
[Machine Learning] 21-day Challenge Study Notes (2)
【MySQL系列】- LIKE查询 以%开头一定会让索引失效吗
Chapter 09 Use of Performance Analysis Tools [2. Index and Tuning] [MySQL Advanced]
用@Mapper查询oracle的分区情况报错
How to deal with your own shame
第十四天&postman
DDOS攻击真的是无解吗?不!
跨域解决方案
.Net C# Console Create a window using Win32 API
Flink 1.15.1 集群搭建(StandaloneSession)
《.NET物联网从零开始》系列
KingbaseES V8 GIS数据迁移方案(2. Kingbase GIS能力介绍)
iNFTnews | 对体育行业和球迷来说,NFT可以带来什么?
【Unity入门计划】2D游戏中遮挡问题的处理方法&伪透视
如何模拟后台API调用场景,很细!