YOLOv7快速复现 demo演示YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object

Posted 2022-07-15 CV-杨帆

2022年7月6日周三 YOLOv7发布

目录

• 0 相关资源
• 1 论文简叙
• • 1.1 Title
  • 1.2 Abstract
• 2 Hugging Face
• 3 GPU平台
• 4 yolov7安装
• 5 demo测试

0 相关资源

b站视频：https://www.bilibili.com/video/BV1VB4y1v7kV/
官网链接：https://github.com/WongKinYiu/yolov7
相关博客：
YOLOv7上线：无需预训练，5-160 FPS内超越所有目标检测器
【论文解读】YOLOR: 2021年YOLO系列目标检测的最强王者

Hugging Face：https://huggingface.co/spaces/akhaliq/yolov7

1 论文简叙

1.1 Title

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object
detectors

1.2 Abstract

YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100.

YOLOv7-E6 object detector (56 FPS V100, 55.9% AP) outperforms both transformer-based detector SWINL Cascade-Mask R-CNN (9.2 FPS A100, 53.9% AP) by 509% in speed and 2% in accuracy,

and convolutionalbased detector ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS A100, 55.2% AP) by 551% in speed and 0.7% AP in accuracy,

as well as YOLOv7 outperforms: YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, DETR, Deformable DETR, DINO-5scale-R50, ViT-Adapter-B and many other object detectors in speed and accuracy.

Moreover, we train YOLOv7 only on MS COCO dataset from scratch without using any other datasets or pre-trained weights. Source code is released in https:// github.com/WongKinYiu/yolov7.

2 Hugging Face

yolov7 Hugging Face ：https://huggingface.co/spaces/akhaliq/yolov7

3 GPU平台

我使用的是极链AI云平台：https://cloud.videojj.com/auth/register?inviter=18452&activityChannel=student_invite

选择镜像：

4 yolov7安装

cd /home
git clone https://gitee.com/YFwinston/yolov7.git
cd yolov7
pip install -r requirements.txt 
pip install opencv-python-headless==4.1.2.30

5 demo测试

注意：第一次运行，yolov7.pt的下载速度比较慢，可以先在本地下载，然后上传平台，

cd /home/yolov7
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/1.jpg

只要人的检测结果

cd /home/yolov7
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/1.jpg --classes 0