赞
踩
- conda create -n yolov10=3.9
- conda activate yolov10
conda install pytorch torchvision torchaudio cpuonly -c pytorch
GitHub - THU-MIG/yolov10: YOLOv10: Real-Time End-to-End Object Detection
- pip install -r requirements.txt
- pip install -e .
datasets------images----train
-----val
------labels------train
------val
里面内容为
- #path: ../datasets/mydata # dataset root dir
- #path: home/hexuran/ultralytics-main/datasets/CMD
- path: ../datasets # dataset root dir
- train: images/train
- val: images/val
- #test: # test images (optional)
-
-
- nc: 5
- names: ['binary1','binary2','binary3','binary4','binary5']
nc:种类
names:按打标签的顺序依次填入
yolo detect train data=mydata.yaml model=yolov10n.pt epochs=10 imgsz=640
参数解释:
yolo detect train:表示进行目标检测的训练
data=mydata.yaml:指定你自己数据集yaml文件
model=yolov10n.pt:指定下载yolov10的预训练权重文件
epochs=10:设置训练轮次,可以先设置小一点,先看看结果如何
imgsz=640:设置图片长度
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。