yolo8安装、训练
https://developer.aliyun.com/article/1352768#:~:text=%E7%AC%AC%E4%B8%80%E6%AD%A5%20%E6%89%93%E5%BC%80conda%E7%AA%97%E5%8F%A3%20%E8%BF%9B%E5%85%A5%E5%88%B0%E5%AE%89%E8%A3%85%E7%9A%84YOLOv8%E7%95%8C%E9%9D%A2%20%E7%AC%AC%E4%BA%8C%E6%AD%A5%20%E5%88%9B%E5%BB%BA%E6%96%B0%E7%9A%84%E8%99%9A%E6%8B%9F%E7%8E%AF%E5%A2%83%20%E8%BE%93%E5%85%A5%E4%B8%8B%E9%9D%A2%E5%91%BD%E4%BB%A4,conda%20create%20-n%20y8%20python%3D3.8%20%E6%98%AF%E5%90%A6%E5%AE%89%E8%A3%85%E7%8E%AF%E5%A2%83%E6%89%80%E9%9C%80%E5%9F%BA%E7%A1%80%E5%8C%85%EF%BC%8C%E8%BE%93%E5%85%A5y%E5%AE%89%E8%A3%85%E5%8D%B3%E5%8F%AF%EF%BC%8C%E5%AE%89%E8%A3%85%E5%AE%8C%E6%88%90%E5%A6%82%E4%B8%8B%E5%9B%BE
gpu版本torch torchvision安装
https://pytorch.org/ 拉下去找到图片选择配置，复制 安装命令 到anaconda安装
import torch
import torchvision
print(torch.__version__)
print(torchvision.__version__)
print(torch.cuda.is_available())
print(torch.cuda.device_count())
如果cuda不对 不是cu121之类的（cuda12.1），按照下文安装
https://blog.csdn.net/m0_74890428/article/details/130974669
小数据集试着训练
https://zhuanlan.zhihu.com/p/269587479
coco128百度盘
https://blog.csdn.net/GreenHand_Zhao/article/details/123183122
数据集 购买
https://item.taobao.com/item.htm?ft=t&id=686270772909
视频识别框闪烁
https://blog.csdn.net/weixin_56184890/article/details/123702142
https://zhuanlan.zhihu.com/p/362705124
数据集在线标注网站https://www.makesense.ai/以及分类处理，以及训练和推断
https://mp.weixin.qq.com/s?__biz=Mzg2MzkwNDM0OQ==&mid=2247486292&idx=1&sn=4a4dcd226e421f3f02aa7930f88c3a1d&chksm=ce703c66f907b5708c2e0a8120adb003e77244bc0921d16085fe768aa742a789d6459b0c8969&mpshare=1&scene=1&srcid=11224OByj7FXmeiUoa8E8A5s&sharer_shareinfo=279880e6c3641e794cfa0880eed7beba&sharer_shareinfo_first=3f11d0bf0a944ea6c679ca62abd10ec6&exportkey=n_ChQIAhIQ44%2FFTu7FUnYzVNlhwPS7HxKZAgIE97dBBAEAAAAAAM5ZLMYAnYgAAAAOpnltbLcz9gKNyK89dVj06EmINxRofU5JP8iswCueMzRGyH6BcqswkTEUA9OpqKkydrz1JMTrK9e8WYNhU4spVFlouIzlhr4t%2FWsGaUGV01FJbCRzPIWkaxShLFR5nhNqLPuW9kD%2BiLaVlB4p8sBKp4viPPPYZzoozZqHvVW1moft7JP%2Bt5HvDT65Csfs4yeb1ruXx6BlWEoxILrkna%2FGFrVq6OmM6jtD%2BowVW3Y3frIc45dcIsU%2BYdFBcTrpdg6jb8eOQiSLZ1O9836iQopBvV6EnQuzutOyJbLOy3AU9JJ1cHoKJ%2BQkQBT1qKCTBPQGMWMDDnnO1t0RhRDhyNgEQmJS&acctmode=0&pass_ticket=FXPusm2URx83nmonfbibwZBFYvEblMvNA22GpWwdzRQ7IN6ulkXr%2Fat4vXnT5qInisNsTj7UHa2%2FXSA79xi%2B4w%3D%3D&wx_header=0#rd
训练
yolo train data=../fingertipdata_split.yaml model=yolov8s.pt epochs=300 imgsz=120 batch=8 workers=0 device=0
验证集验证
yolo task=detect mode=val split=val model=runs/detect/train4/weights/best.pt data=../fingertipdata_split.yaml
测试集验证
yolo task=detect mode=val split=test model=runs/detect/train4/weights/best.pt data=../fingertipdata_split.yaml