【yolov8.1超简单环境搭建、标注、训练、转onnx、转输出维度】https://www.bilibili.com/video/BV1Mu411F7MD?vd_source=0aeb782d0b9c2e6b0e0cdea3e2121eba

4.创建python环境

conda create -n yolo python==3.8

查看现存环境

conda env list

激活环境

conda activate yolo

激活失败

onda init cmd.exe

删除环境

conda eny remove -n yolo

pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

1.显卡驱动查看
nvidia-smi

2.yolo源码与模型
https://hub.nuaa.cf/ultralytics/ultralytics
https://github.com/ultralytics/ultralytics

3.anaconda
https://www.anaconda.com/download
https://repo.anaconda.com/miniconda/Miniconda3-latest-Windows-x86_64.exe
环境变量：
C:\ProgramData\miniconda3
C:\ProgramData\miniconda3\Scripts
C:\ProgramData\miniconda3\Library\bin

4.创建python环境
conda create -n yolo python==3.8
查看现有环境
conda env list
激活环境
conda activate yolo
激活失败
conda init cmd.exe
删除环境
conda env remove -n yolo

5.安装库
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
pip install ultralytics==8.1 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnx -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnxsim -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnxruntime -i https://pypi.tuna.tsinghua.edu.cn/simple


修改输出维度
gitub镜像下载地址:https://hub.nuaa.cf/shouxieai/infer
python v8trans.py best.onnx

推理检测
yolo predict model=yolov8n.pt source=4.png


yolo标注转换工具(30元)
微信:PUSHEBX

需要C#、易语言yolo调用框架可联系up，全网最强，没有之一

验证：

yolo task=detect mode=predict model=yolov8n.pt source=E:/my_project/yolov8_project/ultralytics-main/ultralytics/assets/bus.jpg imgsz=640 show=True save=True

环境配置参考如下链接：

Win11+Anaconda+Pycharm+Yolov8开发环境搭建与检测验证_conda install ultralytics-CSDN博客