yolov8学习总结与文件

1、https://mirrors.tuna.tsinghua.edu.cn/anaconda/miniconda/ 2、搜py38 Miniconda3-py38_22.11.1-1-Windows-x86_64.exe 52.5 MiB 2022-12-23 07:57 3、安装C:\Users\Administrator\miniconda3 4、conda环境安装 命令：conda create -n yolov8 python=3.8 conda activate opencv2 conda activate opencv4x 5 、配置国内的源 清华源：https:/mirrors.tuna.tsinghua.edu.cn/help/pypi/ pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple 激活环境： conda activate yolov8 6、安装pytorch https://pytorch.org/ 如果只需要训练，简单推理，则无需要单独安装CUDA，直接安装pytorch;如果有部署需求，例如导出TensorRT模型，则需要进行CUDA安装 # CUDA 11.6 conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.6 -c pytorch -c nvidia # CUDA 11.7 conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia # CPU Only conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 cpuonly -c pytorch 清除缓存：运行 conda clean --all 清除 Conda 的缓存，然后重试安 7\测试运行：yolo predict model=yolov8n.pt source=ultralytics/assets/bus.jpg 8\删除ultralytics pip uninstall ultralytics 9\源码安装: 在当前文件目录中 pip install -e. 查看安装情况：pip list conda activate opencv2 jupyter notebook 0.安装minconda 1. 创建conda create -n yolov8 python=3.8 2.激活conda activate opencv4x \ 3.conda install opencv=4.5.5 4.安装jupyter notebook conda activate paddlepaddl paddlepaddle python=2.7.15 pip install -U paddlepaddle 查看安装虚拟环境 conda env list 标注：安装pip install labelimg 打开: labelimg 训练：yolo task=detect mode=train model=./yolov8n.pt data=yolo-bvn.yaml epochs=30 workers=1 batch=16 预测：yolo detect predict model=runs/detect/train/weights/best.pt source=./BVN.mp4 show=True yolo detect predict model=runs/detect/train/weights/best.pt source=ultralytics/assets/aaa.jpg show=True yolo detect predict model=runs/detect/train2/weights/best.pt source=ultralytics/assets/bbb.jpg show=True yolo detect predict model=runs/detect/train2/weights/best.pt source=ultralytics/assets/ccc.jpg show=True