从0配置SAM

科研繁忙呀，挤出时间做一期视频

SAM展示 
https://segment-anything.com/

下载CUDA　11.8
https://developer.nvidia.com/cuda-downloads
百度网盘：
链接：https://pan.baidu.com/s/1bEbCftypWZatNmhYptZesw?pwd=dt38 
提取码：dt38
阿里云盘：
https://www.aliyundrive.com/s/mRDqMB84S86

打开cmd，输入 nvcc -V

下载CUDNN
百度网盘：
链接：https://pan.baidu.com/s/1q0dVHlvcfa442kWe2AGv7g?pwd=xytk 
提取码：xytk

粘贴到安装位置

在anaconda中创建新环境
conda create -n SAM python==3.8
conda activate SAM

下载torch2.0.0
https://pytorch.org/get-started/locally/

下载VSCODE
https://code.visualstudio.com/Download
链接：https://pan.baidu.com/s/1k4FoWHaZLsTSk9RtIBkrCA?pwd=98kk 
提取码：98kk

下载GIT
https://git-scm.com/download
https://blog.csdn.net/qq_41521682/article/details/122764915

下载SAM
https://github.com/facebookresearch/segment-anything
git clone https://github.com/facebookresearch/segment-anything.git
cd segment-anything
pip install -e .
pip install opencv-python pycocotools matplotlib onnxruntime onnx