NVIDIA相关：
- NVIDIA CUDA镜像的docker hub：https://hub.docker.com/r/nvidia/cuda/tags?page=\&page_size=\&ordering=\&name=12.4.1
- NVIDIA 构建的Tensorflow镜像包：https://docs.nvidia.com/deeplearning/frameworks/tensorflow-release-notes/overview.html
- CUDA ToolKits 下载地址：https://developer.nvidia.com/cuda-toolkit-archive
Tensorflow相关：
- Tensorflow官网安装地址：https://www.tensorflow.org/install/pip?hl=zh-cn
- Tensorflow官网gpu支持：https://www.tensorflow.org/install/gpu?hl=zh-cn#software_requirements
- Tensorflow docker hub地址：https://hub.docker.com/r/tensorflow/tensorflow/tags?page=\&page_size=\&ordering=\&name=
- Tensorflow Github地址：https://github.com/tensorflow/tensorflow/blob/v2.15.0/tensorflow/tools/ci_build/README.md
TensorRT相关：
- 安装指南：https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html
- TensorRT下载地址：https://developer.nvidia.com/tensorrt/download
- TensorRT 报错TF-TRT Warning: Could not find TensorRT解决：https://blog.csdn.net/weixin_45710350/article/details/140232873?utm_medium=distribute.pc_relevant.none-task-blog-2~default~baidujs_baidulandingword\~default-0-140232873-blog-132561059.235、 https://github.com/tensorflow/tensorflow/issues/61986
- TensorRT pip源地址：https://pypi.org/project/tensorrt-cu12/#history、https://pypi.org/simple/tensorrt/
TensorBoard相关
python相关
- miniconda的安装包地址（里面内置了不同版本的python）：https://repo.anaconda.com/miniconda/
- 官方源：https://pypi.org/
- 增加国内镜像源 conda/pip：
# conda/pip增加国内源 RUN conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/ && \ conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/ && \ conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/ && \ conda config --set show_channel_urls yes && \ pip config set global.index-url http://mirrors.aliyun.com/pypi/simple/ && \ pip config set global.trusted-host mirrors.aliyun.com