1.cudnn 安装
师兄没有在node3装cudnn,于是重新装了一遍.版本查看:
cat /usr/local/cuda/version.txt
cat /usr/local/cuda/include/cudnn.h | grep CUDNN_MAJOR -A 2
现在装的是cuda8.0,cudnn6.0
安装过程
官网下载 cudnn-8.0-linux-x64-v6.0.tgz
解压到名为cuda的文件夹
tar zxvf cudnn-8.0-linux-x64-v6.0_1.tgz cuda
复制文件
cd cuda/include
sudo cp *.h /usr/local/cuda/include/
cd cuda/lib64
sudo cp libcudnn* /usr/local/cuda/lib64/
最后终端运行
chmod a+r /usr/local/cuda/include/cudnn.h /usr/local/cuda/lib64/libcudnn*
2.tensorflow安装
sudo apt-get install libcupti-dev
conda create -n tensorflow pip python=2.7
source activate tensorflow
pip install --ignore-installed --upgrade https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-1.3.0-cp27-none-linux_x86_64.whl
