install NVIDIA driver
install driver by apt-get (ref),with a VPN to turn over the GFW
sudo apt-get purge nvidia*
sudo add-apt-repository ppa:graphics-drivers
sudo apt-get update
sudo apt-cache search nvidia
sudo apt-get install nvidia-396
test driver
reboot
lsmod | grep nvidia
lsmod | grep nouveau # no output
install cuda9.0
2. Install CUDA 9.0 (ref)
The CUDA runfile installer can be downloaded from NVIDIA's websie, or using wget in case you can't find it easily on NVIDIA:
cd
wget https://developer.nvidia.com/cuda-90-download-archive?target_os=Linux&target_arch=x86_64&target_distro=Ubuntu&target_version=1604&target_type=runfilelocal
chmod a+x cuda_*
./cuda_9.0.176_384.81_linux-run
Follow the command-line prompts
finally,install patch as above
Please make sure that
- PATH includes /usr/local/cuda-9.0/bin
- LD_LIBRARY_PATH includes /usr/local/cuda-9.0/lib64, or, add /usr/local/cuda-9.0/lib64 to /etc/ld.so.conf and run ldconfig as root
add the script to ~/.bashrc
export PATH=$PATH:/usr/local/cuda-9.0/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda-9.0/lib64
To uninstall the CUDA Toolkit, run the uninstall script in /usr/local/cuda-9.0/bin
Install cuDNN 7.0
The recommended way for installing cuDNN is by Installing from a Tar File
- Download the "cuDNN v7.0.5 Library for Linux"
tgzfile (need to register for an Nvidia account).
- your CUDA directory path is referred to as
/usr/local/cuda/ - your cuDNN download path is referred to as
<cudnnpath>
- Navigate to your <cudnnpath> directory containing the cuDNN Tar file.
4, Unzip the cuDNN package.
tar -xzvf cudnn-9.0-linux-x64-v7.tgz
- Copy the following files into the CUDA Toolkit directory.
sudo cp cuda/include/cudnn.h /usr/local/cuda/include
sudo cp cuda/lib64/libcudnn* /usr/local/cuda/lib64
sudo chmod a+r /usr/local/cuda/include/cudnn.h /usr/local/cuda/lib64/libcudnn*
install tensorflow
- install anaconda and create env
conda create -n tensorflow_gpu
source activate tensorflow_gpu
- use pip to get the latest version of tensorflow-gpu
pip install tensorflow-gpu
3.verify
from tensorflow.python.client import device_lib
device_lib.list_local_devices()
