CUDA, NCCL, CUDNN, TensorFlow, and PyTorch

setup.sh

#!/bin/bash

# Check for CUDA and try to install.
# https://gitlab.com/nvidia/cuda/blob/ubuntu16.04/9.0/base/Dockerfile

apt-get update && apt-get install -y --no-install-recommends ca-certificates apt-transport-https gnupg-curl && \
    rm -rf /var/lib/apt/lists/* && \
    NVIDIA_GPGKEY_SUM=d1be581509378368edeec8c1eb2958702feedf3bc3d17011adbf24efacce4ab5 && \
    NVIDIA_GPGKEY_FPR=ae09fe4bbd223a84b2ccfce3f60f4b3d7fa2af80 && \
    apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/7fa2af80.pub && \
    apt-key adv --export --no-emit-version -a $NVIDIA_GPGKEY_FPR | tail -n +5 > cudasign.pub && \
    echo "$NVIDIA_GPGKEY_SUM  cudasign.pub" | sha256sum -c --strict - && rm cudasign.pub && \
    echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 /" > /etc/apt/sources.list.d/cuda.list && \
    echo "deb https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64 /" > /etc/apt/sources.list.d/nvidia-ml.list

CUDA_VERSION=9.0.176
CUDA_PKG_VERSION=9-0=$CUDA_VERSION-1

apt-get update && apt-get install -y --no-install-recommends \
        cuda-cudart-$CUDA_PKG_VERSION

curl -O http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/cuda-repo-ubuntu1604_${CUDA_VERSION}-1_amd64.deb
dpkg -i ./cuda-repo-ubuntu1604_${CUDA_VERSION}-1_amd64.deb
apt-get update && apt-get install -y --no-install-recommends cuda=${CUDA_VERSION}-1
rm ./cuda-repo-ubuntu1604_${CUDA_VERSION}-1_amd64.deb

ln -s cuda-9.0 /usr/local/cuda

echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf
echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf

PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:${PATH}
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64

# Check CUDA
nvidia-smi

# NCCL install
# https://gitlab.com/nvidia/cuda/blob/ubuntu16.04/9.0/runtime/Dockerfile

NCCL_VERSION=2.2.13

apt-get update && apt-get install -y --no-install-recommends \
        cuda-libraries-$CUDA_PKG_VERSION \
        cuda-cublas-9-0=9.0.176.3-1 \
        libnccl2=$NCCL_VERSION-1+cuda9.0


# CUDNN install
# https://gitlab.com/nvidia/cuda/blob/ubuntu16.04/9.0/runtime/cudnn7/Dockerfile

CUDNN_VERSION=7.1.4.18

apt-get update && apt-get install -y --no-install-recommends \
            libcudnn7=$CUDNN_VERSION-1+cuda9.0

rm -rf /var/lib/apt/lists/*


# Tensorflow
# https://github.com/tensorflow/tensorflow/blob/master/tensorflow/tools/docker/Dockerfile.gpu

apt-get update && apt-get install -y --no-install-recommends \
        build-essential \
        cuda-command-line-tools-9-0 \
        cuda-cublas-9-0 \
        cuda-cufft-9-0 \
        cuda-curand-9-0 \
        cuda-cusolver-9-0 \
        cuda-cusparse-9-0 \
        curl \
        libcudnn7=7.1.4.18-1+cuda9.0 \
        libnccl2=2.2.13-1+cuda9.0 \
        libfreetype6-dev \
        libhdf5-serial-dev \
        libpng12-dev \
        libzmq3-dev \
        pkg-config \
        rsync \
        software-properties-common \
        unzip && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*

# If E: something occured, please try it like below
# https://itsfoss.com/fix-ubuntu-install-error/
# sudo killall apt-get
# sudo rm /var/lib/apt/lists/lock
# sudo rm /var/cache/apt/archives/lock
# sudo rm /var/lib/dpkg/lock
# sudo dpkg --configure -a


# Default: python3
ln -s -f /usr/bin/python3 /usr/bin/python

curl -O https://bootstrap.pypa.io/get-pip.py && \
    python get-pip.py && \
    rm get-pip.py

pip --no-cache-dir install \
        Pillow \
        h5py \
        ipykernel \
        jupyter \
        matplotlib \
        numpy \
        pandas \
        scipy \
        sklearn \
        tensorflow-gpu==1.9.0

python -m ipykernel.kernelspec

# jupyter notebook
jupyter notebook --generate-config
wget 'https://gist.githubusercontent.com/GzuPark/b70ee9a3fb47ae9598065ac20b5c9743/raw/1ce659f5f9327d1f6da0b85d2baf8170d8a4f67a/jupyter_notebook_config.py'
mv jupyter_notebook_config.py .jupyter/

LD_LIBRARY_PATH=/usr/local/cuda/extras/CUPTI/lib64:$LD_LIBRARY_PATH

# PyTorch
pip install http://download.pytorch.org/whl/cu90/torch-0.4.0-cp35-cp35m-linux_x86_64.whl 
pip install torchvision

# Screen setting
wget 'https://gist.githubusercontent.com/GzuPark/6411fee45ee81add9f00925275232074/raw/ca6900be3381e4ac1290959d4687d52d694cebd1/.screenrc'