Installing TensorFlow on EC2

install-tensorflow.sh

# Note – this is not a bash script (some of the steps require reboot)
# I named it .sh just so Github does correct syntax highlighting.
# This install Tensorflow 0.11, Cuda 8.0 and cudnn-8.0
# The CUDA part is mostly based on this excellent blog post:
# http://tleyden.github.io/blog/2014/10/25/cuda-6-dot-5-on-aws-gpu-instance-running-ubuntu-14-dot-04/
# I extened Erick using additional instructions from http://ramhiser.com/2016/01/05/installing-tensorflow-on-an-aws-ec2-instance-with-gpu-support/

# Install various packages
sudo apt-get update
sudo apt-get upgrade -y # choose “install package maintainers version”
sudo apt-get install -y build-essential python-pip python-dev git python-numpy swig python-dev default-jdk zip zlib1g-dev

sudo apt-get install -y build-essential git python-pip libfreetype6-dev libxft-dev libncurses-dev libopenblas-dev gfortran python-matplotlib libblas-dev liblapack-dev libatlas-base-dev python-dev python-pydot linux-headers-generic linux-image-extra-virtual unzip python-numpy swig python-pandas python-sklearn unzip wget pkg-config zip g++ zlib1g-dev


# Blacklist Noveau which has some kind of conflict with the nvidia driver
echo -e "blacklist nouveau\nblacklist lbm-nouveau\noptions nouveau modeset=0\nalias nouveau off\nalias lbm-nouveau off\n" | sudo tee /etc/modprobe.d/blacklist-nouveau.conf
echo options nouveau modeset=0 | sudo tee -a /etc/modprobe.d/nouveau-kms.conf
sudo update-initramfs -u
sudo reboot # Reboot (annoying you have to do this in 2015!)

# Some other annoying thing we have to do
# sudo apt-get install -y linux-image-extra-virtual
#sudo reboot # Not sure why this is needed

# Install latest Linux headers
sudo apt-get install -y linux-source linux-headers-`uname -r` 

# Install CUDA 8.0 (note – don't use any other version)
mkdir packages 
cd packages
wget https://developer.nvidia.com/compute/cuda/8.0/prod/local_installers/cuda-repo-ubuntu1604-8-0-local_8.0.44-1_amd64-deb
sudo dpkg -i cuda-repo-ubuntu1604-8-0-local_8.0.44-1_amd64-deb
rm cuda-repo-ubuntu1604-8-0-local_8.0.44-1_amd64-deba
sudo apt-get update
sudo apt-get install -y cuda

# chmod +x cuda_7.0.28_linux.run
# ./cuda_7.0.28_linux.run -extract=`pwd`/nvidia_installers
# cd nvidia_installers
# sudo ./NVIDIA-Linux-x86_64-346.46.run 
# sudo modprobe nvidia
# sudo ./cuda-linux64-rel-7.0.28-19326674.run 
cd

# After filling out an annoying questionnaire, you’ll download a file named cudnn-8.0-linux-x64-v2.tgz. You need to transfer it to your EC2 instance: I did this by adding it to my Dropbox folder and using wget to upload it. Once you have uploaded it to your home directory, run the following:
# Install CUDA NN 8.0
tar -vxzf cudnn-8.0-linux-x64-v5.0-ga.tgz
sudo cp cuda/lib64/libcudnn* /usr/local/cuda/lib64
sudo cp cuda/include/cudnn.h /usr/local/cuda/include/

# Next up, we’ll add some environment variables. You may wish to add these to your ~/.bashrc.
export CUDA_HOME=/usr/local/cuda
export CUDA_ROOT=/usr/local/cuda
export PATH=$PATH:$CUDA_ROOT/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CUDA_ROOT/lib64

# 1. Install JDK 8
sudo add-apt-repository -y ppa:webupd8team/java
sudo apt-get update
# Hack to silently agree license agreement
echo debconf shared/accepted-oracle-license-v1-1 select true | sudo debconf-set-selections
echo debconf shared/accepted-oracle-license-v1-1 seen true | sudo debconf-set-selections
sudo apt-get install -y oracle-java8-installer
# Note: You might need to sudo apt-get install software-properties-common if you don't have the add-apt-repository command. See here.

#sudo apt-get install openjdk-8-jdk. Inst
# all other required packages

sudo apt-get install pkg-config zip g++ zlib1g-dev unzip



# At this point the root mount is getting a bit full
# I had a lot of issues where the disk would fill up and then Bazel would end up in this weird state complaining about random things
# Make sure you don't run out of disk space when building Tensorflow!
sudo mkdir /mnt/tmp
sudo chmod 777 /mnt/tmp
sudo rm -rf /tmp
sudo ln -s /mnt/tmp /tmp
# Note that /mnt is not saved when building an AMI, so don't put anything crucial on it

# Install Bazel
cd /tmp
wget https://github.com/bazelbuild/bazel/releases/download/0.4.0/bazel-0.4.0-jdk7-installer-linux-x86_64.sh
sudo bash bazel-0.4.0-jdk7-installer-linux-x86_64.sh

# Install Tensorflow
sudo apt-get install pkg-config zip g++ zlib1g-dev
git clone --recurse-submodules https://github.com/tensorflow/tensorflow
git checkout tags/v0.11.0
TF_UNOFFICIAL_SETTING=1 ./configure

# Please specify a list of comma-separated Cuda compute capabilities you want to build with.
# You can find the compute capability of your device at: https://developer.nvidia.com/cuda-gpus.
# Please note that each additional compute capability significantly increases your build time and binary size.
# [Default is: "3.5,5.2"]: 3.0


# Install TensorFlow
cd /mnt/tmp
export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64"
export CUDA_HOME=/usr/local/cuda
git clone --recurse-submodules https://github.com/tensorflow/tensorflow
cd tensorflow
# Patch to support older K520 devices on AWS
# wget "https://gist.githubusercontent.com/infojunkie/cb6d1a4e8bf674c6e38e/raw/5e01e5b2b1f7afd3def83810f8373fbcf6e47e02/cuda_30.patch"
# git apply cuda_30.patch
# According to https://github.com/tensorflow/tensorflow/issues/25#issuecomment-156234658 this patch is no longer needed
# Instead, you need to run ./configure like below (not tested yet)
TF_UNOFFICIAL_SETTING=1 ./configure
bazel build -c opt --config=cuda //tensorflow/cc:tutorials_example_trainer
bazel build -c opt --config=cuda //tensorflow/tools/pip_package:build_pip_package
bazel-bin/tensorflow/tools/pip_package/build_pip_package /tmp/tensorflow_pkg
sudo pip install --upgrade /tmp/tensorflow_pkg/tensorflow-0.11.0-cp27-cp27mu-linux_x86_64.whl

# test in a python
# import tensorflow as tf
# tf_session = tf.Session()
# x = tf.constant(1)
# y = tf.constant(1)
# tf_session.run(x + y)

# Test it wit CIFAR
cd tensorflow/models/image/cifar10/
python cifar10_multi_gpu_train.py 

# You can also check that TensorFlow is working by training a CNN on the MNIST data set.
python ~/tensorflow/tensorflow/models/image/mnist/convolutional.py