easyfmri Code
Brought to you by:
myousefnezhad
Menu
▾
▴
Tree [eb21e4] master / History
myousefnezhad
Read Me
<!DOCTYPE html><html><head><meta charset="utf-8"><title>Untitled Document.md</title><script type="text/javascript">
//<![CDATA[
window.__cfRocketOptions = {byc:0,p:0,petok:"991437689aae00a4c85453f421d0f581ef4b5e98-1523348501-1800"};
//]]>
</script>
<script type="text/javascript" src="https://ajax.cloudflare.com/cdn-cgi/scripts/935cb224/cloudflare-static/rocket.min.js"></script>
<style></style></head><body id="preview">
<h1><a id="easy_fMRI_project_V18B4200_beta_0"></a>easy fMRI project (V1.8B4200 beta)</h1>
<h3><a id="Introduction_3"></a>Introduction</h3>
<p>Easy fMRI is an open source toolbox for the Human Brain Mapping and Decoding. This project is developing by <a href="https://myousefnezhad.sourceforge.io">Muhammad Yousefnezhad</a>, <a href="http://ibrain.nuaa.edu.cn">iBRAIN Group</a>, <a href="http://iao.nuaa.edu.cn">Nanjing University of Aeronautics and Astronautics</a>, China.</p>
<p>The project website is <a href="https://easyfmri.github.io/">https://easyfmri.github.io/</a> or <a href="https://easyfmri.sourceforge.io/">https://easyfmri.sourceforge.io/</a>.</p>
<h3><a id="Dependencies_9"></a>Dependencies</h3>
<p>Easy fMRI needs following software:</p>
<p>-Platform: Linux (recommended), Mac, Windows (via Linux Virtual Machine, or Bash for Windows 10 or above)</p>
<p>-<a href="https://anaconda.org/anaconda/python">Python3</a> (version=3.6.2 or above)</p>
<p>-<a href="https://fsl.fmrib.ox.ac.uk/fsl/fslwiki">FSL</a> (version=5.0.10 or above) for preprocessing steps</p>
<p>-<a href="https://afni.nimh.nih.gov/">AFNI & SUMA</a> (version=17.3.06 or above) for 3D visualization</p>
<p>-<a href="https://developer.nvidia.com/cuda-toolkit">CUDA</a> for GPU-based algorithms</p>
<p>-<a href="https://developer.nvidia.com/cudnn">CUDNN</a> for GPU-based algorithms</p>
<p>-<a href="https://www.tensorflow.org/install/">Tensorflow</a> for Gradient-based Optimization and Learning</p>
<h3><a id="How_to_install_easy_fMRI_28"></a>How to install easy fMRI</h3>
<h3><a id="Preinstall_for_Windows_10_users_30"></a>Pre-install for Windows 10 users:</h3>
<p>– Install Windows Subsystem for Linux <a href="https://docs.microsoft.com/en-us/windows/wsl/install-win10">https://docs.microsoft.com/en-us/windows/wsl/install-win10</a></p>
<p>NOTE: You have to install UBUNTU Linux from Windows Store.</p>
<p>– Install Xming X Server for Windows: <a href="https://sourceforge.net/projects/xming/files/latest/download">https://sourceforge.net/projects/xming/files/latest/download</a></p>
<p>– Open command prompt (press Windows key + R, then in run window type <code>cmd</code> and press enter)</p>
<p>– Open bash via cmd:</p>
<pre><code>bash
</code></pre>
<p>– Set Display:</p>
<pre><code>echo "export DISPLAY=:0.0" >> ~/.profile
source ~/.profile
</code></pre>
<p>Now you can install easy fMRI same as a linux system</p>
<h4><a id="STEP_A_Copy_Files_55"></a>STEP A) Copy Files</h4>
<p>– Download easy fMRI files:</p>
<p>From <a href="https://github.com/easyfmri/easyfmri">GitHub</a>:</p>
<pre><code>git clone https://github.com/easyfmri/easyfmri.git ~/.easyfmri
</code></pre>
<p>From <a href="https://sourceforge.net/p/easyfmri/code/ci/master/tree/">SourceForge Git</a>:</p>
<pre><code>git clone git://git.code.sf.net/p/easyfmri/code ~/.easyfmri
</code></pre>
<p>From <a href="https://sourceforge.net/projects/easyfmri/files/">SourceForge</a> as a zip file</p>
<pre><code>unzip easyfMRI.<version>.zip
mv easyfmri .easyfmri
</code></pre>
<p>– Copy <code>ezfmri</code> to <code>/usr/bin/local</code></p>
<pre><code>cd ~/.easyfmri/Script
./cp_script
</code></pre>
<p>– Set environment variables (see example at the end)</p>
<h4><a id="STEP_B_Install_FSL_5010_or_above_88"></a>STEP B) Install FSL 5.0.10 or above</h4>
<p>– Register on <a href="https://fsl.fmrib.ox.ac.uk/fsl/fslwiki">FSL website</a></p>
<p>– Download <code>fslinstaller.py</code></p>
<p>– Run following for downloading installation file (e.g. In version 5.0.10, the file name is <code>fsl-5.0.10-macOS_64.tar.gz</code> for Mac or <code>fsl-5.0.10-centos7_64.tar.gz</code> for all Linux distribution)</p>
<p>For Linux:</p>
<pre><code>python2 fslinstaller.py -o
md5sum fsl-5.0.10-centos7_64.tar.gz
</code></pre>
<p>For Mac:</p>
<pre><code>python2 fslinstaller.py -o
md5sum fsl-5.0.10-macOS_64.tar.gz
</code></pre>
<p>– Install the downloaded file:</p>
<p>For Linux:</p>
<pre><code>python2 fslinstaller.py -f fsl-5.0.10-centos7_64.tar.gz -M
</code></pre>
<p>For Mac:</p>
<pre><code>python2 fslinstaller.py -f fsl-5.0.10-macOS_64.tar.gz -M
</code></pre>
<p>– Set environment variables (see example at the end)</p>
<h4><a id="STEP_D_Install_AFNI_17306_or_above_128"></a>STEP D) Install AFNI 17.3.06 or above</h4>
<p>– Download <a href="https://afni.nimh.nih.gov/">AFNI</a></p>
<p>– Extract AFNI to <code>~/abin</code></p>
<p>– Set environment variables (see example at the end)</p>
<p>NOTE: For Ubuntu-based Linux, you have to install following packages:</p>
<pre><code>sudo apt-get install -y tcsh xfonts-base python-qt4 gsl-bin netpbm gnome-tweak-tool libjpeg62 xvfb xterm vim curl
sudo apt-get install -y libglu1-mesa-dev libglw1-mesa libxm4 build-essential
</code></pre>
<h4><a id="STEP_D_Install_Python_36x_144"></a>STEP D) Install Python 3.6.x</h4>
<p>– Download <a href="https://anaconda.org/anaconda/python">Anaconda3</a> and Install Python3 by using Anaconda3</p>
<p>For Linux:</p>
<pre><code>sh Anaconda3-<version>-Linux<platform>.sh
</code></pre>
<p>For Mac: click PKG file and continue installation.</p>
<p>– Set environment variables (see example at the end)</p>
<p>– Install all packages in <code>~/.easyfmri/PyPackage</code> directory</p>
<pre><code>cd ~/.easyfmri/PyPackage
pip install *
</code></pre>
<p>– Install MPI packages:</p>
<pre><code>conda install mpi4py
</code></pre>
<p>– Install Tensorflow package:</p>
<p>For CPU version:</p>
<pre><code>pip install tensorflow
</code></pre>
<p>For GPU Vesion: You must install <a href="https://developer.nvidia.com/cuda-toolkit">CUDA</a> and <a href="https://developer.nvidia.com/cudnn">CuDNN</a>. Then, you can install <a href="https://www.tensorflow.org/install/">Tensorflow</a></p>
<p>Note: By employing <code>CUDA 9.0</code>, <code>CUDNN 7.0</code> and <code>Ubuntu 16.04.x</code>, you can use following command to install tensorflow:</p>
<pre><code>pip install tensorflow-gpu
</code></pre>
<h4><a id="STEP_E_Run_easy_fMRI_188"></a>STEP E) Run easy fMRI</h4>
<p>After restarting your computer, open a terminal and run easyfmri:</p>
<pre><code>ezfmri
</code></pre>
<h3><a id="How_to_upgrade_easy_fMRI_196"></a>How to upgrade easy fMRI</h3>
<p>For updating a new version, just replace the old files with the new files.</p>
<p>Note: default directory for easy fMRI is a hidden folder in <code>~/.easyfmri</code></p>
<pre><code>rm -R ~/.easyfmri
git clone https://github.com/easyfmri/easyfmri.git ~/.easyfmri
</code></pre>
<h3><a id="An_example_of_environment_variables_208"></a>An example of environment variables</h3>
<p>You can install this script automatically as follows:</p>
<p>For Linux:</p>
<pre><code>cd ~/.easyfmri/Script
./install_script_linux
</code></pre>
<p>For Mac:</p>
<pre><code>cd ~/.easyfmri/Script
./install_script_mac
</code></pre>
<p>Or just copy following to in <code>.profile</code> or <code>.bashrc</code> and restart your computer</p>
<pre><code>######################################
# Enable ("1") or Disable ("0") features #
######################################
export EN_EZFMRI="1"
export EN_PYTHON="1"
export EN_PYTHON_ALIAS="1"
export EN_AFNI="1"
export EN_FSL="1"
export EN_CUDA="1"
export EN_BASH="1"
export EN_MC="1"
export EN_COLOR="1"
######################################
# Directories #
######################################
export INSTALL_DIR="$HOME" # Base dir for Anaconda, easy fMRI, and AFNI
export FSLDIR="/usr/local/fsl" # for FSL 5.0.10
export ANACON_PATH="$INSTALL_DIR/anaconda3/bin"
export AFNI_PATH="$INSTALL_DIR/abin"
export CUDA_HOME="/usr/local/cuda"
# export FSLDIR="/usr/share/fsl/5.0" # for FSL 5.0.9
# export DISPLAY=:0.0 # Enable for Windows 10
######################################
# Scripts #
######################################
######## Easy fMRI
if (( $EN_EZFMRI != "0" )); then
export EASYFMRI="$INSTALL_DIR/.easyfmri"
fi
######## Python
if (( $EN_PYTHON != "0" )); then
export PATH="$ANACON_PATH:$PATH"
fi
if (( $EN_PYTHON_ALIAS != "0" )); then
alias python="python -m IPython"
alias python3="python -m IPython"
fi
######## AFNI
if (( $EN_AFNI != "0" )); then
export DYLD_LIBRARY_PATH=/opt/X11/lib/flat_namespace
export DYLD_FALLBACK_LIBRARY_PATH="$HOME/abin"
export PATH="/usr/local/bin:$AFNI_PATH:$PATH"
fi
####### FSL
if (( $EN_FSL != "0" )); then
. $FSLDIR/etc/fslconf/fsl.sh
export PATH="$FSLDIR/bin:$PATH"
fi
####### CUDA
if (( $EN_CUDA != "0" )); then
export DYLD_LIBRARY_PATH="$DYLD_LIBRARY_PATH:$CUDA_HOME/lib"
export LD_LIBRARY_PATH="$DYLD_LIBRARY_PATH:$CUDA_HOME/lib:/usr/local/cuda/lib64/"
export PATH="$CUDA_HOME/bin:$PATH"
fi
####### BASH
if (( $EN_BASH != "0" )); then
[ -f /usr/local/etc/bash_completion ] && . /usr/local/etc/bash_completion
fi
####### MC
if (( $EN_MC != "0" )); then
alias mc=". /usr/local/opt/midnight-commander/libexec/mc/mc-wrapper.sh"
fi
####### BASH COLOR
if (( $EN_COLOR != "0" )); then
# Define Colors
C_DEFAULT="\[\033[m\]"
C_WHITE="\[\033[1m\]"
C_BLACK="\[\033[30m\]"
C_RED="\[\033[31m\]"
C_GREEN="\[\033[32m\]"
C_YELLOW="\[\033[33m\]"
C_BLUE="\[\033[34m\]"
C_PURPLE="\[\033[35m\]"
C_CYAN="\[\033[36m\]"
C_LIGHTGRAY="\[\033[37m\]"
C_DARKGRAY="\[\033[1;30m\]"
C_LIGHTRED="\[\033[1;31m\]"
C_LIGHTGREEN="\[\033[1;32m\]"
C_LIGHTYELLOW="\[\033[1;33m\]"
C_LIGHTBLUE="\[\033[1;34m\]"
C_LIGHTPURPLE="\[\033[1;35m\]"
C_LIGHTCYAN="\[\033[1;36m\]"
C_BG_BLACK="\[\033[40m\]"
C_BG_RED="\[\033[41m\]"
C_BG_GREEN="\[\033[42m\]"
C_BG_YELLOW="\[\033[43m\]"
C_BG_BLUE="\[\033[44m\]"
C_BG_PURPLE="\[\033[45m\]"
C_BG_CYAN="\[\033[46m\]"
C_BG_LIGHTGRAY="\[\033[47m\]"
# Set Terminal Colors
export CLICOLOR=1
export LSCOLORS=GxacCxDxBxegedabagaced
alias ls='ls -GFh'
export PS1="\n$C_LIGHTPURPLE\<a href="/cdn-cgi/l/email-protection" class="__cf_email__" data-cfemail="700554332f34353631253c2430">[email protected]</a>$C_LIGHTCYAN\h$C_DEFAULT:$C_LIGHTBLUE\W$C_DEFAULT\$$C_LIGHTYELLOW "
if (( $EUID != 0 )); then
export LSCOLORS=GxacCxDxBxegedabagaced
export PS1="\n$C_LIGHTGREEN\<a href="/cdn-cgi/l/email-protection" class="__cf_email__" data-cfemail="3c49187f6378797a7d6970687c">[email protected]</a>$C_LIGHTCYAN\h$C_DEFAULT:$C_LIGHTBLUE\W$C_DEFAULT\$$C_LIGHTYELLOW "
fi
fi
</code></pre>
<script data-cfasync="false" src="/cdn-cgi/scripts/d07b1474/cloudflare-static/email-decode.min.js"></script></body></html>
