Contents

• Run Microscopy Image Browser as standalone (Linux, x64 bit)
• First start of MIB
• Issues and solutions
  • MATLAB crashes during start of training in DeepMIB
  • MIB in Singularity container does not see GPU

If you have a MATLAB license it is recommended to use MIB for MATLAB environment distribution of MIB suitable for Windows, MacOS and Linux. Otherwise use the standalone versions of MIB compiled for your operating system.

Tested and compiled with Ubuntu, version 18.04.5 LTS (Bionic Beaver) and MATLAB version 9.7 (R2019b)

• Requires 64-bit Linux
• Download ZIP archive file with the recent release of MIB (MIB2_Linux.zip or use the releases section on GitHub for older releases
• Extract the installer from the downloaded file MIB2_Linux.zip
  Extract the installer
• Double click on MIB2_Linux.install icon to start the installation process
• Choose the installation folder
  (it is recommended to install MIB into an own home directory as demonstrated on the snapshot)
  
  Choose the installation folder
• Choose the installation folder for MATLAB runtime
  (it is recommended to install MIB into an own home directory as demonstrated on the snapshot.
  If MATLAB runtime is already installed, provide its location)
  
  Choose the installation folder for MATLAB runtime
• Accept the license agreement and press Next
• Press Install to begin installation of MIB and MCR
• Press Finish to quit the installer
  optionally, some additional tweaks may also be applied
  
  Press Finish to quit the installer
• Start MIB from terminal window using the following syntax:
  [location of run_MIB.sh file] [location of MRC]
/home/ad/lxhome/i/ibelev/linux/MATLAB/MIB_deploy_2701/application/run_MIB.sh /home/ad/lxhome/i/ibelev/linux/MATLAB/Runtime/v97
  Start MIB using similarly formed command from terminal window

• If the size of MIB window is not optimal please refer to the GUI scaling instructions in the Additional Info section
• Access help and tutorials from the menu of MIB: im_browser->Menu->Help->Help or from http:\\mib.helsinki.fi/tutorials

This issue was detected on VM when using MIB with MATLAB container. When starting training of CNN, MATLAB crashes with "Could not initialize GLX" error.
This can be fixed by

• forcing nosoftwareopengl by starting MATLAB from terminal using this command:
  >> matlab -nosoftwareopengl
• or switching of the loss function plot:
  Train tab->Training settings->Plots->none

This issue was detected on VM when using compiled MIB inside a singularity container. When starting DeepMIB, the GPU card was not detected.
This can be fixed by

• modify run_MIB.sh file by adding
  LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/.singularity.d/libs;
  just before export LD_LIBRARY_PATH;
• start MIB singularity container as
  singularity exec --nv /path/to/the/container
  the --nv key made the nvidia driver libs available inside the container at /.singularity.d/libs.

How to start MIB in the standalone mode

---