Difference between revisions of "Monai"

Revision as of 21:37, 10 March 2022

Description

The MONAI framework is the open-source foundation being created by Project MONAI. MONAI is a freely available, community-supported, PyTorch-based framework for deep learning in healthcare imaging. It provides domain-optimized foundational capabilities for developing healthcare imaging training workflows in a native PyTorch paradigm.

Project MONAI also includes MONAI Label, an intelligent open source image labeling and learning tool that helps researchers and clinicians collaborate, create annotated datasets, and build AI models in a standardized MONAI paradigm.

Environment Modules

Run module spider monai to find out what environment modules are available for this application.

System Variables

HPC_MONAI_DIR - installation directory
HPC_MONAI_BIN - executable directory
HPC_MONAI_LIB - library directory

HPC_MONAILABEL_DIR - MONAI label installation directory

MONAI core

         NGC container usage:
            ml purge
            ml ngc-monai/<version>
            python <your__python_script>

MONAI label

         NGC container usage:

           1) Server:

                To start the server as a slurm job:
                   ml purge
                   ml ngc-monailabel/<version>
                   sbatch start_monai_server_readonly.sh

                Note server address from job output: used in next step

           2) 3DSlicer client

               - Start Open On Demand (OOD) session
               - Start Console in hwgui with 1 GPU: gpu:geforce:1
               - In console: load & start Slicer
                    ml slicer/4.13.0
                    Slicer
               - In Slicer GUI:
                    Select module: Active Learning -> MONAILabel
                    Fill in server address, e.g.: http://c1007a-s17:8000/
                    Click on refresh button next to server address
                    Load Next Sample
               You are good to go! Enjoy!