Download the resource

Download the resource manually from top right corner of resource page in this address:

https://ngc.nvidia.com/catalog/resources/nvidia:unet3d_medical_for_tensorflow

Also you can use this wget command:

wget --content-disposition https://api.ngc.nvidia.com/v2/resources/nvidia/unet3d_medical_for_tensorflow/versions/20.06.0/zip -O unet3d_medical_for_tensorflow_20.06.0.zip

Build the U-Net TensorFlow NGC container

This command will use the Dockerfile to create a Docker image named unet3d_tf, downloading all the required components automatically.

docker build -t unet3d_tf .

Download the Dataset

Data can be obtained by registering on Brain Tumor Segmentation 2019 dataset website at this address "https://www.med.upenn.edu/cbica/brats-2019/". The data should be downloaded and placed where /data in the container is mounted.

Run the Container

Start an interactive session in the NGC container to run preprocessing/training/inference. The following command will launch the container and mount the ./data directory as a volume to the /data directory inside the container, and ./results directory to the /results directory in the container.

mkdir data
mkdir results

docker run  -it --gpus=all --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 --rm --ipc=host -v ${PWD}/data:/data -v ${PWD}/results:/results  -p 8888:8888 unet3d_tf:latest /bin/bash

Start notebook inside the container:

Use this command to start a jupyter notebook inside the container:

jupyter notebook --ip 0.0.0.0 --port 8888 --allow-root

Move the dataset to the /data directory inside the container

Download the notebook from the top right part of this page or use wget command on top of the page then upload the notebook into the jupyterlab and run the cells of the notebook to preprocess the dataset, train, benchmark and test the model.