Installation

DeepReg is written in Python 3.7. Dependent external libraries provide core IO functionalities and other standard processing tools. The dependencies for DeepReg are managed by pip.

Create a virtual environment

The recommended method is to install DeepReg in a dedicated virtual environment to avoid issues with other dependencies. The conda environment is recommended:

Anaconda / Miniconda

DeepReg primarily supports and is regularly tested with Ubuntu and Debian Linux distributions.

Linux

Mac OS

Windows

With CPU only

conda env create -f environment_cpu.yml
conda activate deepreg

With GPU

conda env create -f environment.yml
conda activate deepreg

With CPU only

conda env create -f environment_cpu.yml
conda activate deepreg

With GPU

Warning

Not supported or tested.

With CPU only

Warning

DeepReg on Windows is not fully supported. However, you can use the Windows Subsystem for Linux with CPU only. Set up WSL and follow the DeepReg setup instructions for Linux.

With GPU

Warning

Not supported or tested.

Use docker

We also provide the docker file for building the docker image.

Install docker

Docker can be installed following the official documentation.

For Linux based OS, there are some additional setup after the installation. Otherwise you might have permission errors.

Build docker image

docker build . -t deepreg -f Dockerfile

where

• -t names the built image as deepreg.

• -f provides the docker file for configuration.

Create a container

docker run --name <container_name> --privileged=true -ti deepreg bash

where - --name names the created container. - --privileged=true is required to solve the permission issue linked to TensorFlow profiler. - -it allows interaction with container and enters the container directly, check more info on stackoverflow.

Remove a container

docker rm -v <container_name>

which removes a created container and its volumes, check more info on docker documentation.

Install the package directly

Install from the cloned local project

git clone https://github.com/DeepRegNet/DeepReg.git # clone the repository
cd DeepReg # change working directory to the DeepReg root directory
pip install -e . # install the package

Install from the PyPI release

pip install deepreg

Note

All dependencies, APIs and command-line tools will be installed automatically via either installation method. However, the PyPI release currently does not ship with test data and demos. Running examples in this documentation may require downloading test data and changing default paths to user-installed packages with the PyPI release. These examples include those in the Quick Start and DeepReg Demo.