Getting code ready for the next major release

.gitignore

@@ -58,3 +58,9 @@ vsts*
 superbuild
 build
 debug.log
+data/dicoms_from_tcia/*
+venv/*
+src/applications/FeTS_Tool_Helper.egg-info/*
+src/applications/__pycache__/*
+data/*.zip
+src/applications/data_prep_models/*

CMakeLists.txt

@@ -11,9 +11,9 @@ SET( ${PROJECT_NAME}_Variant "Full" ) # the particular variant of CaPTk (Full/Ne
 # So small changes here to formatting or naming convention *may potentially break the linux packager*!
 # STRING(TIMESTAMP TODAY "%Y%m%d")
 
-SET( PROJECT_VERSION_MAJOR 1 )
+SET( PROJECT_VERSION_MAJOR 2 )
 SET( PROJECT_VERSION_MINOR 0 )
-SET( PROJECT_VERSION_PATCH 3 )
+SET( PROJECT_VERSION_PATCH 0 )
 SET( PROJECT_VERSION_TWEAK )
 
 # check for the string "nonRelease" in the PROJECT_VERSION_PATCH variable
@@ -157,12 +157,12 @@ IF(${PROJECT_NAME}_Variant MATCHES "Full" )
 ELSE()
   SET( PROJECT_NAME_EXTENDED "Federated Tumor Segmentation (${PROJECT_NAME}_${${PROJECT_NAME}_Variant})" )
 ENDIF()
-SET( PROJECT_VENDOR "CBICA - UPenn" )
+SET( PROJECT_VENDOR "The FeTS-AI Group" )
 SET( LICENSE_FILE "${PROJECT_SOURCE_DIR}/LICENSE" )
 SET( README_FILE  "${PROJECT_SOURCE_DIR}/README.txt" )
-SET( PROJECT_DOMAIN "https://www.med.upenn.edu/cbica/captk/" )
-SET( PROJECT_CONTACT "[email protected]" )
-SET( COPYRIGHT "Copyright (c) 2019 CBICA. All rights reserved.")
+SET( PROJECT_DOMAIN "https://www.fets.ai" )
+SET( PROJECT_CONTACT "admin@fets" )
+SET( COPYRIGHT "Copyright (c) 2023 FeTS-AI. All rights reserved.")
 SET( IDENTIFIER "")
 ADD_DEFINITIONS(-DPROJECT_NAME="${PROJECT_NAME}" )
 ADD_DEFINITIONS(-DPROJECT_VERSION="${PROJECT_VERSION}" )
@@ -544,95 +544,95 @@ IF( NOT BUILD_DOCUMENTATION_ONLY )
     ${LIBNAME_Applications} 
   )
 
-  # update submodule
-  IF( NOT EXISTS "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/setup.py" )
-    EXECUTE_PROCESS(COMMAND git submodule update --init --recursive
-    WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
-    RESULT_VARIABLE git_result
-    OUTPUT_VARIABLE git_ver)    
-  ENDIF()
+  # # update submodule
+  # IF( NOT EXISTS "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/setup.py" )
+  #   EXECUTE_PROCESS(COMMAND git submodule update --init --recursive
+  #   WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+  #   RESULT_VARIABLE git_result
+  #   OUTPUT_VARIABLE git_ver)    
+  # ENDIF()
 
-  # update submodule
-  IF( NOT EXISTS "${PROJECT_SOURCE_DIR}/Models_Pretrained/README.md" )
-    EXECUTE_PROCESS(COMMAND git submodule update --init --recursive
-    WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
-    RESULT_VARIABLE git_result
-    OUTPUT_VARIABLE git_ver)    
-  ENDIF()
+  # # update submodule
+  # IF( NOT EXISTS "${PROJECT_SOURCE_DIR}/Models_Pretrained/README.md" )
+  #   EXECUTE_PROCESS(COMMAND git submodule update --init --recursive
+  #   WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+  #   RESULT_VARIABLE git_result
+  #   OUTPUT_VARIABLE git_ver)    
+  # ENDIF()
 
-  # get lfs to pull
-  IF( EXISTS "${PROJECT_SOURCE_DIR}/BrainMaGe" )
-    EXECUTE_PROCESS(COMMAND git lfs pull
-    WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/BrainMaGe
-    RESULT_VARIABLE git_result
-    OUTPUT_VARIABLE git_ver)  
-  ENDIF()  
+  # # get lfs to pull
+  # IF( EXISTS "${PROJECT_SOURCE_DIR}/BrainMaGe" )
+  #   EXECUTE_PROCESS(COMMAND git lfs pull
+  #   WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/BrainMaGe
+  #   RESULT_VARIABLE git_result
+  #   OUTPUT_VARIABLE git_ver)  
+  # ENDIF()  
 
-  # copy plans from algorithms 
-  IF( EXISTS "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/submodules/fets_ai/Algorithms/fets/bin/federations/plans/pt_3dresunet_brainmagebrats.yaml" )
-    FILE( GLOB FETS_AI_PLANS
-      "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/submodules/fets_ai/Algorithms/fets/bin/federations/plans/*.yaml"
-    )
-    FOREACH(fetsai_plan ${FETS_AI_PLANS})
-      CONFIGURE_FILE("${fetsai_plan}" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/" COPYONLY) 
-    ENDFOREACH()
-  ENDIF()
-
-  # copy weights from models
-  SET( DOWNLOAD_LINK "ftp://www.nitrc.org/home/groups/captk/downloads/models/torch/pt_3dresunet_ss_brainmagebrats_best.pt" )
-  SET( FILE_TO_EXTRACT "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/weights/pt_3dresunet_ss_brainmagebrats_best.pt")
-#   IF( NOT EXISTS "${FILE_TO_EXTRACT}" )
-
-#     # download exe from url
-#     MESSAGE( STATUS "Downloading weights for skull stripping" )
-#     FILE(DOWNLOAD "${DOWNLOAD_LINK}" "${FILE_TO_EXTRACT}" TIMEOUT 1000000 STATUS STATUS_CODE SHOW_PROGRESS)
-#     IF(NOT STATUS_CODE EQUAL 0)
-#       MESSAGE(FATAL_ERROR "Failed to download skull-stripping weights. Status=${STATUS_CODE}")
-#     ENDIF()
-#   ENDIF()
-
-  # copy network information
-  ## todo: change to a direct installation so that git doesn't get confused that submodule has changed
-  CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/network.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/defaults/network.yaml")
-  CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/cert_chain.crt" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/pki/cert_chain.crt")
-  #CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/pt_3dresunet_brainmagebrats.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/pt_3dresunet_brainmagebrats.yaml" COPYONLY) 
-  CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/deepscan_inference.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/deepscan_inference.yaml" COPYONLY) 
-  CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/nnunet_inference.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/nnunet_inference.yaml" COPYONLY) 
+  # # copy plans from algorithms 
+  # IF( EXISTS "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/submodules/fets_ai/Algorithms/fets/bin/federations/plans/pt_3dresunet_brainmagebrats.yaml" )
+  #   FILE( GLOB FETS_AI_PLANS
+  #     "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/submodules/fets_ai/Algorithms/fets/bin/federations/plans/*.yaml"
+  #   )
+  #   FOREACH(fetsai_plan ${FETS_AI_PLANS})
+  #     CONFIGURE_FILE("${fetsai_plan}" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/" COPYONLY) 
+  #   ENDFOREACH()
+  # ENDIF()
 
-  # find stand-alone CMD applications
-  FILE( GLOB DeepScan_Weights
-    "${PROJECT_SOURCE_DIR}/data/fets/*.tar"
-  )
-  file(MAKE_DIRECTORY "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/weights/deepscan/")
-  FOREACH(deepScan_weight ${DeepScan_Weights})
-    CONFIGURE_FILE("${deepScan_weight}" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/weights/deepscan/" COPYONLY) 
-  ENDFOREACH()
+  # # copy weights from models
+  # SET( DOWNLOAD_LINK "ftp://www.nitrc.org/home/groups/captk/downloads/models/torch/pt_3dresunet_ss_brainmagebrats_best.pt" )
+  # SET( FILE_TO_EXTRACT "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/weights/pt_3dresunet_ss_brainmagebrats_best.pt")
+  # IF( NOT EXISTS "${FILE_TO_EXTRACT}" )
+
+  #   # download exe from url
+  #   MESSAGE( STATUS "Downloading weights for skull stripping" )
+  #   FILE(DOWNLOAD "${DOWNLOAD_LINK}" "${FILE_TO_EXTRACT}" TIMEOUT 1000000 STATUS STATUS_CODE SHOW_PROGRESS)
+  #   IF(NOT STATUS_CODE EQUAL 0)
+  #     MESSAGE(FATAL_ERROR "Failed to download skull-stripping weights. Status=${STATUS_CODE}")
+  #   ENDIF()
+  # ENDIF()
 
-  INSTALL(
-    DIRECTORY "${PROJECT_SOURCE_DIR}/OpenFederatedLearning" 
-    DESTINATION bin
-    PATTERN ".git" EXCLUDE
-    PATTERN "venv" EXCLUDE
-  )
+  # # copy network information
+  # ## todo: change to a direct installation so that git doesn't get confused that submodule has changed
+  # CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/network.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/defaults/network.yaml")
+  # CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/cert_chain.crt" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/pki/cert_chain.crt")
+  # #CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/pt_3dresunet_brainmagebrats.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/pt_3dresunet_brainmagebrats.yaml" COPYONLY) 
+  # CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/deepscan_inference.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/deepscan_inference.yaml" COPYONLY) 
+  # CONFIGURE_FILE("${PROJECT_SOURCE_DIR}/data/fets/nnunet_inference.yaml" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/plans/nnunet_inference.yaml" COPYONLY) 
+
+  # # find stand-alone CMD applications
+  # FILE( GLOB DeepScan_Weights
+  #   "${PROJECT_SOURCE_DIR}/data/fets/*.tar"
+  # )
+  # file(MAKE_DIRECTORY "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/weights/deepscan/")
+  # FOREACH(deepScan_weight ${DeepScan_Weights})
+  #   CONFIGURE_FILE("${deepScan_weight}" "${PROJECT_SOURCE_DIR}/OpenFederatedLearning/bin/federations/weights/deepscan/" COPYONLY) 
+  # ENDFOREACH()
+
+  # INSTALL(
+  #   DIRECTORY "${PROJECT_SOURCE_DIR}/OpenFederatedLearning" 
+  #   DESTINATION bin
+  #   PATTERN ".git" EXCLUDE
+  #   PATTERN "venv" EXCLUDE
+  # )
 
-  INSTALL(
-    DIRECTORY "${PROJECT_SOURCE_DIR}/LabelFusion" 
-    DESTINATION bin
-    PATTERN ".git" EXCLUDE
-    PATTERN "venv" EXCLUDE
-  )
+  # INSTALL(
+  #   DIRECTORY "${PROJECT_SOURCE_DIR}/LabelFusion" 
+  #   DESTINATION bin
+  #   PATTERN ".git" EXCLUDE
+  #   PATTERN "venv" EXCLUDE
+  # )
 
-  INSTALL(
-    DIRECTORY "${PROJECT_SOURCE_DIR}/BrainMaGe" 
-    DESTINATION bin
-    PATTERN ".git" EXCLUDE
-    PATTERN "venv" EXCLUDE
-  )
+  # INSTALL(
+  #   DIRECTORY "${PROJECT_SOURCE_DIR}/BrainMaGe" 
+  #   DESTINATION bin
+  #   PATTERN ".git" EXCLUDE
+  #   PATTERN "venv" EXCLUDE
+  # )
 
 
-  FILE( GLOB_RECURSE ALL_PY_FILES "${PROJECT_SOURCE_DIR}/src/applications/*.py" )
+  FILE( GLOB ALL_PY_FILES "${PROJECT_SOURCE_DIR}/src/applications/*.py" )
   FOREACH( pyFile ${ALL_PY_FILES} )
-    INSTALL( FILES "${pyFile}" DESTINATION bin )
+    INSTALL( FILES "${pyFile}" DESTINATION bin PERMISSIONS OWNER_READ OWNER_WRITE OWNER_EXECUTE GROUP_READ GROUP_EXECUTE WORLD_READ WORLD_EXECUTE)
   ENDFOREACH()
 
   # find stand-alone CMD applications
@@ -1046,9 +1046,9 @@ IF( NOT BUILD_DOCUMENTATION_ONLY )
       SET(CPACK_NSIS_ENABLE_UNINSTALL_BEFORE_INSTALL ON)
       SET(CPACK_NSIS_MUI_ICON "${DATA_DIR}/icons/application/windows/FeTS.ico")
       SET(CPACK_NSIS_MUI_FINISHPAGE_RUN "${EXE_NAME}.exe")
-      SET(CPACK_NSIS_HELP_LINK "https:\\\\\\\\www.med.upenn.edu\\\\cbica\\\\captk\\\\")
+      SET(CPACK_NSIS_HELP_LINK "https:\\\\\\\\www.fets.ai\\\\")
       SET(CPACK_NSIS_CONTACT "${PROJECT_CONTACT}")
-      SET(CPACK_NSIS_URL_INFO_ABOUT "https:\\\\\\\\www.med.upenn.edu\\\\cbica\\\\captk\\\\")
+      SET(CPACK_NSIS_URL_INFO_ABOUT "https:\\\\\\\\www.fets.ai\\\\")
       #SET(CPACK_NSIS_MODIFY_PATH "ON") # desktop shortcut doesn't work, for some reason
       # create extra shortcuts and respective uninstall targets
       SET(CPACK_NSIS_CREATE_ICONS_EXTRA "CreateShortCut '\$SMPROGRAMS\\\\$STARTMENU_FOLDER\\\\${EXE_NAME}.lnk' '\$INSTDIR\\\\bin\\\\${EXE_NAME}.exe'")

Dockerfile

@@ -1,65 +1,54 @@
-FROM ghcr.io/fets-ai/fetstool_docker_dependencies:0.0.2.gpu
+FROM ghcr.io/fets-ai/fetstool_docker_dependencies AS fets_base
 
 LABEL authors="FeTS_Admin <[email protected]>"
 
 RUN apt-get update && apt-get update --fix-missing && apt-get install -y libnss3 libnspr4 libxcursor1 libxcursor-dev libasound2 libdbus-1-dev libglfw3-dev libgles2-mesa-dev ffmpeg libsm6 libxext6 python3.8 python3.8-venv python3.8-dev python3-setuptools
 
-# older python
-RUN apt-get update -y && apt install -y --reinstall software-properties-common && add-apt-repository ppa:deadsnakes/ppa && apt update -y && apt install -y python3.7 python3.7-venv python3.7-dev python3-setuptools
-
-ENV PATH=/workspace/CaPTk/bin/qt/5.12.1/bin:/workspace/CaPTk/bin/qt/5.12.1/libexec:$PATH
-ENV CMAKE_PREFIX_PATH=/workspace/CaPTk/bin/ITK-build:/workspace/CaPTk/bin/DCMTK-build:/workspace/CaPTk/bin/qt/5.12.1/lib/cmake/Qt5:$CMAKE_PREFIX_PATH
-ENV SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL=True
+ENV PATH=/CaPTk/bin/qt/5.12.1/bin:/CaPTk/bin/qt/5.12.1/libexec:$PATH
+ENV CMAKE_PREFIX_PATH=/CaPTk/bin/ITK-build:/CaPTk/bin/DCMTK-build:/CaPTk/bin/qt/5.12.1/lib/cmake/Qt5:$CMAKE_PREFIX_PATH
 
 RUN pwd && ls -l
 
 WORKDIR /Front-End
 
-COPY . .
+# Download model checkpoints to torch checkpoint location
+# https://pytorch.org/docs/stable/hub.html#where-are-my-downloaded-models-saved
+ENV TORCH_HOME="/.pytorch_cache"
+RUN mkdir -p $TORCH_HOME/hub/checkpoints && \
+    wget -O $TORCH_HOME/hub/checkpoints/dpn98-722954780.pth http://data.lip6.fr/cadene/pretrainedmodels/dpn98-722954780.pth --no-check-certificate && \
+    wget -O $TORCH_HOME/hub/checkpoints/resnet50-19c8e357.pth https://download.pytorch.org/models/resnet50-19c8e357.pth
+
+COPY src src
+
+COPY CMakeLists.txt README.txt LICENSE .
+
+COPY cmake_modules cmake_modules
 
-RUN pwd && ls -l && mv ./data/Algorithms_for_fetsTool1.0.zip OpenFederatedLearning/submodules/fets_ai/ && cd OpenFederatedLearning/submodules/fets_ai/ && unzip -qq Algorithms_for_fetsTool1.0.zip && rm -rf Algorithms_for_fetsTool1.0.zip
+COPY data data
 
-RUN pwd && ls -l && mv ./data/GANDLF_for_fetsTool1.0.zip OpenFederatedLearning/submodules/fets_ai/Algorithms && cd OpenFederatedLearning/submodules/fets_ai/Algorithms && unzip -qq GANDLF_for_fetsTool1.0.zip && rm -rf GANDLF_for_fetsTool1.0.zip
+COPY docs_sources docs_sources
+
+RUN pwd && ls -l
 
 ## C++ build
-RUN mkdir bin && cd bin && cmake -DCMAKE_INSTALL_PREFIX="./install/appdir/usr" -DITK_DIR="/workspace/CaPTk/bin/ITK-build" -DDCMTK_DIR="/workspace/CaPTk/bin/DCMTK-build" -DBUILD_TESTING=OFF .. && make -j$(nproc) && make install/strip 
-
-# ## Python package installation -- this is for the new docker image, which is much simpler
-# RUN cd bin/install/appdir/usr/bin/ && python3.8 -m venv ./venv && ./venv/bin/pip install --upgrade pip wheel && ./venv/bin/pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu && ./venv/bin/pip install -e . && ./venv/bin/pip install setuptools-rust Cython scikit-build scikit-learn openvino-dev==2023.0.1 && ./venv/bin/pip install -e .
-
-# set up environment and install correct version of pytorch
-RUN echo "Setting up virtual environment for OpenFederatedLearning with base dependencies" && \
-    cd bin/install/appdir/usr/bin/OpenFederatedLearning && \
-    rm -rf ./venv && python3.7 -m venv ./venv && ./venv/bin/pip install Cython && \
-    ./venv/bin/pip install --upgrade pip setuptools wheel setuptools-rust && \
-    ./venv/bin/pip install torch==1.7.1+cu110 torchvision==0.8.2+cu110 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html && \
-    ./venv/bin/pip install wheel && \
-    ./venv/bin/pip install SimpleITK==1.2.4 && \
-    ./venv/bin/pip install protobuf==3.17.3 grpcio==1.30.0 && \
-    ./venv/bin/pip install opencv-python==4.2.0.34 && \
-    ./venv/bin/pip install scikit-build scikit-learn && \
-    make install_openfl && \
-    make install_openfl_pytorch
-
-RUN echo "Setting up virtual environment for OpenFederatedLearning with second-level dependencies" && \
-    cd bin/install/appdir/usr/bin/OpenFederatedLearning && \
-    ./venv/bin/pip install ../BrainMaGe && \
-    ./venv/bin/pip install ./submodules/fets_ai/Algorithms && \
-    ./venv/bin/pip install -e ./submodules/fets_ai/Algorithms/GANDLF
-
-RUN echo "Installing separate environment for LabelFusion" && \
-    cd bin/install/appdir/usr/bin/LabelFusion && \
-    rm -rf venv && python3.8 -m venv ./venv && \
-    ./venv/bin/pip install --upgrade pip setuptools wheel setuptools-rust && \
-    ./venv/bin/pip install -e .
-
-RUN echo "Downloading model weights" && \
-    cd bin/install/appdir/usr/data && \
-    wget https://upenn.box.com/shared/static/f7zt19d08c545qt3tcaeg7b37z6qafum.zip -O nnunet.zip && \
-    unzip -qq nnunet.zip && rm -rf nnunet.zip && \
-    wget https://upenn.box.com/shared/static/hhvn8nb9xtz6nxcilmdl8kbx9n1afkdu.zip -O ./fets_consensus_models.zip && \
-    unzip -qq fets_consensus_models.zip && rm -rf fets_consensus_models.zip
-
+RUN mkdir bin && cd bin && cmake -DCMAKE_INSTALL_PREFIX="./install/appdir/usr" -DITK_DIR="/CaPTk/bin/ITK-build" -DDCMTK_DIR="/CaPTk/bin/DCMTK-build" -DBUILD_TESTING=OFF .. && make -j$(nproc) && make install/strip 
+
+## Python package installation
+RUN apt-get install software-properties-common curl -y && \
+    add-apt-repository ppa:deadsnakes/ppa -y && apt-get update && \
+    apt-get install python3.8 python3.8-distutils -y && \
+    apt-get remove --purge python3.6 -y && \
+    apt autoremove -y && \
+    apt-get install python3.8-distutils -y && \
+    rm -fr /usr/bin/python /usr/bin/python3 /usr/bin/pip /usr/bin/pip3 && \
+    ln -s /usr/bin/python3.8 /usr/bin/python && ln -s /usr/bin/python3.8 /usr/bin/python3 && \
+    ln -s /usr/bin/pip3.8 /usr/bin/pip && ln -s /usr/bin/pip3.8 /usr/bin/pip3
+
+RUN curl -fSsL -O https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
+    python3.8 get-pip.py &&     rm get-pip.py
+
+RUN cd bin/install/appdir/usr/bin/ && pip install --upgrade pip wheel && pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu && pip install -e . && pip install setuptools-rust Cython scikit-build scikit-learn openvino==2023.0.1 openvino-dev==2023.0.1 && pip install -e .
+
 ### put together a data example that is already aligned and ready to invoke the brain extraction and tumor segmentation
 
 # set up the docker for GUI
@@ -71,4 +60,43 @@ ENV QT_GRAPHICSSYSTEM="native"
 RUN echo "Env paths\n" && echo $PATH && echo $LD_LIBRARY_PATH
 
 # define entry point
-ENTRYPOINT ["/Front-End/bin/install/appdir/usr/bin/FeTS_CLI_Segment"]
+ENTRYPOINT ["python", "/Front-End/bin/install/appdir/usr/bin/PrepareDataset.py"]
+
+FROM fets_base AS data_prep
+
+RUN find /Front-End/bin/install/appdir/usr/bin -type f \( -perm -u=x -o -type l \) -exec cp -P {} /usr/bin \;
+
+WORKDIR /
+
+COPY ./mlcubes/data_preparation/project/requirements.txt /project/requirements.txt 
+
+RUN pip install --upgrade pip
+
+RUN pip install -r /project/requirements.txt
+
+ENV LANG C.UTF-8
+
+RUN mkdir /project/stages
+
+RUN cp /Front-End/bin/install/appdir/usr/bin/*.py /project/stages/
+
+RUN cp -R /Front-End/bin/install/appdir/usr/bin/data_prep_models /project/stages/data_prep_models
+
+# Hotfix: install more recent version of GaNDLF for metrics generation
+RUN pip install git+https://github.com/mlcommons/GaNDLF@616b37bafad8f89d5c816a88f44fa30470601311
+
+# setup a separate env for nnunet
+RUN python -m venv /nnunet_env && /nnunet_env/bin/pip install --upgrade pip
+
+RUN /nnunet_env/bin/pip install torch==1.12.1+cu102 torchvision==0.13.1+cu102 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu102
+
+RUN /nnunet_env/bin/pip install git+https://github.com/MIC-DKFZ/nnUNet.git@nnunetv1
+
+ENV nnUNet_raw_data_base="/tmp/nnUNet_raw_data_base"
+ENV nnUNet_preprocessed="/tmp/nnUNet_preprocessed"
+# see https://docs.docker.com/config/containers/resource_constraints/#gpu for detailed explanation
+ENV CUDA_VISIBLE_DEVICES="0"
+
+COPY ./mlcubes/data_preparation/project /project
+
+ENTRYPOINT ["python", "/project/mlcube.py"]