Dockerfile-ROCm

FROM rocm/pytorch:rocm5.7_ubuntu20.04_py3.9_pytorch_2.0.1
LABEL github="https://github.com/mlcommons/GaNDLF"
LABEL docs="https://mlcommons.github.io/GaNDLF/"
LABEL version=1.0

# Quick start instructions on using Docker with ROCm: https://github.com/RadeonOpenCompute/ROCm-docker/blob/master/quick-start.md

# The base image contains ROCm, python 3.9 and pytorch already, no need to install those
RUN apt-get update && apt-get install -y software-properties-common
RUN add-apt-repository ppa:deadsnakes/ppa
RUN apt-get update &&  apt-get install -y  python3.9 python3-pip libjpeg8-dev zlib1g-dev python3-dev libpython3.9-dev libffi-dev libgl1
RUN python3.9 -m pip install --upgrade pip==24.0
RUN python3.9 -m pip install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/rocm5.7
RUN python3.9 -m pip install --upgrade pip && python3.9 -m pip install openvino-dev==2023.0.1 opencv-python-headless mlcube_docker
RUN apt-get update && apt-get install -y libgl1

# Do some dependency installation separately here to make layer caching more efficient
COPY ./setup.py ./setup.py
RUN python3.9 -c "from setup import requirements; file = open('requirements.txt', 'w'); file.writelines([req + '\n' for req in requirements]); file.close()" \
    && python3.9 -m pip install -r ./requirements.txt

COPY . /GaNDLF
WORKDIR /GaNDLF
RUN python3.9 -m pip install -e .

# Entrypoint forces all commands given via "docker run" to go through python, CMD forces the default entrypoint script argument to be gandlf run
# If a user calls "docker run gandlf:[tag] anonymize", it will resolve to running "gandlf anonymize" instead.
# CMD is inherently overridden by args to "docker run", entrypoint is constant.
ENTRYPOINT gandlf
CMD run


# The below force the container commands to run as a nonroot user with UID > 10000.
# This greatly reduces UID collision probability between container and host, helping prevent privilege escalation attacks.
# As a side benefit this also decreases the likelihood that users on a cluster won't be able to access their files.
# See https://github.com/hexops/dockerfile as a best practices guide.
#RUN addgroup --gid 10001 --system nonroot \
# && adduser  --uid 10000 --system --ingroup nonroot --home /home/nonroot nonroot
# 
#USER nonroot

# Prepare the container for possible model embedding later.
RUN mkdir /embedded_model