environments automl dnn vision gpu

automl-dnn-vision-gpu

Overview

GPU based environment for finetuning AutoML legacy models for image tasks.

Version: 75

Tags

OS : Ubuntu20.04 Training Preview

View in Studio: https://ml.azure.com/registries/azureml/environments/automl-dnn-vision-gpu/version/75

Docker image: mcr.microsoft.com/azureml/curated/automl-dnn-vision-gpu:75

Docker build context

Dockerfile

FROM mcr.microsoft.com/aifx/acpt/stable-ubuntu2204-cu118-py310-torch271:biweekly.202512.3


ENV AZUREML_CONDA_ENVIRONMENT_PATH /azureml-envs/azureml-automl-dnn-vision-gpu
# Prepend path to AzureML conda environment
ENV PATH $AZUREML_CONDA_ENVIRONMENT_PATH/bin:$PATH

COPY --from=mcr.microsoft.com/azureml/mlflow-ubuntu20.04-py38-cpu-inference:20250506.v1 /var/mlflow_resources/ /var/mlflow_resources/

ENV MLFLOW_MODEL_FOLDER="mlflow-model"
# ENV AML_APP_ROOT="/var/mlflow_resources"
# ENV AZUREML_ENTRY_SCRIPT="mlflow_score_script.py"

# Inference requirements
COPY --from=mcr.microsoft.com/azureml/o16n-base/python-assets:20250310.v1 /artifacts /var/
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        libcurl4 \
        liblttng-ust1 \
        libunwind8 \
        libxml++2.6-2v5 \
        nginx-light \
        psmisc \
        rsyslog \
        runit \
        libc-bin \
        dpkg-dev \
        libssl-dev \
        dpkg \
        dotnet-hostfxr-8.0 \
        dotnet-host-8.0 \
        dotnet-runtime-8.0 \
        binutils \
        binutils-common \
        binutils-x86-64-linux-gnu \
        libbinutils \
        libctf0 \
        libctf-nobfd0 \
        libc6 \
        libc6-dev \
        libc-dev-bin \
        libssh-4 \
        libxml2 \
        linux-libc-dev \
        linux-headers-generic \
        locales \
        openssl \
        unzip && \
    apt-get clean && rm -rf /var/lib/apt/lists/* && \
    cp /var/configuration/rsyslog.conf /etc/rsyslog.conf && \
    cp /var/configuration/nginx.conf /etc/nginx/sites-available/app && \
    ln -sf /etc/nginx/sites-available/app /etc/nginx/sites-enabled/app && \
    rm -f /etc/nginx/sites-enabled/default

# Upgrade sudo to patch known vulnerability
RUN apt-get update && \
    apt-get install -y sudo=1.9.9-1ubuntu2.5 && \
    apt-mark hold sudo && \
    apt-get clean && rm -rf /var/lib/apt/lists/* && \
    apt-get autoremove -y

ENV SVDIR=/var/runit
ENV WORKER_TIMEOUT=400
EXPOSE 5001 8883 8888

ENV ENABLE_METADATA=true

# try updating pip for base and ptca env using conda
RUN conda install pip -n base -y || true
RUN conda install pip -n ptca -y || true

# Create conda environment
COPY conda_dependencies.yaml .
RUN conda env create -p $AZUREML_CONDA_ENVIRONMENT_PATH -f conda_dependencies.yaml -q && \
    rm conda_dependencies.yaml && \
    conda run -p $AZUREML_CONDA_ENVIRONMENT_PATH && \
    conda clean -afy

# Install packages with torch packages separately to reduce layer size
RUN pip install --no-cache-dir \
                azureml-train-automl-client==1.61.0.post1 \
                azureml-train-automl-runtime==1.61.0 \
                azureml-automl-dnn-vision==1.61.0.post1

# vulnearbility fix
RUN pip install pyarrow==14.0.2
RUN pip install --upgrade torch==2.8.0 torchvision==0.23.0
RUN pip install --upgrade urllib3==2.6.0

# Update conda base and ptca envs
RUN /opt/conda/bin/pip install --upgrade requests urllib3 || true
RUN /opt/conda/envs/ptca/bin/pip install --upgrade torch==2.8.0 torchvision==0.23.0 || true
RUN /opt/conda/envs/ptca/bin/pip install --upgrade urllib3==2.6.0 || true

# Patch pillow vulnerability
RUN pip install --upgrade pillow==12.0.0
RUN /opt/conda/bin/pip install --upgrade pillow==12.0.0 || true
RUN /opt/conda/envs/ptca/bin/pip install --upgrade pillow==12.0.0 || true


ENV LD_LIBRARY_PATH $AZUREML_CONDA_ENVIRONMENT_PATH/lib:$LD_LIBRARY_PATH
# dummy number to change when needing to force rebuild without changing the definition: 1