PyTorch 1.3.1

.gitignore

@@ -1 +1,2 @@
-.idea/
+.idea/
+.DS_Store

docker/1.3.1/py2/Dockerfile.cpu

@@ -0,0 +1,88 @@
+FROM ubuntu:16.04
+
+LABEL maintainer="Amazon AI"
+
+ARG PYTHON_VERSION=2.7
+ARG PYTORCH_VERSION=1.3.1
+ARG TORCHVISION_VERSION=0.4.2
+ARG MMS_VERSION=1.0.8
+
+# See http://bugs.python.org/issue19846
+ENV LANG C.UTF-8
+ENV LD_LIBRARY_PATH /opt/conda/lib/:$LD_LIBRARY_PATH
+ENV PATH /opt/conda/bin:$PATH
+ENV SAGEMAKER_SERVING_MODULE sagemaker_pytorch_serving_container.serving:main
+ENV TEMP=/home/model-server/tmp
+
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends \
+    build-essential \
+    ca-certificates \
+    cmake \
+    curl \
+    git \
+    jq \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    openjdk-8-jdk-headless \
+    vim \
+    wget \
+    zlib1g-dev
+
+
+RUN curl -o ~/miniconda.sh -O  https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh \
+ && chmod +x ~/miniconda.sh \
+ && ~/miniconda.sh -b -p /opt/conda \
+ && rm ~/miniconda.sh \
+ && /opt/conda/bin/conda update conda \
+ && /opt/conda/bin/conda install -y \
+    python=$PYTHON_VERSION \
+    cython==0.29.12 \
+    ipython==5.8.0 \
+    mkl-include==2019.4 \
+    mkl==2019.4 \
+    numpy==1.16.4 \
+    scipy==1.2.1 \
+    typing==3.7.4 \
+ && /opt/conda/bin/conda clean -ya
+
+RUN conda install -c \
+    conda-forge \
+    awscli==1.16.210 \
+    opencv==4.0.1 \
+ && conda install -y \
+    scikit-learn==0.20.3 \
+    pandas==0.24.2 \
+    pillow==6.1.0 \
+    h5py==2.9.0 \
+    requests==2.22.0 \
+ && conda install \
+    pytorch==$PYTORCH_VERSION \
+    torchvision==$TORCHVISION_VERSION cpuonly -c pytorch \
+ && conda clean -ya \
+ && pip install --upgrade pip --trusted-host pypi.org --trusted-host files.pythonhosted.org \
+ && pip install mxnet-model-server==$MMS_VERSION
+
+RUN useradd -m model-server \
+ && mkdir -p /home/model-server/tmp \
+ && chown -R model-server /home/model-server
+
+COPY docker/$PYTORCH_VERSION/py2/mms-entrypoint.py /usr/local/bin/dockerd-entrypoint.py
+COPY docker/$PYTORCH_VERSION/py2/config.properties /home/model-server
+COPY src/sagemaker_pytorch_serving_container/deep_learning_container.py /usr/local/bin/deep_learning_container.py
+
+RUN chmod +x /usr/local/bin/dockerd-entrypoint.py \
+ && chmod +x /usr/local/bin/deep_learning_container.py
+
+COPY dist/sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl
+RUN pip install --no-cache-dir \
+    /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl \
+ && rm /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl
+
+
+EXPOSE 8080 8081
+ENTRYPOINT ["python", "/usr/local/bin/dockerd-entrypoint.py"]
+CMD ["mxnet-model-server", "--start", "--mms-config", "/home/model-server/config.properties"]

docker/1.3.1/py2/Dockerfile.gpu

@@ -0,0 +1,112 @@
+FROM nvidia/cuda:10.1-cudnn7-devel-ubuntu16.04
+# NCCL_VERSION=2.4.7, CUDNN_VERSION=7.6.2.24
+LABEL maintainer="Amazon AI"
+
+ARG PYTHON_VERSION=2.7
+ARG PYTORCH_VERSION=1.3.1
+ARG TORCHVISION_VERSION=0.4.2
+ARG MMS_VERSION=1.0.8
+
+# See http://bugs.python.org/issue19846
+ENV LANG C.UTF-8
+ENV LD_LIBRARY_PATH /opt/conda/lib/:$LD_LIBRARY_PATH
+ENV PATH /opt/conda/bin:$PATH
+ENV SAGEMAKER_SERVING_MODULE sagemaker_pytorch_serving_container.serving:main
+ENV TEMP=/home/model-server/tmp
+
+RUN apt-get update \
+ && apt-get install -y --allow-downgrades --allow-change-held-packages --no-install-recommends \
+    build-essential \
+    build-essential \
+    ca-certificates \
+    cmake \
+    curl \
+    git \
+    jq \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libgomp1 \
+    libibverbs-dev \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    openjdk-8-jdk-headless \
+    vim \
+    wget \
+    zlib1g-dev
+
+# Install OpenSSH, Allow OpenSSH to talk to containers without asking for confirmation
+RUN apt-get install -y --no-install-recommends \
+    openssh-client openssh-server \
+ && mkdir -p /var/run/sshd \
+ && cat /etc/ssh/ssh_config | grep -v StrictHostKeyChecking > /etc/ssh/ssh_config.new \
+ && echo "    StrictHostKeyChecking no" >> /etc/ssh/ssh_config.new \
+ && mv /etc/ssh/ssh_config.new /etc/ssh/ssh_config
+
+RUN curl -o ~/miniconda.sh -O  https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh  \
+ && chmod +x ~/miniconda.sh \
+ && ~/miniconda.sh -b -p /opt/conda \
+ && rm ~/miniconda.sh \
+ && /opt/conda/bin/conda update conda \
+ && /opt/conda/bin/conda install -y \
+    python=$PYTHON_VERSION \
+    cython==0.29.12 \
+    ipython==5.8.0 \
+    mkl-include==2019.4 \
+    mkl==2019.4 \
+    numpy==1.16.4 \
+    scipy==1.2.1 \
+    typing==3.7.4 \
+ && /opt/conda/bin/conda clean -ya
+
+
+RUN conda install -c \
+    pytorch magma-cuda100 \
+ && conda install -c \
+    conda-forge \
+    awscli==1.16.210 \
+    opencv==4.0.1 \
+ && conda install -y scikit-learn==0.20.3 \
+    h5py==2.9.0 \
+    pandas==0.24.2 \
+    pillow==6.1.0 \
+    requests==2.22.0 \
+ && conda install -c \
+    pytorch \
+    cudatoolkit=10.0 \
+    pytorch==$PYTORCH_VERSION \
+    torchvision==$TORCHVISION_VERSION \
+ && conda clean -ya \
+ && /opt/conda/bin/conda config --set ssl_verify False \
+ && pip install --upgrade pip --trusted-host pypi.org --trusted-host files.pythonhosted.org \
+ && pip install mxnet-model-server==$MMS_VERSION
+
+RUN useradd -m model-server \
+ && mkdir -p /home/model-server/tmp \
+ && chown -R model-server /home/model-server
+
+COPY docker/$PYTORCH_VERSION/py2/mms-entrypoint.py /usr/local/bin/dockerd-entrypoint.py
+COPY docker/$PYTORCH_VERSION/py2/config.properties /home/model-server
+COPY src/sagemaker_pytorch_serving_container/deep_learning_container.py /usr/local/bin/deep_learning_container.py
+
+RUN chmod +x /usr/local/bin/dockerd-entrypoint.py \
+ && chmod +x /usr/local/bin/deep_learning_container.py
+
+# Install OpenSSH for MPI to communicate between containers, Allow OpenSSH to talk to containers without asking for confirmation
+RUN apt-get install -y --no-install-recommends \
+    openssh-client openssh-server \
+ && mkdir -p /var/run/sshd \
+ && cat /etc/ssh/ssh_config | grep -v StrictHostKeyChecking > /etc/ssh/ssh_config.new \
+ && echo "    StrictHostKeyChecking no" >> /etc/ssh/ssh_config.new \
+ && mv /etc/ssh/ssh_config.new /etc/ssh/ssh_config
+
+# RUN pip install --no-cache-dir 'opencv-python>=4.0,<4.1'
+
+COPY dist/sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl
+RUN pip install --no-cache-dir \
+    /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl \
+ && rm /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl
+
+EXPOSE 8080 8081
+ENTRYPOINT ["python", "/usr/local/bin/dockerd-entrypoint.py"]
+CMD ["mxnet-model-server", "--start", "--mms-config", "/home/model-server/config.properties"]

docker/1.3.1/py2/config.properties

@@ -0,0 +1,26 @@
+vmargs=-Xmx128m -XX:-UseLargePages -XX:+UseG1GC -XX:MaxMetaspaceSize=32M -XX:MaxDirectMemorySize=10m -XX:+ExitOnOutOfMemoryError
+model_store=/opt/ml/model
+load_models=ALL
+inference_address=http://0.0.0.0:8080
+management_address=http://0.0.0.0:8081
+# management_address=unix:/tmp/management.sock
+# number_of_netty_threads=0
+# netty_client_threads=0
+# default_response_timeout=120
+# default_workers_per_model=0
+# job_queue_size=100
+# async_logging=false
+# number_of_gpu=1
+# cors_allowed_origin
+# cors_allowed_methods
+# cors_allowed_headers
+# keystore=src/test/resources/keystore.p12
+# keystore_pass=changeit
+# keystore_type=PKCS12
+# private_key_file=src/test/resources/key.pem
+# certificate_file=src/test/resources/certs.pem
+# max_response_size=6553500
+# max_request_size=6553500
+# blacklist_env_vars=
+# decode_input_request=false
+# enable_envvars_config=false

docker/1.3.1/py2/mms-entrypoint.py

@@ -0,0 +1,16 @@
+import shlex
+import subprocess
+import sys
+import os.path
+
+if not os.path.exists("/opt/ml/input/config"):
+    subprocess.call(['python', '/usr/local/bin/deep_learning_container.py', '&>/dev/null', '&'])
+
+if sys.argv[1] == 'serve':
+    from sagemaker_pytorch_serving_container import serving
+    serving.main()
+else:
+    subprocess.check_call(shlex.split(' '.join(sys.argv[1:])))
+
+# prevent docker exit
+subprocess.call(['tail', '-f', '/dev/null'])

docker/1.3.1/py3/Dockerfile.cpu

@@ -0,0 +1,87 @@
+FROM ubuntu:16.04
+
+LABEL maintainer="Amazon AI"
+
+ARG PYTHON_VERSION=3.6.6
+ARG PYTORCH_VERSION=1.3.1
+ARG TORCHVISION_VERSION=0.4.2
+ARG MMS_VERSION=1.0.8
+
+# See http://bugs.python.org/issue19846
+ENV LANG C.UTF-8
+ENV LD_LIBRARY_PATH /opt/conda/lib/:$LD_LIBRARY_PATH
+ENV PATH /opt/conda/bin:$PATH
+ENV SAGEMAKER_SERVING_MODULE sagemaker_pytorch_serving_container.serving:main
+ENV TEMP=/home/model-server/tmp
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    ca-certificates \
+    cmake \
+    curl \
+    git \
+    jq \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    openjdk-8-jdk-headless \
+    vim \
+    wget \
+    zlib1g-dev 
+
+RUN curl -o ~/miniconda.sh -O  https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh  \
+ && chmod +x ~/miniconda.sh \
+ && ~/miniconda.sh -b -p /opt/conda \
+ && rm ~/miniconda.sh \
+ && /opt/conda/bin/conda update conda \
+ && /opt/conda/bin/conda install -y \
+    python=$PYTHON_VERSION \
+    cython==0.29.12 \
+    ipython==7.7.0 \
+    mkl-include==2019.4 \
+    mkl==2019.4 \
+    numpy==1.16.4 \
+    scipy==1.3.0 \
+    typing==3.6.4 \
+ && /opt/conda/bin/conda clean -ya
+
+RUN conda install -c \
+    conda-forge \
+    awscli==1.16.210 \
+    opencv==4.0.1 \
+ && conda install -y \
+    scikit-learn==0.21.2 \
+    pandas==0.25.0 \
+    pillow==5.4.1 \
+    h5py==2.9.0 \
+    requests==2.22.0 \
+ && conda install \
+    pytorch==$PYTORCH_VERSION \
+    torchvision==$TORCHVISION_VERSION cpuonly -c pytorch \
+ && conda clean -ya \
+ && pip install --upgrade pip --trusted-host pypi.org --trusted-host files.pythonhosted.org \
+ && ln -s /opt/conda/bin/pip /usr/local/bin/pip3 \
+ && pip install mxnet-model-server==$MMS_VERSION
+
+RUN useradd -m model-server \
+ && mkdir -p /home/model-server/tmp \
+ && chown -R model-server /home/model-server
+
+COPY docker/$PYTORCH_VERSION/py3/mms-entrypoint.py /usr/local/bin/dockerd-entrypoint.py
+COPY docker/$PYTORCH_VERSION/py3/config.properties /home/model-server
+COPY src/sagemaker_pytorch_serving_container/deep_learning_container.py /usr/local/bin/deep_learning_container.py
+
+RUN chmod +x /usr/local/bin/dockerd-entrypoint.py \
+ && chmod +x /usr/local/bin/deep_learning_container.py
+
+COPY dist/sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl
+RUN pip install --no-cache-dir \
+    /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl \
+ && rm /sagemaker_pytorch_serving_container-1.2-py2.py3-none-any.whl
+
+
+EXPOSE 8080 8081
+ENTRYPOINT ["python", "/usr/local/bin/dockerd-entrypoint.py"]
+CMD ["mxnet-model-server", "--start", "--mms-config", "/home/model-server/config.properties"]