ml-agents/Dockerfile

FROM nvidia/cudagl:9.0-devel-ubuntu16.04

# TensorFlow version is tightly coupled to CUDA and cuDNN so it should be selected carefully
ENV TENSORFLOW_VERSION=1.12.0
ENV PYTORCH_VERSION=1.1.0
ENV TORCHVISION_VERSION=0.2.2.post3
ENV CUDNN_VERSION=7.4.1.5-1+cuda9.0
ENV NCCL_VERSION=2.3.7-1+cuda9.0

# Set default shell to /bin/bash
SHELL ["/bin/bash", "-cu"]

# ensure local python is preferred over distribution python
ENV PATH /usr/local/bin:$PATH

# http://bugs.python.org/issue19846
# > At the moment, setting "LANG=C" on a Linux system *fundamentally breaks Python 3*, and that's not OK.
ENV LANG C.UTF-8

# runtime dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
		ca-certificates \
		libexpat1 \
		libffi6 \
		libgdbm3 \
		libreadline6 \
		libsqlite3-0 \
		libssl1.0.0 \
	&& rm -rf /var/lib/apt/lists/*

ENV GPG_KEY 0D96DF4D4110E5C43FBFB17F2D347EA6AA65421D
ENV PYTHON_VERSION 3.6.4

RUN set -ex \
	&& buildDeps=" \
		dpkg-dev \
		gcc \
		libbz2-dev \
		libc6-dev \
		libexpat1-dev \
		libffi-dev \
		libgdbm-dev \
		liblzma-dev \
		libncursesw5-dev \
		libreadline-dev \
		libsqlite3-dev \
		libssl-dev \
		make \
		tcl-dev \
		tk-dev \
		wget \
		xz-utils \
		zlib1g-dev \
# as of Stretch, "gpg" is no longer included by default
		$(command -v gpg > /dev/null || echo 'gnupg dirmngr') \
	" \
	&& apt-get update && apt-get install -y $buildDeps --no-install-recommends && rm -rf /var/lib/apt/lists/* \
	\
	&& wget -O python.tar.xz "https://www.python.org/ftp/python/${PYTHON_VERSION%%[a-z]*}/Python-$PYTHON_VERSION.tar.xz" \
	&& wget -O python.tar.xz.asc "https://www.python.org/ftp/python/${PYTHON_VERSION%%[a-z]*}/Python-$PYTHON_VERSION.tar.xz.asc" \
	&& export GNUPGHOME="$(mktemp -d)" \
	&& gpg --keyserver ha.pool.sks-keyservers.net --recv-keys "$GPG_KEY" \
	&& gpg --batch --verify python.tar.xz.asc python.tar.xz \
	&& rm -rf "$GNUPGHOME" python.tar.xz.asc \
	&& mkdir -p /usr/src/python \
	&& tar -xJC /usr/src/python --strip-components=1 -f python.tar.xz \
	&& rm python.tar.xz \
	\
	&& cd /usr/src/python \
	&& gnuArch="$(dpkg-architecture --query DEB_BUILD_GNU_TYPE)" \
	&& ./configure \
		--build="$gnuArch" \
		--enable-loadable-sqlite-extensions \
		--enable-shared \
		--with-system-expat \
		--with-system-ffi \
		--without-ensurepip \
	&& make -j "$(nproc)" \
	&& make install \
	&& ldconfig \
	\
	&& apt-get purge -y --auto-remove $buildDeps \
	\
	&& find /usr/local -depth \
		\( \
			\( -type d -a \( -name test -o -name tests \) \) \
			-o \
			\( -type f -a \( -name '*.pyc' -o -name '*.pyo' \) \) \
		\) -exec rm -rf '{}' + \
	&& rm -rf /usr/src/python

# make some useful symlinks that are expected to exist
RUN cd /usr/local/bin \
	&& ln -s idle3 idle \
	&& ln -s pydoc3 pydoc \
	&& ln -s python3 python \
	&& ln -s python3-config python-config

# if this is called "PIP_VERSION", pip explodes with "ValueError: invalid truth value '<VERSION>'"
ENV PYTHON_PIP_VERSION 9.0.3

RUN set -ex; \
	\
	apt-get update; \
	apt-get install -y --no-install-recommends wget; \
	rm -rf /var/lib/apt/lists/*; \
	\
	wget -O get-pip.py 'https://bootstrap.pypa.io/get-pip.py'; \
	\
	apt-get purge -y --auto-remove wget; \
	\
	python get-pip.py \
		--disable-pip-version-check \
		--no-cache-dir \
		"pip==$PYTHON_PIP_VERSION" \
	; \
	pip --version; \
	\
	find /usr/local -depth \
		\( \
			\( -type d -a \( -name test -o -name tests \) \) \
			-o \
			\( -type f -a \( -name '*.pyc' -o -name '*.pyo' \) \) \
		\) -exec rm -rf '{}' +; \
	rm -f get-pip.py


RUN apt-get update && apt-get install -y --allow-downgrades --allow-change-held-packages --no-install-recommends \
        build-essential \
        cmake \
        g++-4.8 \
        git \
        curl \
        vim \
        wget \
        ca-certificates \
        libcudnn7=${CUDNN_VERSION} \
        libnccl2=${NCCL_VERSION} \
        libnccl-dev=${NCCL_VERSION} \
        libjpeg-dev \
        libpng-dev \
        librdmacm1 \
        libibverbs1 \
        libibverbs-dev \
        xvfb

# Install TensorFlow
RUN pip install future typing
RUN pip install numpy \
        tensorflow-gpu==${TENSORFLOW_VERSION} \
        keras \
        h5py

# Install Open MPI
RUN mkdir /tmp/openmpi && \
    cd /tmp/openmpi && \
    wget https://www.open-mpi.org/software/ompi/v4.0/downloads/openmpi-4.0.0.tar.gz && \
    tar zxf openmpi-4.0.0.tar.gz && \
    cd openmpi-4.0.0 && \
    ./configure --enable-orterun-prefix-by-default && \
    make -j $(nproc) all && \
    make install && \
    ldconfig && \
    rm -rf /tmp/openmpi


# Install Horovod, temporarily using CUDA stubs
RUN ldconfig /usr/local/cuda-9.0/targets/x86_64-linux/lib/stubs && \
    HOROVOD_GPU_ALLREDUCE=NCCL HOROVOD_WITH_TENSORFLOW=1 pip install --no-cache-dir horovod && \
    ldconfig

# Install OpenSSH for MPI to communicate between containers
RUN apt-get install -y --no-install-recommends openssh-client openssh-server && \
    mkdir -p /var/run/sshd

# Allow OpenSSH to talk to containers without asking for confirmation
RUN 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

# Install ml-agents-envs package locally
COPY ml-agents-envs /ml-agents-envs
WORKDIR /ml-agents-envs
RUN pip install -e .

# Install ml-agents package next
COPY ml-agents /ml-agents
WORKDIR /ml-agents
RUN pip install -e .

# setup google-cloud-sdk, which is used to copy files to gcs after the training is finished
RUN apt-get install --yes --no-install-recommends \
    ca-certificates \
    curl \
  && echo "deb http://packages.cloud.google.com/apt cloud-sdk-xenial main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list \
  && curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key add - \
  && apt-get update \
  && apt-get install --yes google-cloud-sdk \
  && apt-get clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*

COPY unity-volume /unity-volume
RUN chmod +x /unity-volume/*.x86_64

CMD ["/bin/bash"]