docker-python/tpu/Dockerfile at main · ZahidSQLDBA/docker-python · GitHub

History

73 lines (58 loc) · 3.38 KB

Raw

ARG BASE_IMAGE

FROM $BASE_IMAGE

# We need to define the ARG here to get the ARG below the FROM statement to access it within this build context

# See: https://docs.docker.com/engine/reference/builder/#understand-how-arg-and-from-interact

ARG PYTHON_WHEEL_VERSION

ARG PYTHON_VERSION_PATH

ARG TENSORFLOW_VERSION

ARG TORCH_LINUX_WHEEL_VERSION

ARG TORCH_VERSION

ARG TORCHVISION_VERSION

ARG TORCHAUDIO_VERSION

ENV ISTPUVM=1

ADD tpu/clean-layer.sh /tmp/clean-layer.sh

ADD patches/nbconvert-extensions.tpl /opt/kaggle/nbconvert-extensions.tpl

ADD patches/template_conf.json /opt/kaggle/conf.json

# Add BigQuery client proxy settings, kaggle secrets etc.

ENV PYTHONUSERBASE "/root/.local"

ADD patches/kaggle_secrets.py /root/.local/lib/${PYTHON_VERSION_PATH}/site-packages/kaggle_secrets.py

ADD patches/kaggle_session.py /root/.local/lib/${PYTHON_VERSION_PATH}/site-packages/kaggle_session.py

ADD patches/kaggle_web_client.py /root/.local/lib/${PYTHON_VERSION_PATH}/site-packages/kaggle_web_client.py

ADD patches/kaggle_datasets.py /root/.local/lib/${PYTHON_VERSION_PATH}/site-packages/kaggle_datasets.py

# Prereqs

# This is needed for cv2 (opencv-python):

# https://stackoverflow.com/questions/55313610/importerror-libgl-so-1-cannot-open-shared-object-file-no-such-file-or-directo

RUN apt-get update && apt-get install ffmpeg libsm6 libxext6 -y

# Install all the packages together for maximum compatibility.

# Additional useful packages should be added in the requirements.txt

# Bring in the requirements.txt and replace variables in it:

RUN apt-get install -y gettext

ADD tpu/requirements.txt /kaggle_requirements.txt

RUN envsubst < /kaggle_requirements.txt > /requirements.txt

# Install uv and then install the requirements:

RUN curl -LsSf https://astral.sh/uv/install.sh | sh

RUN export PATH="${HOME}/.local/bin:${PATH}" && uv pip install --system -r /requirements.txt --prerelease=allow --force-reinstall && \

/tmp/clean-layer.sh

ENV PATH="~/.local/bin:${PATH}"

# Try to force tensorflow to reliably install without breaking other installed deps

RUN export PATH="${HOME}/.local/bin:${PATH}" && \

uv pip freeze --system > /tmp/constraints.txt && \

uv pip install --system -c /tmp/constraints.txt tensorflow-tpu -f https://storage.googleapis.com/libtpu-tf-releases/index.html --force-reinstall && \

rm /tmp/constraints.txt

# Kaggle Model Hub patches:

ADD patches/kaggle_module_resolver.py /usr/local/lib/${PYTHON_VERSION_PATH}/site-packages/tensorflow_hub/kaggle_module_resolver.py

RUN sed -i '/from tensorflow_hub import uncompressed_module_resolver/a from tensorflow_hub import kaggle_module_resolver' /usr/local/lib/${PYTHON_VERSION_PATH}/site-packages/tensorflow_hub/config.py

RUN sed -i '/_install_default_resolvers()/a \ \ registry.resolver.add_implementation(kaggle_module_resolver.KaggleFileResolver())' /usr/local/lib/${PYTHON_VERSION_PATH}/site-packages/tensorflow_hub/config.py

# Set these env vars so that they don't produce errs calling the metadata server to load them:

ENV TPU_ACCELERATOR_TYPE=v3-8

ENV TPU_PROCESS_ADDRESSES=local

# Metadata

ARG GIT_COMMIT=unknown

ARG BUILD_DATE=unknown

LABEL git-commit=$GIT_COMMIT

LABEL build-date=$BUILD_DATE

ENV GIT_COMMIT=${GIT_COMMIT}

ENV BUILD_DATE=${BUILD_DATE}

LABEL kaggle-lang=python

# Correlate current release with the git hash inside the kernel editor by running `!cat /etc/git_commit`.

RUN echo "$GIT_COMMIT" > /etc/git_commit && echo "$BUILD_DATE" > /etc/build_date

docker-python/tpu/Dockerfile at main · ZahidSQLDBA/docker-python · GitHub

Expand file tree

Breadcrumbs

Dockerfile

Latest commit

History

Breadcrumbs

Dockerfile

File metadata and controls