lightning/.github/workflows/ci_pt-conda.yml

110 lines
4.3 KiB
YAML

name: PyTorch & Conda
# see: https://help.github.com/en/actions/reference/events-that-trigger-workflows
on: # Trigger the workflow on push or pull request, but only for the master branch
push:
branches: [master]
pull_request:
branches: [master]
jobs:
conda:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-20.04]
python-version: [3.7]
pytorch-version: [1.3, 1.4, 1.5, 1.6, 1.7]
# Timeout: https://stackoverflow.com/a/59076067/4521646
timeout-minutes: 35
steps:
- uses: actions/checkout@v2
- name: Setup PyTorch nightly channel
if: matrix.pytorch-version >= 1.7
run: |
# NOTE: this requires that the channel is presented in the yaml before packages
python -c "fname = 'environment.yml' ; req = open(fname).read().replace('pytorch', 'pytorch-nightly', 1) ; open(fname, 'w').write(req)"
- name: Setup PyTorch version
run: |
python -c "fname = 'environment.yml' ; req = open(fname).read().replace('torch>=1.3', 'torch=${{ matrix.pytorch-version }}') ; open(fname, 'w').write(req)"
cat environment.yml
- name: Cache conda
uses: actions/cache@v2
with:
path: ~/conda_pkgs_dir
key: ${{ runner.os }}-conda-py${{ matrix.python-version }}-pt${{ matrix.pytorch-version }}-${{ hashFiles('environment.yml') }}
restore-keys: |
${{ runner.os }}-conda-py${{ matrix.python-version }}-pt${{ matrix.pytorch-version }}-
# Add another cache for Pip as not all packages lives in Conda env
- name: Cache pip
uses: actions/cache@v2
with:
path: ~/.cache/pip
key: ${{ runner.os }}-pip-py${{ matrix.python-version }}-pt${{ matrix.pytorch-version }}-${{ hashFiles('requirements/base.txt') }}
restore-keys: |
${{ runner.os }}-pip-py${{ matrix.python-version }}-pt${{ matrix.pytorch-version }}-
# https://docs.conda.io/projects/conda/en/4.6.0/_downloads/52a95608c49671267e40c689e0bc00ca/conda-cheatsheet.pdf
# https://gist.github.com/mwouts/9842452d020c08faf9e84a3bba38a66f
- name: Setup Miniconda
uses: goanpeca/setup-miniconda@v1.6.0
env:
# MAKEFLAGS: "-j2"
HOROVOD_WITHOUT_MXNET: 1
HOROVOD_WITHOUT_TENSORFLOW: 1
with:
# auto-update-conda: true
auto-activate-base: false
# miniconda-version: 4.7.12 # This downloads a new conda, use the conda-version
conda-version: 4.7.12
python-version: ${{ matrix.python-version }}
environment-file: environment.yml
activate-environment: lightning
use-only-tar-bz2: true # IMPORTANT: This needs to be set for caching to work properly!
- name: Reinstall Horovod if necessary
if: runner.os != 'windows'
env:
HOROVOD_BUILD_ARCH_FLAGS: "-mfma"
run: |
HOROVOD_BUILT=$(python -c "import horovod.torch; horovod.torch.nccl_built(); print('SUCCESS')" || true)
if [[ $HOROVOD_BUILT != "SUCCESS" ]]; then
pip uninstall -y horovod
pip install --no-cache-dir $(grep "horovod" requirements/extra.txt)
fi
horovodrun --check-build
shell: bash -l {0}
- name: Cache datasets
uses: actions/cache@v2
with:
path: Datasets # This path is specific to Ubuntu
# Look to see if there is a cache hit for the corresponding requirements file
key: pl-dataset
- name: Tests
run: |
conda info
conda list
pip install --requirement requirements/test.txt
pip list
# NOTE: run coverage on tests does not propagare faler status for Win, https://github.com/nedbat/coveragepy/issues/1003
python -m pytest pytorch_lightning tests -v --durations=0 --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
# coverage report
shell: bash -l {0}
- name: Upload pytest test results
uses: actions/upload-artifact@master
with:
name: pytest-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}
path: junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
# Use always() to always run this step to publish test results when there are test failures
if: always()