Merge branch 'master' into feat/fsdp_2n

# Conflicts: # pytorch_lightning/accelerators/accelerator.py
Lightning-AI · Mar 18, 2021 · 4b94920 · 4b94920
2 parents 62fe5a4 + 4e9b453
commit 4b94920
Show file tree

Hide file tree

Showing 267 changed files with 5,834 additions and 9,032 deletions.
diff --git a/.github/workflows/ci_test-base.yml b/.github/workflows/ci_test-base.yml
@@ -51,9 +51,8 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade --user pip
-        pip install --requirement ./requirements.txt --quiet  --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --upgrade
-        pip install --requirement ./requirements/test.txt --quiet --upgrade-strategy only-if-needed
-        # pip install tox coverage
+        pip install --requirement ./requirements.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --upgrade
+        pip install "pytest>6.0" "pytest-cov>2.10" --upgrade-strategy only-if-needed
         python --version
         pip --version
         pip list
@@ -69,7 +68,7 @@ jobs:
     - name: Test Package [only]
       run: |
         # NOTE: run coverage on tests does not propagare faler status for Win, https://github.com/nedbat/coveragepy/issues/1003
-        coverage run --source pytorch_lightning -m pytest pytorch_lightning -v --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
+        python -m pytest pytorch_lightning -v --cov=pytorch_lightning --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
 
     - name: Upload pytest test results
       uses: actions/upload-artifact@v2

diff --git a/.github/workflows/ci_test-conda.yml b/.github/workflows/ci_test-conda.yml
@@ -27,33 +27,47 @@ jobs:
       run: |
         conda info
         conda list
+        # adjust versions according installed Torch version
+        python ./requirements/adjust_versions.py requirements/extra.txt
+        python ./requirements/adjust_versions.py requirements/examples.txt
         pip install --requirement requirements/devel.txt --upgrade-strategy only-if-needed
         pip list
 
     - name: Pull checkpoints from S3
-      # todo: consider adding coma caching, but ATM all models have less then 100KB
       run: |
         # enter legacy and update checkpoints from S3
         cd legacy
         curl https://pl-public-data.s3.amazonaws.com/legacy/checkpoints.zip --output checkpoints.zip
         unzip -o checkpoints.zip
         ls -l checkpoints/
 
-    # todo: require proper fix in docker image
-    - name: Hotfix dependency
-      run: |
-        pip install torchtext==0.6.0 -U
-      shell: bash
-
     - name: Tests
       run: |
         # 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=50 --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
+        python -m pytest pytorch_lightning tests --cov=pytorch_lightning -v --durations=50 --junitxml=junit/test-results-${{ runner.os }}-torch${{ matrix.pytorch-version }}.xml
       shell: bash -l {0}
 
-    - name: Upload pytest test results
+    - name: Upload pytest results
       uses: actions/upload-artifact@v2
       with:
         name: pytest-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}
         path: junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
       if: failure()
+
+    - name: Statistics
+      if: success()
+      run: |
+        coverage report
+        coverage xml
+
+    - name: Upload coverage to Codecov
+      uses: codecov/codecov-action@v1
+      if: always()
+      # see: https://github.com/actions/toolkit/issues/399
+      continue-on-error: true
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}
+        file: coverage.xml
+        flags: cpu,pytest,torch${{ matrix.pytorch-version }}
+        name: CPU-coverage
+        fail_ci_if_error: false
diff --git a/.github/workflows/ci_test-full.yml b/.github/workflows/ci_test-full.yml
@@ -17,10 +17,6 @@ jobs:
         os: [ubuntu-18.04, windows-2019, macOS-10.15]
         python-version: [3.6, 3.7, 3.8]
         requires: ['minimal', 'latest']
-        exclude:
-          # # todo: segmentation fault for minimal and hanging for latest
-          - python-version: 3.8
-            os: ubuntu-18.04
 
     # Timeout: https://stackoverflow.com/a/59076067/4521646
     timeout-minutes: 35  # TODO: the macOS is taking too long, probably caching did not work...
@@ -104,20 +100,17 @@ jobs:
         HOROVOD_WITHOUT_MXNET: 1
         HOROVOD_WITHOUT_TENSORFLOW: 1
       run: |
-        # python -m pip install --upgrade --user pip
-        pip install --requirement requirements.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --quiet --upgrade
-        pip install --requirement ./requirements/devel.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --quiet --upgrade
         python --version
         pip --version
+        # python -m pip install --upgrade --user pip
+        pip install --requirement requirements.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --upgrade
+        # adjust versions according installed Torch version
+        python ./requirements/adjust_versions.py requirements/extra.txt
+        python ./requirements/adjust_versions.py requirements/examples.txt
+        pip install --requirement ./requirements/devel.txt --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --upgrade
         pip list
       shell: bash
 
-    # todo: require proper fix in docker image
-    - name: Hotfix dependency
-      run: |
-        pip install torchtext==0.6.0 -U
-      shell: bash
-
     - name: Reinstall Horovod if necessary
       if: runner.os != 'windows'
       env:
@@ -141,14 +134,13 @@ jobs:
     - name: Tests
       run: |
         # NOTE: do not include coverage report here, see: https://github.com/nedbat/coveragepy/issues/1003
-        coverage run --source pytorch_lightning -m pytest pytorch_lightning tests -v --durations=50 --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
+        python -m pytest pytorch_lightning tests --cov=pytorch_lightning -v --durations=50 --junitxml=junit/test-results-${{ runner.os }}-py${{ matrix.python-version }}-${{ matrix.requires }}.xml
 
-    # todo: put this back just when TorchVision can download datasets
-    #- name: Examples
-    #  run: |
-    #    python -m pytest pl_examples -v --durations=10
+    - name: Examples
+      run: |
+        python -m pytest pl_examples -v --durations=10
 
-    - name: Upload pytest test results
+    - name: Upload pytest results
       uses: actions/upload-artifact@v2
       with:
         name: pytest-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}
@@ -169,6 +161,6 @@ jobs:
       with:
         token: ${{ secrets.CODECOV_TOKEN }}
         file: coverage.xml
-        flags: cpu,pytest
+        flags: cpu,pytest,python${{ matrix.python-version }}
         name: CPU-coverage
         fail_ci_if_error: false
diff --git a/.github/workflows/docs-checks.yml b/.github/workflows/docs-checks.yml
@@ -41,15 +41,15 @@ jobs:
 
       - name: Install dependencies
         run: |
+          python --version
+          pip --version
           # remove Horovod from requirements
           python -c "fname = 'requirements/extra.txt' ; lines = [line for line in open(fname).readlines() if not line.startswith('horovod')] ; open(fname, 'w').writelines(lines)"
           # python -m pip install --upgrade --user pip
           pip install --requirement requirements.txt --upgrade-strategy only-if-needed --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --quiet
           pip install --requirement requirements/extra.txt
           pip install --requirement requirements/loggers.txt
           pip install --requirement requirements/docs.txt
-          python --version
-          pip --version
           pip list
         shell: bash
 
@@ -84,12 +84,12 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --requirement requirements.txt --upgrade-strategy only-if-needed --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --quiet
+          python --version
+          pip --version
+          # pip install --requirement requirements.txt --upgrade-strategy only-if-needed --find-links https://download.pytorch.org/whl/cpu/torch_stable.html --quiet
           pip install --requirement requirements/docs.txt
           # install Texlive, see https://linuxconfig.org/how-to-install-latex-on-ubuntu-20-04-focal-fossa-linux
           sudo apt-get update && sudo apt-get install -y texlive-latex-extra dvipng texlive-pictures
-          python --version
-          pip --version
           pip list
         shell: bash
 

diff --git a/.github/workflows/events-nightly.yml b/.github/workflows/events-nightly.yml
@@ -102,8 +102,6 @@ jobs:
         id: extend
 
       - name: Publish CUDA to Docker Hub
-        # ToDo: extend also building for Nightly from pip
-        if: matrix.pytorch_version < 1.8
         # publish master/release
         uses: docker/build-push-action@v2
         with: