CI: split tests-examples (Lightning-AI#990)

* CI: split tests-examples * tests without template * comment depends * CircleCI typo * add doctest * update test req. * CI tests * setup macOS * longer train * lover pred acc * fix model * rename default model * lower tests acc * typo * imports * fix test optimizer * update calls * fix Win * lower Drone image * fix call * pytorch image * fix test * add dev image * add dev image * update image * drone volume * lint * update test notes * rename tests/models >> tests/base * group models * conftest * optim imports * typos * fix import * fix tests * install AMP * tests * fix import
digital-idiot · Mar 25, 2020 · 45d671a · 45d671a
1 parent ced662f
commit 45d671a
Show file tree

Hide file tree

Showing 40 changed files with 298 additions and 282 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -11,7 +11,6 @@ references:
       name: Install Dependences
       command: |
         pip install "$TORCH_VERSION" --user
-        # this is temporal fix til test-tube is not merged and released
         pip install -r requirements.txt --user
         sudo pip install pytest pytest-cov pytest-flake8
         pip install -r ./tests/requirements.txt --user
@@ -21,7 +20,16 @@ references:
      name: Testing
      command: |
        python --version ; pip --version ; pip list
-       py.test pytorch_lightning tests pl_examples -v --doctest-modules --junitxml=test-reports/pytest_junit.xml
+       py.test pytorch_lightning tests -v --doctest-modules --junitxml=test-reports/pytest_junit.xml
+     no_output_timeout: 15m
+
+  examples: &examples
+   run:
+     name: PL Examples
+     command: |
+       pip install -r ./pl_examples/requirements.txt --user
+       python --version ; pip --version ; pip list
+       py.test pl_examples -v --doctest-modules --junitxml=test-reports/pytest_junit.xml
      no_output_timeout: 15m
 
   install_pkg: &install_pkg
@@ -84,10 +92,8 @@ jobs:
       - TORCH_VERSION: "torch"
     steps: &steps
       - checkout
-
       - *install_deps
       - *tests
-
       - store_test_results:
           path: test-reports
       - store_artifacts:
@@ -121,6 +127,16 @@ jobs:
       - TORCH_VERSION: "torch>=1.4, <1.5"
     steps: *steps
 
+  Examples:
+    docker:
+      - image: circleci/python:3.7
+    environment:
+        - TORCH_VERSION: "torch"
+    steps:
+      - checkout
+      - *install_deps
+      - *examples
+
   Install-pkg:
     docker:
       - image: circleci/python:3.7
@@ -141,3 +157,4 @@ workflows:
       - PyTorch-v1.3
       - PyTorch-v1.4
       - Install-pkg
+      - Examples
diff --git a/.drone.yml b/.drone.yml
@@ -6,7 +6,7 @@ name: torch-GPU
 
 steps:
 - name: testing
-  image: nvcr.io/nvidia/pytorch:20.02-py3
+  image: pytorch/pytorch:1.4-cuda10.1-cudnn7-runtime
   environment:
     SLURM_LOCALID: 0
     CODECOV_TOKEN:
@@ -16,12 +16,12 @@ steps:
     - pip install pip -U
     - pip --version
     - nvidia-smi
-    #- pip install torch==1.3
+    - bash ./tests/install_AMP.sh
     - pip install -r requirements.txt --user
     - pip install coverage pytest pytest-cov pytest-flake8 codecov
     - pip install -r ./tests/requirements.txt --user
     - pip list
     - python -c "import torch ; print(' & '.join([torch.cuda.get_device_name(i) for i in range(torch.cuda.device_count())]) if torch.cuda.is_available() else 'only CPU')"
-    - coverage run --source pytorch_lightning -m py.test pytorch_lightning tests pl_examples -v --doctest-modules #  --flake8
+    - coverage run --source pytorch_lightning -m py.test pytorch_lightning tests -v --doctest-modules #  --flake8
     - coverage report
     - codecov --token $CODECOV_TOKEN  # --pr $DRONE_PULL_REQUEST --build $DRONE_BUILD_NUMBER --branch $DRONE_BRANCH --commit $DRONE_COMMIT --tag $DRONE_TAG
diff --git a/.github/workflows/ci-testing.yml b/.github/workflows/ci-testing.yml
@@ -23,7 +23,7 @@ jobs:
         python-version: [3.6, 3.7]
         requires: ['minimal', 'latest']
 
-    # https://stackoverflow.com/a/59076067/4521646
+    # Timeout: https://stackoverflow.com/a/59076067/4521646
     timeout-minutes: 20
     steps:
     - uses: actions/checkout@v2
@@ -32,6 +32,12 @@ jobs:
       with:
         python-version: ${{ matrix.python-version }}
 
+    # Github Actions: Run step on specific OS: https://stackoverflow.com/a/57948488/4521646
+    - name: Setup macOS
+      if: runner.os == 'macOS'
+      run: |
+        brew install libomp  # https://github.com/pytorch/pytorch/issues/20030
+
     - name: Set min. dependencies
       if: matrix.requires == 'minimal'
       run: |
@@ -71,7 +77,7 @@ jobs:
       run: |
         # tox --sitepackages
         # flake8 .
-        coverage run --source pytorch_lightning -m py.test pytorch_lightning tests pl_examples -v --doctest-modules --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}.xml
+        coverage run --source pytorch_lightning -m py.test pytorch_lightning tests -v --doctest-modules --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}.xml
         coverage report
 
     - name: Upload pytest test results

diff --git a/.markdownlint.yml b/.markdownlint.yml
diff --git a/.run_local_tests.sh b/.run_local_tests.sh
@@ -12,5 +12,5 @@ rm -rf ./tests/cometruns*
 rm -rf ./tests/wandb*
 rm -rf ./tests/tests/*
 rm -rf ./lightning_logs
-coverage run --source pytorch_lightning -m py.test pytorch_lightning tests pl_examples -v --doctest-modules --flake8
-coverage report -m
+python -m coverage run --source pytorch_lightning -m py.test pytorch_lightning tests pl_examples -v --doctest-modules --flake8
+python -m coverage report -m
diff --git a/environment.yml b/environment.yml
@@ -1,4 +1,6 @@
+# This is Conda environment file
 # Usage: `conda env update -f environment.yml`
+
 channels:
     - conda-forge
     - pytorch

diff --git a/pl_examples/basic_examples/lightning_module_template.py b/pl_examples/basic_examples/lightning_module_template.py
@@ -19,7 +19,24 @@
 
 class LightningTemplateModel(LightningModule):
     """
-    Sample model to show how to define a template
+    Sample model to show how to define a template.
+
+    Example:
+
+        >>> # define simple Net for MNIST dataset
+        >>> params = dict(
+        ...     drop_prob=0.2,
+        ...     batch_size=2,
+        ...     in_features=28 * 28,
+        ...     learning_rate=0.001 * 8,
+        ...     optimizer_name='adam',
+        ...     data_root='./datasets',
+        ...     out_features=10,
+        ...     hidden_dim=1000,
+        ... )
+        >>> from argparse import Namespace
+        >>> hparams = Namespace(**params)
+        >>> model = LightningTemplateModel(hparams)
     """
 
     def __init__(self, hparams):

diff --git a/pl_examples/full_examples/semantic_segmentation/models/unet/model.py b/pl_examples/full_examples/semantic_segmentation/models/unet/model.py
@@ -9,9 +9,9 @@ class UNet(nn.Module):
     Link - https://arxiv.org/abs/1505.04597
 
     Parameters:
-    num_classes (int) - Number of output classes required (default 19 for KITTI dataset)
-    bilinear (bool) - Whether to use bilinear interpolation or transposed
-    convolutions for upsampling.
+        num_classes (int) - Number of output classes required (default 19 for KITTI dataset)
+        bilinear (bool) - Whether to use bilinear interpolation or transposed
+        convolutions for upsampling.
     '''
 
     def __init__(self, num_classes=19, bilinear=False):

diff --git a/pytorch_lightning/core/lightning.py b/pytorch_lightning/core/lightning.py
@@ -7,8 +7,8 @@
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 import torch
-from torch import Tensor
 import torch.distributed as torch_distrib
+from torch import Tensor
 from torch.nn.parallel import DistributedDataParallel
 from torch.optim import Adam
 from torch.optim.optimizer import Optimizer

diff --git a/requirements-extra.txt b/requirements-extra.txt
@@ -1,3 +1,5 @@
+# extended list of package dependencies to reach full functionality
+
 neptune-client>=0.4.4
 comet-ml>=1.0.56
 mlflow>=1.0.0

diff --git a/requirements.txt b/requirements.txt
@@ -1,3 +1,5 @@
+# the default package dependencies
+
 tqdm>=4.41.0
 numpy>=1.16.4
 torch>=1.1

diff --git a/setup.cfg b/setup.cfg
@@ -5,7 +5,7 @@ norecursedirs =
     build
 python_files =
     test_*.py
-doctest_plus = disabled
+# doctest_plus = disabled
 addopts = --strict
 markers =
     slow
@@ -41,7 +41,7 @@ ignore =
 # setup.cfg or tox.ini
 [check-manifest]
 ignore =
-    .travis.yml
+    *.yml
     tox.ini
     .github
     .github/*
@@ -51,3 +51,9 @@ ignore =
 license_file = LICENSE
 # long_description = file:README.md
 # long_description_content_type = text/markdown
+
+[pydocstyle]
+convention = pep257
+# D104, D107: Ignore missing docstrings in __init__ files and methods.
+# D202: Ignore a blank line after docstring (collision with Python Black in decorators)
+add-ignore = D104, D107, D202
diff --git a/tests/Dockerfile b/tests/Dockerfile
@@ -0,0 +1,7 @@
+ARG TORCH_VERSION=1.4
+ARG CUDA_VERSION=10.1
+
+FROM pytorch/pytorch:${TORCH_VERSION}-cuda${CUDA_VERSION}-cudnn7-runtime
+
+# Install AMP
+RUN bash ./tests/install_AMP.sh
diff --git a/tests/README.md b/tests/README.md
@@ -13,8 +13,8 @@ To run all tests do the following:
 git clone https://github.com/PyTorchLightning/pytorch-lightning
 cd pytorch-lightning
 
-# install module locally
-pip install -e .
+# install AMP support
+bash tests/install_AMP.sh
 
 # install dev deps
 pip install -r tests/requirements.txt
@@ -36,15 +36,13 @@ Make sure to run coverage on a GPU machine with at least 2 GPUs and NVIDIA apex
 cd pytorch-lightning
 
 # generate coverage (coverage is also installed as part of dev dependencies under tests/requirements.txt)
-pip install coverage
 coverage run --source pytorch_lightning -m py.test pytorch_lightning tests examples -v --doctest-modules
 
 # print coverage stats
 coverage report -m
 
-# exporting resulys
+# exporting results
 coverage xml
-codecov -t 17327163-8cca-4a5d-86c8-ca5f2ef700bc  -v
 ```
 
 
diff --git a/tests/base/__init__.py b/tests/base/__init__.py
@@ -0,0 +1,57 @@
+"""Models for testing."""
+
+import torch
+
+from tests.base.models import TestModelBase, DictHparamsModel
+from tests.base.mixins import (
+    LightEmptyTestStep,
+    LightValidationStepMixin,
+    LightValidationMixin,
+    LightValidationStepMultipleDataloadersMixin,
+    LightValidationMultipleDataloadersMixin,
+    LightTestStepMixin,
+    LightTestMixin,
+    LightTestStepMultipleDataloadersMixin,
+    LightTestMultipleDataloadersMixin,
+    LightTestFitSingleTestDataloadersMixin,
+    LightTestFitMultipleTestDataloadersMixin,
+    LightValStepFitSingleDataloaderMixin,
+    LightValStepFitMultipleDataloadersMixin,
+    LightTrainDataloader,
+    LightTestDataloader,
+    LightInfTrainDataloader,
+    LightInfValDataloader,
+    LightInfTestDataloader,
+    LightTestOptimizerWithSchedulingMixin,
+    LightTestMultipleOptimizersWithSchedulingMixin,
+    LightTestOptimizersWithMixedSchedulingMixin,
+    LightTestReduceLROnPlateauMixin
+)
+
+
+class LightningTestModel(LightTrainDataloader,
+                         LightValidationMixin,
+                         LightTestMixin,
+                         TestModelBase):
+    """Most common test case. Validation and test dataloaders."""
+
+    def on_training_metrics(self, logs):
+        logs['some_tensor_to_test'] = torch.rand(1)
+
+
+class LightningTestModelWithoutHyperparametersArg(LightningTestModel):
+    """ without hparams argument in constructor """
+
+    def __init__(self):
+        import tests.base.utils as tutils
+
+        # the user loads the hparams in some other way
+        hparams = tutils.get_default_hparams()
+        super().__init__(hparams)
+
+
+class LightningTestModelWithUnusedHyperparametersArg(LightningTestModelWithoutHyperparametersArg):
+    """ has hparams argument in constructor but is not used """
+
+    def __init__(self, hparams):
+        super().__init__()
diff --git a/tests/models/debug.py → tests/base/debug.py b/tests/models/debug.py → tests/base/debug.py
@@ -7,7 +7,7 @@
 
 
 # from test_models import assert_ok_test_acc, load_model, \
-#     clear_save_dir, get_test_tube_logger, get_hparams, init_save_dir, \
+#     clear_save_dir, get_default_testtube_logger, get_default_hparams, init_save_dir, \
 #     init_checkpoint_callback, reset_seed, set_random_master_port
 
 

diff --git a/tests/models/mixins.py → tests/base/mixins.py b/tests/models/mixins.py → tests/base/mixins.py
diff --git a/tests/models/base.py → tests/base/models.py b/tests/models/base.py → tests/base/models.py
@@ -1,5 +1,6 @@
 import os
 from collections import OrderedDict
+from typing import Dict
 
 import torch
 import torch.nn as nn
@@ -8,7 +9,6 @@
 from torch.utils.data import DataLoader
 from torchvision import transforms
 from torchvision.datasets import MNIST
-from typing import Dict
 
 try:
     from test_tube import HyperOptArgumentParser
@@ -174,9 +174,8 @@ def configure_optimizers(self):
             optimizer = optim.LBFGS(self.parameters(), lr=self.hparams.learning_rate)
         else:
             optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
-
-        # test returning only 1 list instead of 2
-        return optimizer
+        scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)
+        return [optimizer], [scheduler]
 
     def prepare_data(self):
         transform = transforms.Compose([transforms.ToTensor(),
@@ -201,36 +200,3 @@ def _dataloader(self, train):
         )
 
         return loader
-
-    @staticmethod
-    def add_model_specific_args(parent_parser, root_dir):  # pragma: no-cover
-        """
-        Parameters you define here will be available to your model through self.hparams
-        :param parent_parser:
-        :param root_dir:
-        :return:
-        """
-        parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser])
-
-        # param overwrites
-        # parser.set_defaults(gradient_clip_val=5.0)
-
-        # network params
-        parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
-        parser.add_argument('--in_features', default=28 * 28, type=int)
-        parser.add_argument('--out_features', default=10, type=int)
-        # use 500 for CPU, 50000 for GPU to see speed difference
-        parser.add_argument('--hidden_dim', default=50000, type=int)
-        # data
-        parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
-        # training params (opt)
-        parser.opt_list('--learning_rate', default=0.001 * 8, type=float,
-                        options=[0.0001, 0.0005, 0.001, 0.005], tunable=False)
-        parser.opt_list('--optimizer_name', default='adam', type=str,
-                        options=['adam'], tunable=False)
-        # if using 2 nodes with 4 gpus each the batch size here
-        #  (256) will be 256 / (2*8) = 16 per gpu
-        parser.opt_list('--batch_size', default=256 * 8, type=int,
-                        options=[32, 64, 128, 256], tunable=False,
-                        help='batch size will be divided over all GPUs being used across all nodes')
-        return parser