increase acc (#2039)

* increase acc

* try 0.45

* @pytest

* @pytest

* try .50

* duration

* pytest

.circleci/config.yml

@@ -21,7 +21,7 @@ references:
      name: Testing
      command: |
        python --version ; pip --version ; pip list
-       py.test pytorch_lightning tests -v --doctest-modules --junitxml=test-reports/pytest_junit.xml
+       py.test pytorch_lightning tests -v --junitxml=test-reports/pytest_junit.xml
      no_output_timeout: 15m
 
   examples: &examples
@@ -30,7 +30,7 @@ references:
      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
+       py.test pl_examples -v --junitxml=test-reports/pytest_junit.xml
      no_output_timeout: 20m
 
   install_pkg: &install_pkg

.drone.yml

@@ -38,7 +38,7 @@ steps:
     #- pip install -r ./docs/requirements.txt --user -q
     - 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 benchmarks -v --doctest-modules #  --flake8
+    - coverage run --source pytorch_lightning -m py.test pytorch_lightning tests benchmarks -v  # --flake8
     #- cd docs; make doctest; make coverage
     - coverage report
     - codecov --token $CODECOV_TOKEN  # --pr $DRONE_PULL_REQUEST --build $DRONE_BUILD_NUMBER --branch $DRONE_BRANCH --commit $DRONE_COMMIT --tag $DRONE_TAG

.github/workflows/ci-testing.yml

@@ -112,7 +112,7 @@ jobs:
       run: |
         # tox --sitepackages
         # flake8 .
-        coverage run --source pytorch_lightning -m py.test pytorch_lightning tests -v --doctest-modules --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
+        coverage run --source pytorch_lightning -m py.test pytorch_lightning tests -v --junitxml=junit/test-results-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.requires }}.xml
         coverage report
 
     - name: Upload pytest test results

.run_local_tests.sh

@@ -12,7 +12,7 @@ rm -rf ./tests/cometruns*
 rm -rf ./tests/wandb*
 rm -rf ./tests/tests/*
 rm -rf ./lightning_logs
-python -m coverage run --source pytorch_lightning -m py.test pytorch_lightning tests pl_examples -v --doctest-modules --flake8 --durations=0
+python -m coverage run --source pytorch_lightning -m py.test pytorch_lightning tests pl_examples -v --flake8
 python -m coverage report -m
 
 # specific file

setup.cfg

@@ -6,12 +6,16 @@ norecursedirs =
 python_files =
     test_*.py
 # doctest_plus = disabled
-addopts = --strict
+addopts =
+    --strict
+    --doctest-modules
+    --durations=0
 markers =
     slow
     remote_data
     filterwarnings
     gpus_param_tests
+junit_duration_report = call
 
 [coverage:report]
 exclude_lines =

tests/README.md

@@ -40,7 +40,7 @@ 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-devel.txt)
-coverage run --source pytorch_lightning -m py.test pytorch_lightning tests examples -v --doctest-modules
+coverage run --source pytorch_lightning -m py.test pytorch_lightning tests examples -v
 
 # print coverage stats
 coverage report -m

tests/base/utils.py

@@ -25,7 +25,7 @@ def assert_speed_parity(pl_times, pt_times, num_epochs):
         f"lightning was slower than PT (threshold {max_diff_per_epoch})"
 
 
-def run_model_test_without_loggers(trainer_options, model, min_acc=0.30):
+def run_model_test_without_loggers(trainer_options, model, min_acc=0.50):
     reset_seed()
 
     # fit model
@@ -155,7 +155,7 @@ def load_model_from_checkpoint(root_weights_dir, module_class=EvalModelTemplate)
     return trained_model
 
 
-def run_prediction(dataloader, trained_model, dp=False, min_acc=0.3):
+def run_prediction(dataloader, trained_model, dp=False, min_acc=0.50):
     # run prediction on 1 batch
     for batch in dataloader:
         break

tests/trainer/test_dataloaders.py

@@ -248,9 +248,8 @@ def test_mixing_of_dataloader_options(tmpdir):
         f'`test_dataloaders` not initiated properly, got {trainer.test_dataloaders}'
 
 
+@pytest.mark.skip('TODO: speed up this test')
 def test_train_inf_dataloader_error(tmpdir):
-    pytest.skip('TODO: fix speed of this test')
-
     """Test inf train data loader (e.g. IterableDataset)"""
     model = EvalModelTemplate()
     model.train_dataloader = model.train_dataloader__infinite
@@ -261,9 +260,8 @@ def test_train_inf_dataloader_error(tmpdir):
         trainer.fit(model)
 
 
+@pytest.mark.skip('TODO: speed up this test')
 def test_val_inf_dataloader_error(tmpdir):
-    pytest.skip('TODO: fix speed of this test')
-
     """Test inf train data loader (e.g. IterableDataset)"""
     model = EvalModelTemplate()
     model.val_dataloader = model.val_dataloader__infinite
@@ -274,9 +272,8 @@ def test_val_inf_dataloader_error(tmpdir):
         trainer.fit(model)
 
 
+@pytest.mark.skip('TODO: speed up this test')
 def test_test_inf_dataloader_error(tmpdir):
-    pytest.skip('TODO: fix speed of this test')
-
     """Test inf train data loader (e.g. IterableDataset)"""
     model = EvalModelTemplate()
     model.test_dataloader = model.test_dataloader__infinite
@@ -288,9 +285,8 @@ def test_test_inf_dataloader_error(tmpdir):
 
 
 @pytest.mark.parametrize('check_interval', [50, 1.0])
+@pytest.mark.skip('TODO: speed up this test')
 def test_inf_train_dataloader(tmpdir, check_interval):
-    pytest.skip('TODO: fix speed of this test')
-
     """Test inf train data loader (e.g. IterableDataset)"""
 
     model = EvalModelTemplate()
@@ -307,9 +303,8 @@ def test_inf_train_dataloader(tmpdir, check_interval):
 
 
 @pytest.mark.parametrize('check_interval', [1.0])
+@pytest.mark.skip('TODO: speed up this test')
 def test_inf_val_dataloader(tmpdir, check_interval):
-    pytest.skip('TODO: fix speed of this test')
-
     """Test inf val data loader (e.g. IterableDataset)"""
 
     model = EvalModelTemplate()

tests/trainer/test_lr_finder.py

@@ -134,9 +134,8 @@ def test_call_to_trainer_method(tmpdir):
         'Learning rate was not altered after running learning rate finder'
 
 
+@pytest.mark.skip('TODO: speed up this test')
 def test_accumulation_and_early_stopping(tmpdir):
-    pytest.skip('TODO: speed up this test')
-
     """ Test that early stopping of learning rate finder works, and that
         accumulation also works for this feature """