def test_init_wrong_parameters(self, mock_model): """Ensure correct exceptions are raised when initializing with invalid args""" aiplatform.init(project=_TEST_PROJECT) with pytest.raises(ValueError, match=r"not a supported prediction type"): training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, prediction_type="abcdefg", ) with pytest.raises(ValueError, match=r"not a supported model_type for"): training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, prediction_type="classification", model_type=_TEST_MODEL_TYPE_IOD, ) with pytest.raises(ValueError, match=r"`base_model` is only supported"): training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, prediction_type=_TEST_PREDICTION_TYPE_IOD, base_model=mock_model, )
def test_splits_filter_incomplete( self, mock_pipeline_service_create, mock_pipeline_service_get, mock_dataset_image, mock_model_service_get, mock_model, ): """ Initiate aiplatform with encryption key name. Create and run an AutoML Video Classification training job, verify calls and return value """ aiplatform.init( project=_TEST_PROJECT, encryption_spec_key_name=_TEST_DEFAULT_ENCRYPTION_KEY_NAME, ) job = training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, base_model=mock_model ) with pytest.raises(ValueError): job.run( dataset=mock_dataset_image, model_display_name=_TEST_MODEL_DISPLAY_NAME, training_filter_split=_TEST_FILTER_SPLIT_TRAINING, validation_fraction_split=None, test_filter_split=_TEST_FILTER_SPLIT_TEST, disable_early_stopping=_TEST_TRAINING_DISABLE_EARLY_STOPPING, )
def test_run_called_twice_raises(self, mock_dataset_image, sync): aiplatform.init(project=_TEST_PROJECT) job = training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, ) job.run( dataset=mock_dataset_image, model_display_name=_TEST_MODEL_DISPLAY_NAME, training_fraction_split=_TEST_FRACTION_SPLIT_TRAINING, validation_fraction_split=_TEST_FRACTION_SPLIT_VALIDATION, test_fraction_split=_TEST_FRACTION_SPLIT_TEST, disable_early_stopping=_TEST_TRAINING_DISABLE_EARLY_STOPPING, sync=sync, ) with pytest.raises(RuntimeError): job.run( dataset=mock_dataset_image, model_display_name=_TEST_MODEL_DISPLAY_NAME, training_fraction_split=_TEST_FRACTION_SPLIT_TRAINING, validation_fraction_split=_TEST_FRACTION_SPLIT_VALIDATION, test_fraction_split=_TEST_FRACTION_SPLIT_TEST, sync=sync, )
def test_splits_default( self, mock_pipeline_service_create, mock_pipeline_service_get, mock_dataset_image, mock_model_service_get, mock_model, sync, ): """ Initiate aiplatform with encryption key name. Create and run an AutoML Video Classification training job, verify calls and return value """ aiplatform.init( project=_TEST_PROJECT, encryption_spec_key_name=_TEST_DEFAULT_ENCRYPTION_KEY_NAME, ) job = training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, base_model=mock_model) model_from_job = job.run( dataset=mock_dataset_image, model_display_name=_TEST_MODEL_DISPLAY_NAME, budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS, disable_early_stopping=_TEST_TRAINING_DISABLE_EARLY_STOPPING, sync=sync, create_request_timeout=None, ) if not sync: model_from_job.wait() true_managed_model = gca_model.Model( display_name=_TEST_MODEL_DISPLAY_NAME, description=mock_model._gca_resource.description, encryption_spec=_TEST_DEFAULT_ENCRYPTION_SPEC, ) true_input_data_config = gca_training_pipeline.InputDataConfig( dataset_id=mock_dataset_image.name, ) true_training_pipeline = gca_training_pipeline.TrainingPipeline( display_name=_TEST_DISPLAY_NAME, training_task_definition=schema.training_job.definition. automl_image_classification, training_task_inputs=_TEST_TRAINING_TASK_INPUTS_WITH_BASE_MODEL, model_to_upload=true_managed_model, input_data_config=true_input_data_config, encryption_spec=_TEST_DEFAULT_ENCRYPTION_SPEC, ) mock_pipeline_service_create.assert_called_once_with( parent=initializer.global_config.common_location_path(), training_pipeline=true_training_pipeline, timeout=None, )
def test_run_call_pipeline_if_no_model_display_name( self, mock_pipeline_service_create, mock_dataset_image, mock_model_service_get, sync, ): aiplatform.init(project=_TEST_PROJECT) job = training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, training_encryption_spec_key_name= _TEST_PIPELINE_ENCRYPTION_KEY_NAME, model_encryption_spec_key_name=_TEST_MODEL_ENCRYPTION_KEY_NAME, ) model_from_job = job.run( dataset=mock_dataset_image, training_fraction_split=_TEST_FRACTION_SPLIT_TRAINING, validation_fraction_split=_TEST_FRACTION_SPLIT_VALIDATION, test_fraction_split=_TEST_FRACTION_SPLIT_TEST, budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS, disable_early_stopping=_TEST_TRAINING_DISABLE_EARLY_STOPPING, ) if not sync: model_from_job.wait() true_fraction_split = gca_training_pipeline.FractionSplit( training_fraction=_TEST_FRACTION_SPLIT_TRAINING, validation_fraction=_TEST_FRACTION_SPLIT_VALIDATION, test_fraction=_TEST_FRACTION_SPLIT_TEST, ) # Test that if defaults to the job display name true_managed_model = gca_model.Model( display_name=_TEST_DISPLAY_NAME, encryption_spec=_TEST_MODEL_ENCRYPTION_SPEC) true_input_data_config = gca_training_pipeline.InputDataConfig( fraction_split=true_fraction_split, dataset_id=mock_dataset_image.name, ) true_training_pipeline = gca_training_pipeline.TrainingPipeline( display_name=_TEST_DISPLAY_NAME, training_task_definition=schema.training_job.definition. automl_image_classification, training_task_inputs=_TEST_TRAINING_TASK_INPUTS, model_to_upload=true_managed_model, input_data_config=true_input_data_config, encryption_spec=_TEST_PIPELINE_ENCRYPTION_SPEC, ) mock_pipeline_service_create.assert_called_once_with( parent=initializer.global_config.common_location_path(), training_pipeline=true_training_pipeline, )
def test_raises_before_run_is_called(self, mock_pipeline_service_create): aiplatform.init(project=_TEST_PROJECT) job = training_jobs.AutoMLImageTrainingJob(display_name=_TEST_DISPLAY_NAME,) with pytest.raises(RuntimeError): job.get_model() with pytest.raises(RuntimeError): job.has_failed with pytest.raises(RuntimeError): job.state
def test_init_all_parameters(self, mock_model): """Ensure all private members are set correctly at initialization""" aiplatform.init(project=_TEST_PROJECT) job = training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, prediction_type=_TEST_PREDICTION_TYPE_ICN, model_type=_TEST_MODEL_TYPE_MOBILE, base_model=mock_model, multi_label=True, ) assert job._display_name == _TEST_DISPLAY_NAME assert job._model_type == _TEST_MODEL_TYPE_MOBILE assert job._prediction_type == _TEST_PREDICTION_TYPE_ICN assert job._multi_label is True assert job._base_model == mock_model
def test_run_with_two_split_raises( self, mock_dataset_image, sync, ): aiplatform.init(project=_TEST_PROJECT) job = training_jobs.AutoMLImageTrainingJob(display_name=_TEST_DISPLAY_NAME,) with pytest.raises(ValueError): model_from_job = job.run( dataset=mock_dataset_image, model_display_name=_TEST_MODEL_DISPLAY_NAME, training_fraction_split=_TEST_FRACTION_SPLIT_TRAINING, validation_fraction_split=_TEST_FRACTION_SPLIT_VALIDATION, test_fraction_split=_TEST_FRACTION_SPLIT_TEST, training_filter_split=_TEST_FILTER_SPLIT_TRAINING, validation_filter_split=_TEST_FILTER_SPLIT_VALIDATION, test_filter_split=_TEST_FILTER_SPLIT_TEST, sync=sync, ) if not sync: model_from_job.wait()
def test_run_raises_if_pipeline_fails( self, mock_pipeline_service_create_and_get_with_fail, mock_dataset_image, sync ): aiplatform.init(project=_TEST_PROJECT) job = training_jobs.AutoMLImageTrainingJob(display_name=_TEST_DISPLAY_NAME,) with pytest.raises(RuntimeError): job.run( model_display_name=_TEST_MODEL_DISPLAY_NAME, dataset=mock_dataset_image, training_fraction_split=_TEST_FRACTION_SPLIT_TRAINING, validation_fraction_split=_TEST_FRACTION_SPLIT_VALIDATION, test_fraction_split=_TEST_FRACTION_SPLIT_TEST, sync=sync, ) if not sync: job.wait() with pytest.raises(RuntimeError): job.get_model()
def test_run_call_pipeline_service_create( self, mock_pipeline_service_create, mock_pipeline_service_get, mock_dataset_image, mock_model_service_get, mock_model, sync, ): """Create and run an AutoML ICN training job, verify calls and return value""" aiplatform.init( project=_TEST_PROJECT, encryption_spec_key_name=_TEST_DEFAULT_ENCRYPTION_KEY_NAME, ) job = training_jobs.AutoMLImageTrainingJob( display_name=_TEST_DISPLAY_NAME, base_model=mock_model, labels=_TEST_LABELS, ) model_from_job = job.run( dataset=mock_dataset_image, model_display_name=_TEST_MODEL_DISPLAY_NAME, model_labels=_TEST_MODEL_LABELS, training_filter_split=_TEST_FILTER_SPLIT_TRAINING, validation_filter_split=_TEST_FILTER_SPLIT_VALIDATION, test_filter_split=_TEST_FILTER_SPLIT_TEST, budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS, disable_early_stopping=_TEST_TRAINING_DISABLE_EARLY_STOPPING, sync=sync, ) if not sync: model_from_job.wait() true_filter_split = gca_training_pipeline.FilterSplit( training_filter=_TEST_FILTER_SPLIT_TRAINING, validation_filter=_TEST_FILTER_SPLIT_VALIDATION, test_filter=_TEST_FILTER_SPLIT_TEST, ) true_managed_model = gca_model.Model( display_name=_TEST_MODEL_DISPLAY_NAME, labels=mock_model._gca_resource.labels, description=mock_model._gca_resource.description, encryption_spec=_TEST_DEFAULT_ENCRYPTION_SPEC, ) true_input_data_config = gca_training_pipeline.InputDataConfig( filter_split=true_filter_split, dataset_id=mock_dataset_image.name, ) true_training_pipeline = gca_training_pipeline.TrainingPipeline( display_name=_TEST_DISPLAY_NAME, labels=_TEST_LABELS, training_task_definition=schema.training_job.definition.automl_image_classification, training_task_inputs=_TEST_TRAINING_TASK_INPUTS_WITH_BASE_MODEL, model_to_upload=true_managed_model, input_data_config=true_input_data_config, encryption_spec=_TEST_DEFAULT_ENCRYPTION_SPEC, ) mock_pipeline_service_create.assert_called_once_with( parent=initializer.global_config.common_location_path(), training_pipeline=true_training_pipeline, ) mock_model_service_get.assert_called_once_with( name=_TEST_MODEL_NAME, retry=base._DEFAULT_RETRY ) assert job._gca_resource is mock_pipeline_service_get.return_value assert model_from_job._gca_resource is mock_model_service_get.return_value assert job.get_model()._gca_resource is mock_model_service_get.return_value assert not job.has_failed assert job.state == gca_pipeline_state.PipelineState.PIPELINE_STATE_SUCCEEDED