def infra_validate(
self,
serving_spec: infra_validator_pb2.ServingSpec,
validation_spec: Optional[
infra_validator_pb2.ValidationSpec] = None,
request_spec: Optional[infra_validator_pb2.RequestSpec] = None,
example_input=None):
"""Constructs an InfraValidator component.
No need to specify example_input if you've already specified it in `train()`, `tune()` or `evaluate_model()`.
Args:
example_input ([type], optional): A `ExampleInputs.{RAW_EXAMPLES, PREPROCESSED_EXAMPLES}` function reference which provides
the example input channel. Defaults to None, where the input channel is set to the transformed/preprocessed examples.
Returns: self
"""
args = {
'model': self.trainer.outputs['model'],
'serving_spec': serving_spec,
}
if validation_spec:
args['validation_spec'] = validation_spec
if request_spec:
args['request_spec'] = request_spec
if not example_input and self.cached_example_input:
args['examples'] = self.cached_example_input
elif example_input:
inputs = example_input(self)
args['examples'] = inputs
# unnecessary to assign `inputs` to `self.cached_example_input` here
# this is probably the last stop for the cached example input train
else:
args['examples'] = ExampleInputs.RAW_EXAMPLES(self)
self.infra_validator = InfraValidator(**args)
return self.infra_validator
def _create_pipeline(pipeline_name: Text, pipeline_root: Text, data_root: Text,
module_file: Text, serving_model_dir: Text,
metadata_path: Text,
direct_num_workers: int) -> pipeline.Pipeline:
"""Implements the Iris flowers pipeline with TFX."""
examples = external_input(data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
# Generates schema based on statistics files.
schema_gen = SchemaGen(statistics=statistics_gen.outputs['statistics'],
infer_feature_shape=True)
# Performs anomaly detection based on statistics and data schema.
example_validator = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=schema_gen.outputs['schema'])
# Performs transformations and feature engineering in training and serving.
transform = Transform(examples=example_gen.outputs['examples'],
schema=schema_gen.outputs['schema'],
module_file=module_file)
# Uses user-provided Python function that trains a model using TF-Learn.
trainer = Trainer(
module_file=module_file,
custom_executor_spec=executor_spec.ExecutorClassSpec(GenericExecutor),
examples=transform.outputs['transformed_examples'],
transform_graph=transform.outputs['transform_graph'],
schema=schema_gen.outputs['schema'],
train_args=trainer_pb2.TrainArgs(num_steps=2000),
eval_args=trainer_pb2.EvalArgs(num_steps=5))
# Get the latest blessed model for model validation.
model_resolver = ResolverNode(
instance_name='latest_blessed_model_resolver',
resolver_class=latest_blessed_model_resolver.
LatestBlessedModelResolver,
model=Channel(type=Model),
model_blessing=Channel(type=ModelBlessing))
# Uses TFMA to compute an evaluation statistics over features of a model and
# perform quality validation of a candidate model (compared to a baseline).
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(label_key='variety')],
slicing_specs=[tfma.SlicingSpec()],
metrics_specs=[
tfma.MetricsSpec(metrics=[
tfma.MetricConfig(
class_name='SparseCategoricalAccuracy',
threshold=tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={'value': 0.6}),
change_threshold=tfma.GenericChangeThreshold(
direction=tfma.MetricDirection.HIGHER_IS_BETTER,
absolute={'value': -1e-10})))
])
])
evaluator = Evaluator(
examples=example_gen.outputs['examples'],
model=trainer.outputs['model'],
baseline_model=model_resolver.outputs['model'],
# Change threshold will be ignored if there is no baseline (first run).
eval_config=eval_config)
# Performs infra validation of a candidate model to prevent unservable model
# from being pushed. This config will launch a model server of the latest
# TensorFlow Serving image in a local docker engine.
infra_validator = InfraValidator(
model=trainer.outputs['model'],
examples=example_gen.outputs['examples'],
serving_spec=infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
local_docker=infra_validator_pb2.LocalDockerConfig()),
request_spec=infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.
TensorFlowServingRequestSpec()))
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
pusher = Pusher(model=trainer.outputs['model'],
model_blessing=evaluator.outputs['blessing'],
infra_blessing=infra_validator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=serving_model_dir)))
return pipeline.Pipeline(
pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=[
example_gen,
statistics_gen,
schema_gen,
example_validator,
transform,
trainer,
model_resolver,
evaluator,
infra_validator,
pusher,
],
enable_cache=True,
metadata_connection_config=metadata.sqlite_metadata_connection_config(
metadata_path),
# TODO(b/142684737): The multi-processing API might change.
beam_pipeline_args=['--direct_num_workers=%d' % direct_num_workers],
)
def create_e2e_components(
pipeline_root: Text,
csv_input_location: Text,
transform_module: Text,
trainer_module: Text,
) -> List[BaseComponent]:
"""Creates components for a simple Chicago Taxi TFX pipeline for testing.
Args:
pipeline_root: The root of the pipeline output.
csv_input_location: The location of the input data directory.
transform_module: The location of the transform module file.
trainer_module: The location of the trainer module file.
Returns:
A list of TFX components that constitutes an end-to-end test pipeline.
"""
example_gen = CsvExampleGen(input_base=csv_input_location)
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
schema_gen = SchemaGen(statistics=statistics_gen.outputs['statistics'])
example_validator = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=schema_gen.outputs['schema'])
transform = Transform(examples=example_gen.outputs['examples'],
schema=schema_gen.outputs['schema'],
module_file=transform_module)
latest_model_resolver = resolver.Resolver(
strategy_class=latest_artifact_strategy.LatestArtifactStrategy,
latest_model=Channel(type=Model)).with_id('latest_model_resolver')
trainer = Trainer(
transformed_examples=transform.outputs['transformed_examples'],
schema=schema_gen.outputs['schema'],
base_model=latest_model_resolver.outputs['latest_model'],
transform_graph=transform.outputs['transform_graph'],
train_args=trainer_pb2.TrainArgs(num_steps=10),
eval_args=trainer_pb2.EvalArgs(num_steps=5),
module_file=trainer_module,
)
# Set the TFMA config for Model Evaluation and Validation.
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(signature_name='eval')],
metrics_specs=[
tfma.MetricsSpec(
metrics=[tfma.MetricConfig(class_name='ExampleCount')],
thresholds={
'accuracy':
tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={'value': 0.5}),
change_threshold=tfma.GenericChangeThreshold(
direction=tfma.MetricDirection.HIGHER_IS_BETTER,
absolute={'value': -1e-10}))
})
],
slicing_specs=[
tfma.SlicingSpec(),
tfma.SlicingSpec(feature_keys=['trip_start_hour'])
])
evaluator = Evaluator(examples=example_gen.outputs['examples'],
model=trainer.outputs['model'],
eval_config=eval_config)
infra_validator = InfraValidator(
model=trainer.outputs['model'],
examples=example_gen.outputs['examples'],
serving_spec=infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
kubernetes=infra_validator_pb2.KubernetesConfig()),
request_spec=infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.
TensorFlowServingRequestSpec()))
pusher = Pusher(
model=trainer.outputs['model'],
model_blessing=evaluator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=os.path.join(pipeline_root, 'model_serving'))))
return [
example_gen,
statistics_gen,
schema_gen,
example_validator,
transform,
latest_model_resolver,
trainer,
evaluator,
infra_validator,
pusher,
]
def _create_pipeline(pipeline_name: Text, pipeline_root: Text, data_root: Text,
module_file: Text, serving_model_dir: Text,
metadata_path: Text,
beam_pipeline_args: List[Text]) -> pipeline.Pipeline:
"""Implements the chicago taxi pipeline with TFX."""
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=data_root)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
# Generates schema based on statistics files.
schema_gen = SchemaGen(statistics=statistics_gen.outputs['statistics'],
infer_feature_shape=False)
# Performs anomaly detection based on statistics and data schema.
example_validator = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=schema_gen.outputs['schema'])
# Performs transformations and feature engineering in training and serving.
transform = Transform(examples=example_gen.outputs['examples'],
schema=schema_gen.outputs['schema'],
module_file=module_file)
# Uses user-provided Python function that implements a model using TF-Learn.
trainer = Trainer(
module_file=module_file,
transformed_examples=transform.outputs['transformed_examples'],
schema=schema_gen.outputs['schema'],
transform_graph=transform.outputs['transform_graph'],
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000))
# Get the latest blessed model for model validation.
model_resolver = ResolverNode(
instance_name='latest_blessed_model_resolver',
resolver_class=latest_blessed_model_resolver.
LatestBlessedModelResolver,
model=Channel(type=Model),
model_blessing=Channel(type=ModelBlessing))
# Uses TFMA to compute a evaluation statistics over features of a model and
# perform quality validation of a candidate model (compared to a baseline).
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(signature_name='eval')],
slicing_specs=[
tfma.SlicingSpec(),
tfma.SlicingSpec(feature_keys=['trip_start_hour'])
],
metrics_specs=[
tfma.MetricsSpec(
thresholds={
'accuracy':
tfma.config.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={'value': 0.6}),
# Change threshold will be ignored if there is no
# baseline model resolved from MLMD (first run).
change_threshold=tfma.GenericChangeThreshold(
direction=tfma.MetricDirection.HIGHER_IS_BETTER,
absolute={'value': -1e-10}))
})
])
evaluator = Evaluator(examples=example_gen.outputs['examples'],
model=trainer.outputs['model'],
baseline_model=model_resolver.outputs['model'],
eval_config=eval_config)
# Performs infra validation of a candidate model to prevent unservable model
# from being pushed.
infra_validator = InfraValidator(
model=trainer.outputs['model'],
examples=example_gen.outputs['examples'],
serving_spec=infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
local_docker=infra_validator_pb2.LocalDockerConfig()),
request_spec=infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.
TensorFlowServingRequestSpec()))
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
pusher = Pusher(model=trainer.outputs['model'],
model_blessing=evaluator.outputs['blessing'],
infra_blessing=infra_validator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=serving_model_dir)))
return pipeline.Pipeline(
pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=[
example_gen,
statistics_gen,
schema_gen,
example_validator,
transform,
trainer,
model_resolver,
evaluator,
infra_validator,
pusher,
],
enable_cache=True,
metadata_connection_config=metadata.sqlite_metadata_connection_config(
metadata_path),
beam_pipeline_args=beam_pipeline_args)
def create_pipeline(pipeline_name: Text,
pipeline_root: Text,
data_root_uri: data_types.RuntimeParameter,
train_steps: data_types.RuntimeParameter,
eval_steps: data_types.RuntimeParameter,
enable_tuning: bool,
ai_platform_training_args: Dict[Text, Text],
ai_platform_serving_args: Dict[Text, Text],
beam_pipeline_args: List[Text],
enable_cache: Optional[bool] = False) -> pipeline.Pipeline:
"""Trains and deploys the Keras Covertype Classifier with TFX and Kubeflow Pipeline on Google Cloud.
Args:
pipeline_name: name of the TFX pipeline being created.
pipeline_root: root directory of the pipeline. Should be a valid GCS path.
data_root_uri: uri of the dataset.
train_steps: runtime parameter for number of model training steps for the Trainer component.
eval_steps: runtime parameter for number of model evaluation steps for the Trainer component.
enable_tuning: If True, the hyperparameter tuning through CloudTuner is
enabled.
ai_platform_training_args: Args of CAIP training job. Please refer to
https://cloud.google.com/ml-engine/reference/rest/v1/projects.jobs#Job
for detailed description.
ai_platform_serving_args: Args of CAIP model deployment. Please refer to
https://cloud.google.com/ml-engine/reference/rest/v1/projects.models
for detailed description.
beam_pipeline_args: Optional list of beam pipeline options. Please refer to
https://cloud.google.com/dataflow/docs/guides/specifying-exec-params#setting-other-cloud-dataflow-pipeline-options.
When this argument is not provided, the default is to use GCP
DataflowRunner with 50GB disk size as specified in this function. If an
empty list is passed in, default specified by Beam will be used, which can
be found at
https://cloud.google.com/dataflow/docs/guides/specifying-exec-params#setting-other-cloud-dataflow-pipeline-options
enable_cache: Optional boolean
Returns:
A TFX pipeline object.
"""
# Brings data into the pipeline and splits the data into training and eval splits
output = example_gen_pb2.Output(split_config=example_gen_pb2.SplitConfig(
splits=[
example_gen_pb2.SplitConfig.Split(name='train', hash_buckets=4),
example_gen_pb2.SplitConfig.Split(name='eval', hash_buckets=1)
]))
examplegen = CsvExampleGen(input_base=data_root_uri, output_config=output)
# Computes statistics over data for visualization and example validation.
statisticsgen = StatisticsGen(examples=examplegen.outputs.examples)
# Generates schema based on statistics files. Even though, we use user-provided schema
# we still want to generate the schema of the newest data for tracking and comparison
schemagen = SchemaGen(statistics=statisticsgen.outputs.statistics)
# Import a user-provided schema
import_schema = ImporterNode(instance_name='import_user_schema',
source_uri=SCHEMA_FOLDER,
artifact_type=Schema)
# Performs anomaly detection based on statistics and data schema.
examplevalidator = ExampleValidator(
statistics=statisticsgen.outputs.statistics,
schema=import_schema.outputs.result)
# Performs transformations and feature engineering in training and serving.
transform = Transform(examples=examplegen.outputs.examples,
schema=import_schema.outputs.result,
module_file=TRANSFORM_MODULE_FILE)
# Tunes the hyperparameters for model training based on user-provided Python
# function. Note that once the hyperparameters are tuned, you can drop the
# Tuner component from pipeline and feed Trainer with tuned hyperparameters.
if enable_tuning:
# The Tuner component launches 1 AI Platform Training job for flock management.
# For example, 3 workers (defined by num_parallel_trials) in the flock
# management AI Platform Training job, each runs Tuner.Executor.
tuner = Tuner(
module_file=TRAIN_MODULE_FILE,
examples=transform.outputs.transformed_examples,
transform_graph=transform.outputs.transform_graph,
train_args={'num_steps': train_steps},
eval_args={'num_steps': eval_steps},
tune_args=tuner_pb2.TuneArgs(
# num_parallel_trials=3 means that 3 search loops are running in parallel.
num_parallel_trials=3),
custom_config={
# Configures Cloud AI Platform-specific configs. For details, see
# https://cloud.google.com/ai-platform/training/docs/reference/rest/v1/projects.jobs#traininginput.
ai_platform_trainer_executor.TRAINING_ARGS_KEY:
ai_platform_training_args
})
# Trains the model using a user provided trainer function.
trainer = Trainer(
custom_executor_spec=executor_spec.ExecutorClassSpec(
ai_platform_trainer_executor.GenericExecutor),
module_file=TRAIN_MODULE_FILE,
transformed_examples=transform.outputs.transformed_examples,
schema=import_schema.outputs.result,
transform_graph=transform.outputs.transform_graph,
hyperparameters=(tuner.outputs.best_hyperparameters
if enable_tuning else None),
train_args={'num_steps': train_steps},
eval_args={'num_steps': eval_steps},
custom_config={'ai_platform_training_args': ai_platform_training_args})
# Get the latest blessed model for model validation.
resolver = ResolverNode(instance_name='latest_blessed_model_resolver',
resolver_class=latest_blessed_model_resolver.
LatestBlessedModelResolver,
model=Channel(type=Model),
model_blessing=Channel(type=ModelBlessing))
# Uses TFMA to compute a evaluation statistics over features of a model.
accuracy_threshold = tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(lower_bound={'value': 0.5},
upper_bound={'value':
0.99}), )
metrics_specs = tfma.MetricsSpec(metrics=[
tfma.MetricConfig(class_name='SparseCategoricalAccuracy',
threshold=accuracy_threshold),
tfma.MetricConfig(class_name='ExampleCount')
])
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(label_key='Cover_Type')],
metrics_specs=[metrics_specs],
slicing_specs=[
tfma.SlicingSpec(),
tfma.SlicingSpec(feature_keys=['Wilderness_Area'])
])
evaluator = Evaluator(examples=examplegen.outputs.examples,
model=trainer.outputs.model,
baseline_model=resolver.outputs.model,
eval_config=eval_config)
# Validate model can be loaded and queried in sand-boxed environment
# mirroring production.
serving_config = infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
kubernetes=infra_validator_pb2.KubernetesConfig(),
)
validation_config = infra_validator_pb2.ValidationSpec(
max_loading_time_seconds=60,
num_tries=3,
)
request_config = infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServingRequestSpec(),
num_examples=3,
)
infravalidator = InfraValidator(
model=trainer.outputs.model,
examples=examplegen.outputs.examples,
serving_spec=serving_config,
validation_spec=validation_config,
request_spec=request_config,
)
# Checks whether the model passed the validation steps and pushes the model
# to CAIP Prediction if checks are passed.
pusher = Pusher(custom_executor_spec=executor_spec.ExecutorClassSpec(
ai_platform_pusher_executor.Executor),
model=trainer.outputs.model,
model_blessing=evaluator.outputs.blessing,
infra_blessing=infravalidator.outputs.blessing,
custom_config={
ai_platform_pusher_executor.SERVING_ARGS_KEY:
ai_platform_serving_args
})
components = [
examplegen, statisticsgen, schemagen, import_schema, examplevalidator,
transform, trainer, resolver, evaluator, infravalidator, pusher
]
if enable_tuning:
components.append(tuner)
return pipeline.Pipeline(pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=components,
enable_cache=enable_cache,
beam_pipeline_args=beam_pipeline_args)
def create_pipeline(pipeline_name: Text,
pipeline_root: Text,
data_root_uri,
trainer_config: TrainerConfig,
tuner_config: TunerConfig,
pusher_config: PusherConfig,
runtime_parameters_config: RuntimeParametersConfig = None,
str_runtime_parameters_supported = False,
int_runtime_parameters_supported = False,
local_run: bool = True,
beam_pipeline_args: Optional[List[Text]] = None,
enable_cache: Optional[bool] = True,
code_folder = '',
metadata_connection_config: Optional[metadata_store_pb2.ConnectionConfig] = None
) -> pipeline.Pipeline:
"""Trains and deploys the Keras Titanic Classifier with TFX and Kubeflow Pipeline on Google Cloud.
Args:
pipeline_name: name of the TFX pipeline being created.
pipeline_root: root directory of the pipeline. Should be a valid GCS path.
data_root_uri: uri of the dataset.
train_steps: runtime parameter for number of model training steps for the Trainer component.
eval_steps: runtime parameter for number of model evaluation steps for the Trainer component.
enable_tuning: If True, the hyperparameter tuning through CloudTuner is
enabled.
ai_platform_training_args: Args of CAIP training job. Please refer to
https://cloud.google.com/ml-engine/reference/rest/v1/projects.jobs#Job
for detailed description.
ai_platform_serving_args: Args of CAIP model deployment. Please refer to
https://cloud.google.com/ml-engine/reference/rest/v1/projects.models
for detailed description.
beam_pipeline_args: Optional list of beam pipeline options. Please refer to
https://cloud.google.com/dataflow/docs/guides/specifying-exec-params#setting-other-cloud-dataflow-pipeline-options.
When this argument is not provided, the default is to use GCP
DataflowRunner with 50GB disk size as specified in this function. If an
empty list is passed in, default specified by Beam will be used, which can
be found at
https://cloud.google.com/dataflow/docs/guides/specifying-exec-params#setting-other-cloud-dataflow-pipeline-options
enable_cache: Optional boolean
Returns:
A TFX pipeline object.
"""
#pydevd_pycharm.settrace('localhost', port=9091, stdoutToServer=True, stderrToServer=True)
absl.logging.info('pipeline_name: %s' % pipeline_name)
absl.logging.info('pipeline root: %s' % pipeline_root)
absl.logging.info('data_root_uri for training: %s' % data_root_uri)
absl.logging.info('train_steps for training: %s' % trainer_config.train_steps)
absl.logging.info('tuner_steps for tuning: %s' % tuner_config.tuner_steps)
absl.logging.info('eval_steps for evaluating: %s' % trainer_config.eval_steps)
absl.logging.info('os default list dir: %s' % os.listdir('.'))
schema_proper_folder = os.path.join(os.sep, code_folder, SCHEMA_FOLDER)
absl.logging.info('schema_proper_folder: %s' % schema_proper_folder)
preprocessing_proper_file = os.path.join(os.sep, code_folder, TRANSFORM_MODULE_FILE)
absl.logging.info('preprocessing_proper_file: %s' % preprocessing_proper_file)
model_proper_file = os.path.join(os.sep, code_folder, TRAIN_MODULE_FILE)
absl.logging.info('model_proper_file: %s' % model_proper_file)
hyperparameters_proper_folder = os.path.join(os.sep, code_folder, HYPERPARAMETERS_FOLDER)
absl.logging.info('hyperparameters_proper_folder: %s' % hyperparameters_proper_folder)
# Brings data into the pipeline and splits the data into training and eval splits
output_config = example_gen_pb2.Output(
split_config=example_gen_pb2.SplitConfig(splits=[
example_gen_pb2.SplitConfig.Split(name='train', hash_buckets=4),
example_gen_pb2.SplitConfig.Split(name='eval', hash_buckets=1)
]))
# examples = external_input(data_root_uri)
if str_runtime_parameters_supported and runtime_parameters_config is not None:
data_root_uri = runtime_parameters_config.data_root_runtime
examplegen = CsvExampleGen(input_base=data_root_uri, output_config=output_config)
# examplegen = CsvExampleGen(input_base=data_root_uri)
# Computes statistics over data for visualization and example validation.
statisticsgen = StatisticsGen(examples=examplegen.outputs.examples)
# Generates schema based on statistics files. Even though, we use user-provided schema
# we still want to generate the schema of the newest data for tracking and comparison
schemagen = SchemaGen(statistics=statisticsgen.outputs.statistics)
# Import a user-provided schema
import_schema = Importer(
source_uri=schema_proper_folder,
artifact_type=Schema).with_id('import_user_schema')
# Performs anomaly detection based on statistics and data schema.
examplevalidator = ExampleValidator(
statistics=statisticsgen.outputs.statistics,
schema=import_schema.outputs.result)
# Performs transformations and feature engineering in training and serving.
transform = Transform(
examples=examplegen.outputs.examples,
schema=import_schema.outputs.result,
module_file=preprocessing_proper_file)
# Tunes the hyperparameters for model training based on user-provided Python
# function. Note that once the hyperparameters are tuned, you can drop the
# Tuner component from pipeline and feed Trainer with tuned hyperparameters.
hparams_importer = Importer(
source_uri=hyperparameters_proper_folder,
artifact_type=HyperParameters).with_id('import_hparams')
# apparently only str RuntimeParameters are supported in airflow :/
if int_runtime_parameters_supported and runtime_parameters_config is not None:
train_steps = runtime_parameters_config.train_steps_runtime
eval_steps = runtime_parameters_config.eval_steps_runtime
else:
train_steps = trainer_config.train_steps
eval_steps = trainer_config.eval_steps
absl.logging.info('train_steps: %s' % train_steps)
absl.logging.info('eval_steps: %s' % eval_steps)
if tuner_config.enable_tuning:
tuner_args = {
'module_file': model_proper_file,
'examples': transform.outputs.transformed_examples,
'transform_graph': transform.outputs.transform_graph,
'train_args': {'num_steps': tuner_config.tuner_steps},
'eval_args': {'num_steps': tuner_config.eval_tuner_steps},
'custom_config': {'max_trials': tuner_config.max_trials, 'is_local_run': local_run}
# 'tune_args': tuner_pb2.TuneArgs(num_parallel_trials=3),
}
if tuner_config.ai_platform_tuner_args is not None:
tuner_args.update({
'custom_config': {
ai_platform_trainer_executor.TRAINING_ARGS_KEY: tuner_config.ai_platform_tuner_args
},
'tune_args': tuner_pb2.TuneArgs(num_parallel_trials=3)
})
absl.logging.info("tuner_args: " + str(tuner_args))
tuner = Tuner(**tuner_args)
hyperparameters = tuner.outputs.best_hyperparameters if tuner_config.enable_tuning else hparams_importer.outputs['result']
# Trains the model using a user provided trainer function.
trainer_args = {
'module_file': model_proper_file,
'transformed_examples': transform.outputs.transformed_examples,
'schema': import_schema.outputs.result,
'transform_graph': transform.outputs.transform_graph,
# train_args={'num_steps': train_steps},
'train_args': {'num_steps': train_steps},
'eval_args': {'num_steps': eval_steps},
#'hyperparameters': tuner.outputs.best_hyperparameters if tunerConfig.enable_tuning else None,
'hyperparameters': hyperparameters,
'custom_config': {'epochs': trainer_config.epochs, 'train_batch_size': trainer_config.train_batch_size,
'eval_batch_size': trainer_config.eval_batch_size,
}
}
if trainer_config.ai_platform_training_args is not None:
trainer_args['custom_config'].update({
ai_platform_trainer_executor.TRAINING_ARGS_KEY:
trainer_config.ai_platform_training_args,
})
trainer_args.update({
'custom_executor_spec':
executor_spec.ExecutorClassSpec(ai_platform_trainer_executor.GenericExecutor),
# 'custom_config': {
# ai_platform_trainer_executor.TRAINING_ARGS_KEY:
# ai_platform_training_args,
# }
})
else:
trainer_args.update({
'custom_executor_spec':
executor_spec.ExecutorClassSpec(trainer_executor.GenericExecutor),
#executor_spec.ExecutorClassSpec(custom_trainer_executor.CustomGenericExecutor), # for debugging purposes
})
trainer = Trainer(**trainer_args)
# Get the latest blessed model for model validation.
model_resolver = resolver.Resolver(
#instance_name='latest_blessed_model_resolver', # instance_name is deprecated, use with_id()
strategy_class=latest_blessed_model_resolver.LatestBlessedModelResolver,
model=Channel(type=Model),
model_blessing=Channel(type=ModelBlessing)\
).with_id('latest_blessed_model_resolver')
# Uses TFMA to compute a evaluation statistics over features of a model.
accuracy_threshold = tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={'value': 0.5},
upper_bound={'value': 0.995}),
)
metrics_specs = tfma.MetricsSpec(
metrics=[
tfma.MetricConfig(class_name='BinaryAccuracy',
threshold=accuracy_threshold),
tfma.MetricConfig(class_name='ExampleCount')])
eval_config = tfma.EvalConfig(
model_specs=[
tfma.ModelSpec(label_key='Survived')
],
metrics_specs=[metrics_specs],
slicing_specs=[
tfma.SlicingSpec()
,tfma.SlicingSpec(feature_keys=['Sex'])
,tfma.SlicingSpec(feature_keys=['Age'])
,tfma.SlicingSpec(feature_keys=['Parch'])
]
)
evaluator = Evaluator(
examples=examplegen.outputs.examples,
model=trainer.outputs.model,
baseline_model=model_resolver.outputs.model,
eval_config=eval_config
)
# Validate model can be loaded and queried in sand-boxed environment
# mirroring production.
serving_config = None
if local_run:
serving_config = infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(tags=['latest']),
local_docker=infra_validator_pb2.LocalDockerConfig() # Running on local docker.
)
else:
serving_config = infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(tags=['latest']),
kubernetes=infra_validator_pb2.KubernetesConfig() # Running on K8s.
)
validation_config = infra_validator_pb2.ValidationSpec(
max_loading_time_seconds=60,
num_tries=3,
)
request_config = infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServingRequestSpec(),
num_examples=3,
)
infravalidator = InfraValidator(
model=trainer.outputs.model,
examples=examplegen.outputs.examples,
serving_spec=serving_config,
validation_spec=validation_config,
request_spec=request_config,
)
# Checks whether the model passed the validation steps and pushes the model
# to CAIP Prediction if checks are passed.
pusher_args = {
'model': trainer.outputs.model,
'model_blessing': evaluator.outputs.blessing,
'infra_blessing': infravalidator.outputs.blessing
}
if local_run:
pusher_args.update({'push_destination':
pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=pusher_config.serving_model_dir))})
if pusher_config.ai_platform_serving_args is not None:
pusher_args.update({
'custom_executor_spec':
executor_spec.ExecutorClassSpec(ai_platform_pusher_executor.Executor
),
'custom_config': {
ai_platform_pusher_executor.SERVING_ARGS_KEY:
pusher_config.ai_platform_serving_args
},
})
pusher = Pusher(**pusher_args) # pylint: disable=unused-variable
components = [
examplegen,
statisticsgen,
schemagen,
import_schema,
examplevalidator,
transform,
trainer,
model_resolver,
evaluator,
infravalidator,
pusher
]
if tuner_config.enable_tuning:
components.append(tuner)
else:
components.append(hparams_importer)
return pipeline.Pipeline(
pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=components,
enable_cache=enable_cache,
metadata_connection_config=metadata_connection_config,
beam_pipeline_args=beam_pipeline_args
)
def create_pipeline(pipeline_name: Text,
pipeline_root: Text,
data_root_uri: data_types.RuntimeParameter,
train_steps: data_types.RuntimeParameter,
eval_steps: data_types.RuntimeParameter,
ai_platform_training_args: Dict[Text, Text],
ai_platform_serving_args: Dict[Text, Text],
beam_pipeline_args: List[Text],
enable_cache: Optional[bool] = False) -> pipeline.Pipeline:
"""Trains and deploys the Covertype classifier."""
# Brings data into the pipeline and splits the data into training and eval splits
examples = external_input(data_root_uri)
output_config = example_gen_pb2.Output(
split_config=example_gen_pb2.SplitConfig(splits=[
example_gen_pb2.SplitConfig.Split(name='train', hash_buckets=4),
example_gen_pb2.SplitConfig.Split(name='eval', hash_buckets=1)
]))
generate_examples = CsvExampleGen(input=examples)
# Computes statistics over data for visualization and example validation.
generate_statistics = StatisticsGen(
examples=generate_examples.outputs.examples)
# Import a user-provided schema
import_schema = ImporterNode(instance_name='import_user_schema',
source_uri=SCHEMA_FOLDER,
artifact_type=Schema)
# Generates schema based on statistics files.Even though, we use user-provided schema
# we still want to generate the schema of the newest data for tracking and comparison
infer_schema = SchemaGen(statistics=generate_statistics.outputs.statistics)
# Performs anomaly detection based on statistics and data schema.
validate_stats = ExampleValidator(
statistics=generate_statistics.outputs.statistics,
schema=import_schema.outputs.result)
# Performs transformations and feature engineering in training and serving.
transform = Transform(examples=generate_examples.outputs.examples,
schema=import_schema.outputs.result,
module_file=TRANSFORM_MODULE_FILE)
# Trains the model using a user provided trainer function.
train = Trainer(
custom_executor_spec=executor_spec.ExecutorClassSpec(
ai_platform_trainer_executor.GenericExecutor),
# custom_executor_spec=executor_spec.ExecutorClassSpec(trainer_executor.GenericExecutor),
module_file=TRAIN_MODULE_FILE,
transformed_examples=transform.outputs.transformed_examples,
schema=import_schema.outputs.result,
transform_graph=transform.outputs.transform_graph,
train_args={'num_steps': train_steps},
eval_args={'num_steps': eval_steps},
custom_config={'ai_platform_training_args': ai_platform_training_args})
# Get the latest blessed model for model validation.
resolve = ResolverNode(instance_name='latest_blessed_model_resolver',
resolver_class=latest_blessed_model_resolver.
LatestBlessedModelResolver,
model=Channel(type=Model),
model_blessing=Channel(type=ModelBlessing))
# Uses TFMA to compute a evaluation statistics over features of a model.
accuracy_threshold = tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(lower_bound={'value': 0.5},
upper_bound={'value':
0.99}),
change_threshold=tfma.GenericChangeThreshold(
absolute={'value': 0.0001},
direction=tfma.MetricDirection.HIGHER_IS_BETTER),
)
metrics_specs = tfma.MetricsSpec(metrics=[
tfma.MetricConfig(class_name='SparseCategoricalAccuracy',
threshold=accuracy_threshold),
tfma.MetricConfig(class_name='ExampleCount')
])
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(label_key='Cover_Type')],
metrics_specs=[metrics_specs],
slicing_specs=[
tfma.SlicingSpec(),
tfma.SlicingSpec(feature_keys=['Wilderness_Area'])
])
analyze = Evaluator(examples=generate_examples.outputs.examples,
model=train.outputs.model,
baseline_model=resolve.outputs.model,
eval_config=eval_config)
# Validate model can be loaded and queried in sand-boxed environment
# mirroring production.
serving_config = infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
kubernetes=infra_validator_pb2.KubernetesConfig(),
)
validation_config = infra_validator_pb2.ValidationSpec(
max_loading_time_seconds=60,
num_tries=3,
)
request_config = infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServingRequestSpec(),
num_examples=3,
)
infra_validate = InfraValidator(
model=train.outputs['model'],
examples=generate_examples.outputs['examples'],
serving_spec=serving_config,
validation_spec=validation_config,
request_spec=request_config,
)
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
deploy = Pusher(custom_executor_spec=executor_spec.ExecutorClassSpec(
ai_platform_pusher_executor.Executor),
model=train.outputs['model'],
model_blessing=analyze.outputs['blessing'],
infra_blessing=infra_validate.outputs['blessing'],
custom_config={
ai_platform_pusher_executor.SERVING_ARGS_KEY:
ai_platform_serving_args
})
return pipeline.Pipeline(pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=[
generate_examples, generate_statistics,
import_schema, infer_schema, validate_stats,
transform, train, resolve, analyze,
infra_validate, deploy
],
enable_cache=enable_cache,
beam_pipeline_args=beam_pipeline_args)
def _create_pipeline(pipeline_name: Text, pipeline_root: Text, data_root: Text,
module_file: Text, accuracy_threshold: float,
serving_model_dir: Text, metadata_path: Text,
beam_pipeline_args: List[Text],
make_warmup: bool) -> pipeline.Pipeline:
"""Implements the penguin pipeline with TFX."""
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=data_root)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
# Generates schema based on statistics files.
schema_gen = SchemaGen(statistics=statistics_gen.outputs['statistics'],
infer_feature_shape=True)
# Performs anomaly detection based on statistics and data schema.
example_validator = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=schema_gen.outputs['schema'])
# Performs transformations and feature engineering in training and serving.
transform = Transform(examples=example_gen.outputs['examples'],
schema=schema_gen.outputs['schema'],
module_file=module_file)
# Uses user-provided Python function that trains a model using TF-Learn.
trainer = Trainer(module_file=module_file,
examples=transform.outputs['transformed_examples'],
transform_graph=transform.outputs['transform_graph'],
schema=schema_gen.outputs['schema'],
train_args=trainer_pb2.TrainArgs(num_steps=2000),
eval_args=trainer_pb2.EvalArgs(num_steps=5))
# Get the latest blessed model for model validation.
model_resolver = ResolverNode(
instance_name='latest_blessed_model_resolver',
resolver_class=latest_blessed_model_resolver.
LatestBlessedModelResolver,
model=Channel(type=Model),
model_blessing=Channel(type=ModelBlessing))
# Uses TFMA to compute evaluation statistics over features of a model and
# perform quality validation of a candidate model (compared to a baseline).
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(label_key='species')],
slicing_specs=[tfma.SlicingSpec()],
metrics_specs=[
tfma.MetricsSpec(metrics=[
tfma.MetricConfig(
class_name='SparseCategoricalAccuracy',
threshold=tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={'value': accuracy_threshold}),
# Change threshold will be ignored if there is no
# baseline model resolved from MLMD (first run).
change_threshold=tfma.GenericChangeThreshold(
direction=tfma.MetricDirection.HIGHER_IS_BETTER,
absolute={'value': -1e-10})))
])
])
evaluator = Evaluator(examples=example_gen.outputs['examples'],
model=trainer.outputs['model'],
baseline_model=model_resolver.outputs['model'],
eval_config=eval_config)
# Performs infra validation of a candidate model to prevent unservable model
# from being pushed. This config will launch a model server of the latest
# TensorFlow Serving image in a local docker engine.
infra_validator = InfraValidator(
model=trainer.outputs['model'],
examples=example_gen.outputs['examples'],
serving_spec=infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
local_docker=infra_validator_pb2.LocalDockerConfig()),
request_spec=infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.
TensorFlowServingRequestSpec(),
# If this flag is set, InfraValidator will produce a model with
# warmup requests (in its outputs['blessing']).
make_warmup=make_warmup))
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
if make_warmup:
# If InfraValidator.request_spec.make_warmup = True, its output contains
# a model so that Pusher can push 'infra_blessing' input instead of
# 'model' input.
pusher = Pusher(model_blessing=evaluator.outputs['blessing'],
infra_blessing=infra_validator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=serving_model_dir)))
else:
# Otherwise, 'infra_blessing' does not contain a model and is used as a
# conditional checker just like 'model_blessing' does. This is the typical
# use case.
pusher = Pusher(model=trainer.outputs['model'],
model_blessing=evaluator.outputs['blessing'],
infra_blessing=infra_validator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=serving_model_dir)))
return pipeline.Pipeline(
pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=[
example_gen,
statistics_gen,
schema_gen,
example_validator,
transform,
trainer,
model_resolver,
evaluator,
infra_validator,
pusher,
],
enable_cache=True,
metadata_connection_config=metadata.sqlite_metadata_connection_config(
metadata_path),
beam_pipeline_args=beam_pipeline_args)
def _create_pipeline(pipeline_name: Text, pipeline_root: Text, data_root: Text,
module_file: Text, serving_model_dir: Text,
direct_num_workers: int) -> pipeline.Pipeline:
"""Implements the chicago taxi pipeline with TFX and Kubeflow Pipelines."""
examples = external_input(data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
# Generates schema based on statistics files.
schema_gen = SchemaGen(statistics=statistics_gen.outputs['statistics'],
infer_feature_shape=False)
# Performs anomaly detection based on statistics and data schema.
example_validator = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=schema_gen.outputs['schema'])
# Performs transformations and feature engineering in training and serving.
transform = Transform(examples=example_gen.outputs['examples'],
schema=schema_gen.outputs['schema'],
module_file=module_file)
# Uses user-provided Python function that implements a model using TF-Learn
# to train a model on Google Cloud AI Platform.
trainer = Trainer(
module_file=module_file,
transformed_examples=transform.outputs['transformed_examples'],
schema=schema_gen.outputs['schema'],
transform_graph=transform.outputs['transform_graph'],
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000),
)
# Get the latest blessed model for model validation.
model_resolver = ResolverNode(
instance_name='latest_blessed_model_resolver',
resolver_class=latest_blessed_model_resolver.
LatestBlessedModelResolver,
model=Channel(type=Model),
model_blessing=Channel(type=ModelBlessing))
# Uses TFMA to compute a evaluation statistics over features of a model and
# perform quality validation of a candidate model (compared to a baseline).
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(signature_name='eval')],
slicing_specs=[
tfma.SlicingSpec(),
tfma.SlicingSpec(feature_keys=['trip_start_hour'])
],
metrics_specs=[
tfma.MetricsSpec(
thresholds={
'binary_accuracy':
tfma.config.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={'value': 0.6}),
change_threshold=tfma.GenericChangeThreshold(
direction=tfma.MetricDirection.HIGHER_IS_BETTER,
absolute={'value': -1e-10}))
})
])
evaluator = Evaluator(
examples=example_gen.outputs['examples'],
model=trainer.outputs['model'],
baseline_model=model_resolver.outputs['model'],
# Change threshold will be ignored if there is no baseline (first run).
eval_config=eval_config)
# Performs infra validation of a candidate model to prevent unservable model
# from being pushed. In order to use InfraValidator component, persistent
# volume and its claim that the pipeline is using should be a ReadWriteMany
# access mode.
infra_validator = InfraValidator(
model=trainer.outputs['model'],
examples=example_gen.outputs['examples'],
serving_spec=infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
kubernetes=infra_validator_pb2.KubernetesConfig()),
request_spec=infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.
TensorFlowServingRequestSpec()))
# Checks whether the model passed the validation steps and pushes the model
# to Google Cloud AI Platform if check passed.
pusher = Pusher(model=trainer.outputs['model'],
model_blessing=evaluator.outputs['blessing'],
infra_blessing=infra_validator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=serving_model_dir)))
return pipeline.Pipeline(
pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=[
example_gen,
statistics_gen,
schema_gen,
example_validator,
transform,
trainer,
model_resolver,
evaluator,
infra_validator,
pusher,
],
# TODO(b/142684737): The multi-processing API might change.
beam_pipeline_args=['--direct_num_workers=%d' % direct_num_workers],
)
def create_test_pipeline():
"""Builds a conditional pipeline."""
pipeline_name = "cond"
cond_root = "cond_root"
serving_model_dir = os.path.join(cond_root, "serving_model", pipeline_name)
tfx_root = "tfx_root"
data_path = os.path.join(tfx_root, "data_path")
pipeline_root = os.path.join(tfx_root, "pipelines", pipeline_name)
example_gen = CsvExampleGen(input_base=data_path)
statistics_gen = StatisticsGen(examples=example_gen.outputs["examples"])
schema_gen = SchemaGen(statistics=statistics_gen.outputs["statistics"])
trainer = Trainer(
module_file="module_file",
custom_executor_spec=executor_spec.ExecutorClassSpec(GenericExecutor),
examples=example_gen.outputs["examples"],
schema=schema_gen.outputs["schema"],
train_args=trainer_pb2.TrainArgs(num_steps=2000),
eval_args=trainer_pb2.EvalArgs(num_steps=5))
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(signature_name="eval")],
slicing_specs=[tfma.SlicingSpec()],
metrics_specs=[
tfma.MetricsSpec(
thresholds={
"sparse_categorical_accuracy":
tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={"value": 0.6}),
change_threshold=tfma.GenericChangeThreshold(
direction=tfma.MetricDirection.HIGHER_IS_BETTER,
absolute={"value": -1e-10}))
})
])
evaluator = Evaluator(examples=example_gen.outputs["examples"],
model=trainer.outputs["model"],
eval_config=eval_config)
with conditional.Cond(
evaluator.outputs["blessing"].future()[0].value == 1):
infra_validator = InfraValidator(
model=trainer.outputs["model"],
examples=example_gen.outputs["examples"],
serving_spec=infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=["latest"]),
local_docker=infra_validator_pb2.LocalDockerConfig()),
request_spec=infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.
TensorFlowServingRequestSpec()))
with conditional.Cond(
ph.logical_and(
infra_validator.outputs["blessing"].future()[0].value == 1,
trainer.outputs["model"].future()[0].uri != "")): # pylint: disable=g-explicit-bool-comparison
pusher = Pusher(
model=trainer.outputs["model"],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=serving_model_dir)))
return pipeline.Pipeline(
pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=[
example_gen, statistics_gen, schema_gen, trainer, evaluator,
infra_validator, pusher
],
enable_cache=True,
beam_pipeline_args=["--my_testing_beam_pipeline_args=foo"],
execution_mode=pipeline.ExecutionMode.SYNC)