def _test_complete_flow(self, train_input_fn, eval_input_fn,
predict_input_fn, input_dimension, label_dimension,
prediction_length):
feature_columns = [
feature_column_lib.numeric_column('x', shape=(input_dimension, ))
]
est = _baseline_estimator_fn(label_dimension=label_dimension,
model_dir=self._model_dir)
# TRAIN
# learn y = x
est.train(train_input_fn, steps=200)
# EVALUTE
scores = est.evaluate(eval_input_fn)
self.assertEqual(200, scores[ops.GraphKeys.GLOBAL_STEP])
self.assertIn(metric_keys.MetricKeys.LOSS, six.iterkeys(scores))
# PREDICT
predictions = np.array(
[x['predictions'] for x in est.predict(predict_input_fn)])
self.assertAllEqual((prediction_length, label_dimension),
predictions.shape)
# EXPORT
feature_spec = feature_column_lib.make_parse_example_spec(
feature_columns)
serving_input_receiver_fn = export.build_parsing_serving_input_receiver_fn(
feature_spec)
export_dir = est.export_saved_model(tempfile.mkdtemp(),
serving_input_receiver_fn)
self.assertTrue(gfile.Exists(export_dir))
def _test_complete_flow(
self, train_input_fn, eval_input_fn, predict_input_fn, input_dimension,
label_dimension, batch_size):
feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension,))]
est = linear.LinearEstimatorV2(
head=regression_head.RegressionHead(label_dimension=label_dimension),
feature_columns=feature_columns,
model_dir=self._model_dir)
# Train
num_steps = 10
est.train(train_input_fn, steps=num_steps)
# Evaluate
scores = est.evaluate(eval_input_fn)
self.assertEqual(num_steps, scores[ops.GraphKeys.GLOBAL_STEP])
self.assertIn('loss', six.iterkeys(scores))
# Predict
predictions = np.array([
x[prediction_keys.PredictionKeys.PREDICTIONS]
for x in est.predict(predict_input_fn)
])
self.assertAllEqual((batch_size, label_dimension), predictions.shape)
# Export
feature_spec = feature_column.make_parse_example_spec(feature_columns)
serving_input_receiver_fn = export.build_parsing_serving_input_receiver_fn(
feature_spec)
export_dir = est.export_saved_model(tempfile.mkdtemp(),
serving_input_receiver_fn)
self.assertTrue(gfile.Exists(export_dir))
def _serving_input_receiver_fn():
"""A receiver function to be passed to export_savedmodel."""
placeholders = {}
time_placeholder = array_ops.placeholder(
name=feature_keys.TrainEvalFeatures.TIMES,
dtype=dtypes.int64,
shape=[default_batch_size, default_series_length])
placeholders[
feature_keys.TrainEvalFeatures.TIMES] = time_placeholder
# Values are only necessary when filtering. For prediction the default
# value will be ignored.
placeholders[feature_keys.TrainEvalFeatures.VALUES] = (
array_ops.placeholder_with_default(
name=feature_keys.TrainEvalFeatures.VALUES,
input=array_ops.zeros(shape=[
default_batch_size if default_batch_size else 0,
default_series_length if default_series_length else 0,
self._model.num_features
],
dtype=self._model.dtype),
shape=(default_batch_size, default_series_length,
self._model.num_features)))
if self._model.exogenous_feature_columns:
with ops.Graph().as_default():
# Default placeholders have only an unknown batch dimension. Make them
# in a separate graph, then splice in the series length to the shapes
# and re-create them in the outer graph.
parsed_features = (feature_column.make_parse_example_spec(
self._model.exogenous_feature_columns))
placeholder_features = parsing_ops.parse_example(
serialized=array_ops.placeholder(shape=[None],
dtype=dtypes.string),
features=parsed_features)
exogenous_feature_shapes = {
key: (value.get_shape(), value.dtype)
for key, value in placeholder_features.items()
}
for feature_key, (batch_only_feature_shape, value_dtype) in (
exogenous_feature_shapes.items()):
batch_only_feature_shape = (
batch_only_feature_shape.with_rank_at_least(
1).as_list())
feature_shape = (
[default_batch_size, default_series_length] +
batch_only_feature_shape[1:])
placeholders[feature_key] = array_ops.placeholder(
dtype=value_dtype,
name=feature_key,
shape=feature_shape)
batch_size_tensor = array_ops.shape(time_placeholder)[0]
placeholders.update(
self._model_start_state_placeholders(
batch_size_tensor, static_batch_size=default_batch_size))
return export_lib.ServingInputReceiver(placeholders, placeholders)
def classifier_parse_example_spec(feature_columns,
label_key,
label_dtype=dtypes.int64,
label_default=None,
weight_column=None):
parsing_spec = fc.make_parse_example_spec(feature_columns)
label_spec = parsing_ops.FixedLenFeature((1,), label_dtype, label_default)
return _add_label_and_weight_to_parsing_spec(
parsing_spec=parsing_spec,
label_key=label_key,
label_spec=label_spec,
weight_column=weight_column)
def _serving_input_receiver_fn():
"""A receiver function to be passed to export_savedmodel."""
placeholders = {}
time_placeholder = array_ops.placeholder(
name=feature_keys.TrainEvalFeatures.TIMES,
dtype=dtypes.int64,
shape=[default_batch_size, default_series_length])
placeholders[feature_keys.TrainEvalFeatures.TIMES] = time_placeholder
# Values are only necessary when filtering. For prediction the default
# value will be ignored.
placeholders[feature_keys.TrainEvalFeatures.VALUES] = (
array_ops.placeholder_with_default(
name=feature_keys.TrainEvalFeatures.VALUES,
input=array_ops.zeros(
shape=[
default_batch_size if default_batch_size else 0,
default_series_length if default_series_length else 0,
self._model.num_features
],
dtype=self._model.dtype),
shape=(default_batch_size, default_series_length,
self._model.num_features)))
if self._model.exogenous_feature_columns:
with ops.Graph().as_default():
# Default placeholders have only an unknown batch dimension. Make them
# in a separate graph, then splice in the series length to the shapes
# and re-create them in the outer graph.
parsed_features = (
feature_column.make_parse_example_spec(
self._model.exogenous_feature_columns))
placeholder_features = parsing_ops.parse_example(
serialized=array_ops.placeholder(
shape=[None], dtype=dtypes.string),
features=parsed_features)
exogenous_feature_shapes = {
key: (value.get_shape(), value.dtype) for key, value
in placeholder_features.items()}
for feature_key, (batch_only_feature_shape,
value_dtype) in (exogenous_feature_shapes.items()):
batch_only_feature_shape = (
batch_only_feature_shape.with_rank_at_least(1).as_list())
feature_shape = ([default_batch_size, default_series_length] +
batch_only_feature_shape[1:])
placeholders[feature_key] = array_ops.placeholder(
dtype=value_dtype, name=feature_key, shape=feature_shape)
batch_size_tensor = array_ops.shape(time_placeholder)[0]
placeholders.update(
self._model_start_state_placeholders(
batch_size_tensor, static_batch_size=default_batch_size))
return export_lib.ServingInputReceiver(placeholders, placeholders)
def regressor_parse_example_spec(feature_columns, # pylint: disable=missing-docstring
label_key,
label_dtype=dtypes.float32,
label_default=None,
label_dimension=1,
weight_column=None):
parsing_spec = fc.make_parse_example_spec(feature_columns)
label_spec = parsing_ops.FixedLenFeature(
(label_dimension,), label_dtype, label_default)
return _add_label_and_weight_to_parsing_spec(
parsing_spec=parsing_spec,
label_key=label_key,
label_spec=label_spec,
weight_column=weight_column)
def _serving_input_receiver_fn():
"""A receiver function to be passed to export_savedmodel."""
times_column = feature_column.numeric_column(
key=feature_keys.TrainEvalFeatures.TIMES, dtype=dtypes.int64)
values_column = feature_column.numeric_column(
key=feature_keys.TrainEvalFeatures.VALUES,
dtype=values_input_dtype,
shape=(self._model.num_features, ))
parsed_features_no_sequence = (
feature_column.make_parse_example_spec(
list(self._model.exogenous_feature_columns) +
[times_column, values_column]))
parsed_features = {}
for key, feature_spec in parsed_features_no_sequence.items():
if isinstance(feature_spec, parsing_ops.FixedLenFeature):
if key == feature_keys.TrainEvalFeatures.VALUES:
parsed_features[key] = feature_spec._replace(
shape=((values_proto_length, ) +
feature_spec.shape))
else:
parsed_features[key] = feature_spec._replace(
shape=((filtering_length + prediction_length, ) +
feature_spec.shape))
elif feature_spec.dtype == dtypes.string:
parsed_features[key] = parsing_ops.FixedLenFeature(
shape=(filtering_length + prediction_length, ),
dtype=dtypes.string)
else: # VarLenFeature
raise ValueError(
"VarLenFeatures not supported, got %s for key %s" %
(feature_spec, key))
tfexamples = array_ops.placeholder(shape=[default_batch_size],
dtype=dtypes.string,
name="input")
features = parsing_ops.parse_example(serialized=tfexamples,
features=parsed_features)
features[feature_keys.TrainEvalFeatures.TIMES] = array_ops.squeeze(
features[feature_keys.TrainEvalFeatures.TIMES], axis=-1)
features[feature_keys.TrainEvalFeatures.VALUES] = math_ops.cast(
features[feature_keys.TrainEvalFeatures.VALUES],
dtype=self._model.dtype)[:, :filtering_length]
features.update(
self._model_start_state_placeholders(
batch_size_tensor=array_ops.shape(
features[feature_keys.TrainEvalFeatures.TIMES])[0],
static_batch_size=default_batch_size))
return export_lib.ServingInputReceiver(features,
{"examples": tfexamples})
def _serving_input_receiver_fn():
"""A receiver function to be passed to export_savedmodel."""
times_column = feature_column.numeric_column(
key=feature_keys.TrainEvalFeatures.TIMES, dtype=dtypes.int64)
values_column = feature_column.numeric_column(
key=feature_keys.TrainEvalFeatures.VALUES, dtype=values_input_dtype,
shape=(self._model.num_features,))
parsed_features_no_sequence = (
feature_column.make_parse_example_spec(
list(self._model.exogenous_feature_columns)
+ [times_column, values_column]))
parsed_features = {}
for key, feature_spec in parsed_features_no_sequence.items():
if isinstance(feature_spec, parsing_ops.FixedLenFeature):
if key == feature_keys.TrainEvalFeatures.VALUES:
parsed_features[key] = feature_spec._replace(
shape=((values_proto_length,)
+ feature_spec.shape))
else:
parsed_features[key] = feature_spec._replace(
shape=((filtering_length + prediction_length,)
+ feature_spec.shape))
elif feature_spec.dtype == dtypes.string:
parsed_features[key] = parsing_ops.FixedLenFeature(
shape=(filtering_length + prediction_length,),
dtype=dtypes.string)
else: # VarLenFeature
raise ValueError("VarLenFeatures not supported, got %s for key %s"
% (feature_spec, key))
tfexamples = array_ops.placeholder(
shape=[default_batch_size], dtype=dtypes.string, name="input")
features = parsing_ops.parse_example(
serialized=tfexamples,
features=parsed_features)
features[feature_keys.TrainEvalFeatures.TIMES] = array_ops.squeeze(
features[feature_keys.TrainEvalFeatures.TIMES], axis=-1)
features[feature_keys.TrainEvalFeatures.VALUES] = math_ops.cast(
features[feature_keys.TrainEvalFeatures.VALUES],
dtype=self._model.dtype)[:, :filtering_length]
features.update(
self._model_start_state_placeholders(
batch_size_tensor=array_ops.shape(
features[feature_keys.TrainEvalFeatures.TIMES])[0],
static_batch_size=default_batch_size))
return export_lib.ServingInputReceiver(
features, {"examples": tfexamples})
def _get_exogenous_embedding_shape(self):
"""Computes the shape of the vector returned by _process_exogenous_features.
Returns:
The shape as a list. Does not include a batch dimension.
"""
if not self._exogenous_feature_columns:
return (0,)
with ops.Graph().as_default():
parsed_features = (
feature_column.make_parse_example_spec(
self._exogenous_feature_columns))
placeholder_features = parsing_ops.parse_example(
serialized=array_ops.placeholder(shape=[None], dtype=dtypes.string),
features=parsed_features)
embedded = feature_column.input_layer(
features=placeholder_features,
feature_columns=self._exogenous_feature_columns)
return embedded.get_shape().as_list()[1:]
def _get_exogenous_embedding_shape(self):
"""Computes the shape of the vector returned by _process_exogenous_features.
Returns:
The shape as a list. Does not include a batch dimension.
"""
if not self._exogenous_feature_columns:
return (0,)
with ops.Graph().as_default():
parsed_features = (
feature_column.make_parse_example_spec(
self._exogenous_feature_columns))
placeholder_features = parsing_ops.parse_example(
serialized=array_ops.placeholder(shape=[None], dtype=dtypes.string),
features=parsed_features)
embedded = feature_column.input_layer(
features=placeholder_features,
feature_columns=self._exogenous_feature_columns)
return embedded.get_shape().as_list()[1:]
def _get_exporter(self, name, fc):
feature_spec = feature_column.make_parse_example_spec(fc)
serving_input_receiver_fn = (
export_lib.build_parsing_serving_input_receiver_fn(feature_spec))
return exporter_lib.LatestExporter(
name, serving_input_receiver_fn=serving_input_receiver_fn)
def test_complete_flow_with_mode(self, distribution,
use_train_and_evaluate):
label_dimension = 2
input_dimension = label_dimension
batch_size = 10
data = np.linspace(0.,
2.,
batch_size * label_dimension,
dtype=np.float32)
data = data.reshape(batch_size, label_dimension)
train_input_fn = self.dataset_input_fn(
x={'x': data},
y=data,
batch_size=batch_size // distribution.num_replicas_in_sync,
shuffle=True)
eval_input_fn = self.dataset_input_fn(
x={'x': data},
y=data,
batch_size=batch_size // distribution.num_replicas_in_sync,
shuffle=False)
predict_input_fn = numpy_io.numpy_input_fn(x={'x': data},
batch_size=batch_size,
shuffle=False)
linear_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension, ))
]
dnn_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension, ))
]
feature_columns = linear_feature_columns + dnn_feature_columns
estimator = dnn_linear_combined.DNNLinearCombinedRegressor(
linear_feature_columns=linear_feature_columns,
dnn_hidden_units=(2, 2),
dnn_feature_columns=dnn_feature_columns,
label_dimension=label_dimension,
model_dir=self._model_dir,
# TODO(isaprykin): Work around the colocate_with error.
dnn_optimizer=adagrad.AdagradOptimizer(0.001),
linear_optimizer=adagrad.AdagradOptimizer(0.001),
config=run_config.RunConfig(train_distribute=distribution,
eval_distribute=distribution))
num_steps = 10
if use_train_and_evaluate:
scores, _ = training.train_and_evaluate(
estimator,
training.TrainSpec(train_input_fn, max_steps=num_steps),
training.EvalSpec(eval_input_fn))
else:
estimator.train(train_input_fn, steps=num_steps)
scores = estimator.evaluate(eval_input_fn)
self.assertEqual(num_steps, scores[ops.GraphKeys.GLOBAL_STEP])
self.assertIn('loss', scores)
predictions = np.array([
x[prediction_keys.PredictionKeys.PREDICTIONS]
for x in estimator.predict(predict_input_fn)
])
self.assertAllEqual((batch_size, label_dimension), predictions.shape)
feature_spec = feature_column.make_parse_example_spec(feature_columns)
serving_input_receiver_fn = export.build_parsing_serving_input_receiver_fn(
feature_spec)
export_dir = estimator.export_saved_model(tempfile.mkdtemp(),
serving_input_receiver_fn)
self.assertTrue(gfile.Exists(export_dir))
def _get_exporter(self, name, fc):
feature_spec = feature_column.make_parse_example_spec(fc)
serving_input_receiver_fn = (
export_lib.build_parsing_serving_input_receiver_fn(feature_spec))
return exporter_lib.LatestExporter(
name, serving_input_receiver_fn=serving_input_receiver_fn)
def test_complete_flow_with_mode(self, distribution,
use_train_and_evaluate):
label_dimension = 2
input_dimension = label_dimension
batch_size = 10
data = np.linspace(0.,
2.,
batch_size * label_dimension,
dtype=np.float32)
data = data.reshape(batch_size, label_dimension)
train_input_fn = self.dataset_input_fn(
x={'x': data},
y=data,
batch_size=batch_size // len(distribution.worker_devices))
eval_input_fn = self.dataset_input_fn(x={'x': data},
y=data,
batch_size=batch_size //
len(distribution.worker_devices))
predict_input_fn = numpy_io.numpy_input_fn(x={'x': data},
batch_size=batch_size,
shuffle=False)
linear_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension, ))
]
dnn_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension, ))
]
feature_columns = linear_feature_columns + dnn_feature_columns
session_config = config_pb2.ConfigProto(log_device_placement=True,
allow_soft_placement=True)
estimator = dnn_linear_combined.DNNLinearCombinedRegressor(
linear_feature_columns=linear_feature_columns,
dnn_hidden_units=(2, 2),
dnn_feature_columns=dnn_feature_columns,
label_dimension=label_dimension,
model_dir=self._model_dir,
dnn_optimizer=adam.Adam(0.001),
linear_optimizer=adam.Adam(0.001),
config=run_config.RunConfig(train_distribute=distribution,
eval_distribute=distribution,
session_config=session_config))
num_steps = 2
if use_train_and_evaluate:
scores, _ = training.train_and_evaluate(
estimator,
training.TrainSpec(train_input_fn, max_steps=num_steps),
training.EvalSpec(eval_input_fn))
else:
estimator.train(train_input_fn, steps=num_steps)
scores = estimator.evaluate(eval_input_fn)
self.assertIn('loss', six.iterkeys(scores))
predictions = np.array([
x[prediction_keys.PredictionKeys.PREDICTIONS]
for x in estimator.predict(predict_input_fn)
])
self.assertAllEqual((batch_size, label_dimension), predictions.shape)
feature_spec = feature_column.make_parse_example_spec(feature_columns)
serving_input_receiver_fn = export.build_parsing_serving_input_receiver_fn(
feature_spec)
export_dir = estimator.export_savedmodel(tempfile.mkdtemp(),
serving_input_receiver_fn)
self.assertTrue(gfile.Exists(export_dir))
def test_complete_flow_with_mode(self, distribution, use_train_and_evaluate):
label_dimension = 2
input_dimension = label_dimension
batch_size = 10
data = np.linspace(0., 2., batch_size * label_dimension, dtype=np.float32)
data = data.reshape(batch_size, label_dimension)
train_input_fn = self.dataset_input_fn(
x={'x': data},
y=data,
batch_size=batch_size // distribution.num_replicas_in_sync,
shuffle=True)
eval_input_fn = self.dataset_input_fn(
x={'x': data},
y=data,
batch_size=batch_size // distribution.num_replicas_in_sync,
shuffle=False)
predict_input_fn = numpy_io.numpy_input_fn(
x={'x': data}, batch_size=batch_size, shuffle=False)
linear_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension,))
]
dnn_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension,))
]
feature_columns = linear_feature_columns + dnn_feature_columns
estimator = dnn_linear_combined.DNNLinearCombinedRegressor(
linear_feature_columns=linear_feature_columns,
dnn_hidden_units=(2, 2),
dnn_feature_columns=dnn_feature_columns,
label_dimension=label_dimension,
model_dir=self._model_dir,
# TODO(isaprykin): Work around the colocate_with error.
dnn_optimizer=adagrad.AdagradOptimizer(0.001),
linear_optimizer=adagrad.AdagradOptimizer(0.001),
config=run_config.RunConfig(
train_distribute=distribution, eval_distribute=distribution))
num_steps = 10
if use_train_and_evaluate:
scores, _ = training.train_and_evaluate(
estimator,
training.TrainSpec(train_input_fn, max_steps=num_steps),
training.EvalSpec(eval_input_fn))
else:
estimator.train(train_input_fn, steps=num_steps)
scores = estimator.evaluate(eval_input_fn)
self.assertEqual(num_steps, scores[ops.GraphKeys.GLOBAL_STEP])
self.assertIn('loss', scores)
predictions = np.array([
x[prediction_keys.PredictionKeys.PREDICTIONS]
for x in estimator.predict(predict_input_fn)
])
self.assertAllEqual((batch_size, label_dimension), predictions.shape)
feature_spec = feature_column.make_parse_example_spec(feature_columns)
serving_input_receiver_fn = export.build_parsing_serving_input_receiver_fn(
feature_spec)
export_dir = estimator.export_saved_model(tempfile.mkdtemp(),
serving_input_receiver_fn)
self.assertTrue(gfile.Exists(export_dir))
def test_complete_flow_with_mode(self, distribution, use_train_and_evaluate):
label_dimension = 2
input_dimension = label_dimension
batch_size = 10
data = np.linspace(0., 2., batch_size * label_dimension, dtype=np.float32)
data = data.reshape(batch_size, label_dimension)
train_input_fn = self.dataset_input_fn(
x={'x': data},
y=data,
batch_size=batch_size // len(distribution.worker_devices))
eval_input_fn = self.dataset_input_fn(
x={'x': data},
y=data,
batch_size=batch_size // len(distribution.worker_devices))
predict_input_fn = numpy_io.numpy_input_fn(
x={'x': data}, batch_size=batch_size, shuffle=False)
linear_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension,))
]
dnn_feature_columns = [
feature_column.numeric_column('x', shape=(input_dimension,))
]
feature_columns = linear_feature_columns + dnn_feature_columns
session_config = config_pb2.ConfigProto(
log_device_placement=True, allow_soft_placement=True)
estimator = dnn_linear_combined.DNNLinearCombinedRegressor(
linear_feature_columns=linear_feature_columns,
dnn_hidden_units=(2, 2),
dnn_feature_columns=dnn_feature_columns,
label_dimension=label_dimension,
model_dir=self._model_dir,
dnn_optimizer=adam.Adam(0.001),
linear_optimizer=adam.Adam(0.001),
config=run_config.RunConfig(
train_distribute=distribution,
eval_distribute=distribution,
session_config=session_config))
num_steps = 2
if use_train_and_evaluate:
scores, _ = training.train_and_evaluate(
estimator, training.TrainSpec(train_input_fn, max_steps=num_steps),
training.EvalSpec(eval_input_fn))
else:
estimator.train(train_input_fn, steps=num_steps)
scores = estimator.evaluate(eval_input_fn)
self.assertIn('loss', six.iterkeys(scores))
predictions = np.array([
x[prediction_keys.PredictionKeys.PREDICTIONS]
for x in estimator.predict(predict_input_fn)
])
self.assertAllEqual((batch_size, label_dimension), predictions.shape)
feature_spec = feature_column.make_parse_example_spec(feature_columns)
serving_input_receiver_fn = export.build_parsing_serving_input_receiver_fn(
feature_spec)
export_dir = estimator.export_savedmodel(tempfile.mkdtemp(),
serving_input_receiver_fn)
self.assertTrue(gfile.Exists(export_dir))
