def test_dnn_and_linear_logits_are_added(self):
with ops.Graph().as_default():
variables_lib.Variable([[1.0]],
name='linear/linear_model/x/weights')
variables_lib.Variable([2.0],
name='linear/linear_model/bias_weights')
variables_lib.Variable([[3.0]], name='dnn/hiddenlayer_0/kernel')
variables_lib.Variable([4.0], name='dnn/hiddenlayer_0/bias')
variables_lib.Variable([[5.0]], name='dnn/logits/kernel')
variables_lib.Variable([6.0], name='dnn/logits/bias')
variables_lib.Variable(1, name='global_step', dtype=dtypes.int64)
linear_testing_utils.save_variables_to_ckpt(self._model_dir)
x_column = feature_column.numeric_column('x')
est = dnn_linear_combined.DNNLinearCombinedRegressor(
linear_feature_columns=[x_column],
dnn_hidden_units=[1],
dnn_feature_columns=[x_column],
model_dir=self._model_dir)
input_fn = numpy_io.numpy_input_fn(x={'x': np.array([[10.]])},
batch_size=1,
shuffle=False)
# linear logits = 10*1 + 2 = 12
# dnn logits = (10*3 + 4)*5 + 6 = 176
# logits = dnn + linear = 176 + 12 = 188
self.assertAllClose(
{
prediction_keys.PredictionKeys.PREDICTIONS: [188.],
}, next(est.predict(input_fn=input_fn)))
def _get_estimator(self,
train_distribute,
eval_distribute,
remote_cluster=None):
input_dimension = LABEL_DIMENSION
linear_feature_columns = [
feature_column.numeric_column("x", shape=(input_dimension,))
]
dnn_feature_columns = [
feature_column.numeric_column("x", shape=(input_dimension,))
]
return 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=adagrad.AdagradOptimizer(0.001),
linear_optimizer=adagrad.AdagradOptimizer(0.001),
config=run_config_lib.RunConfig(
experimental_distribute=DistributeConfig(
train_distribute=train_distribute,
eval_distribute=eval_distribute,
remote_cluster=remote_cluster)))
def _test_complete_flow_helper(self, linear_feature_columns,
dnn_feature_columns, feature_spec,
train_input_fn, eval_input_fn,
predict_input_fn, input_dimension,
label_dimension, batch_size):
est = 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)
# TRAIN
num_steps = 10
est.train(train_input_fn, steps=num_steps)
# EVALUTE
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
serving_input_receiver_fn = export.build_parsing_serving_input_receiver_fn(
feature_spec)
export_dir = est.export_savedmodel(tempfile.mkdtemp(),
serving_input_receiver_fn)
self.assertTrue(gfile.Exists(export_dir))
def test_complete_flow_with_mode(self, distribution):
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),
shuffle=True)
eval_input_fn = numpy_io.numpy_input_fn(x={'x': data},
y=data,
batch_size=batch_size,
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))
num_steps = 10
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', 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_regressor_basic_warm_starting(self, fc_impl):
"""Tests correctness of DNNLinearCombinedRegressor default warm-start."""
age = fc_impl.numeric_column('age')
city = fc_impl.embedding_column(
fc_impl.categorical_column_with_vocabulary_list(
'city', vocabulary_list=['Mountain View', 'Palo Alto']),
dimension=5)
# Create a DNNLinearCombinedRegressor and train to save a checkpoint.
dnn_lc_regressor = dnn_linear_combined.DNNLinearCombinedRegressor(
linear_feature_columns=[age],
dnn_feature_columns=[city],
dnn_hidden_units=[256, 128],
model_dir=self._ckpt_and_vocab_dir,
linear_optimizer='SGD',
dnn_optimizer='SGD')
dnn_lc_regressor.train(input_fn=self._input_fn, max_steps=1)
# Create a second DNNLinearCombinedRegressor, warm-started from the first.
# Use a learning_rate = 0.0 optimizer to check values (use SGD so we don't
# have accumulator values that change).
warm_started_dnn_lc_regressor = (
dnn_linear_combined.DNNLinearCombinedRegressor(
linear_feature_columns=[age],
dnn_feature_columns=[city],
dnn_hidden_units=[256, 128],
linear_optimizer=gradient_descent.GradientDescentOptimizer(
learning_rate=0.0),
dnn_optimizer=gradient_descent.GradientDescentOptimizer(
learning_rate=0.0),
warm_start_from=dnn_lc_regressor.model_dir))
warm_started_dnn_lc_regressor.train(input_fn=self._input_fn,
max_steps=1)
for variable_name in warm_started_dnn_lc_regressor.get_variable_names(
):
self.assertAllClose(
dnn_lc_regressor.get_variable_value(variable_name),
warm_started_dnn_lc_regressor.get_variable_value(
variable_name))
def _linear_regressor_fn(feature_columns,
model_dir=None,
label_dimension=1,
weight_feature_key=None,
optimizer='Ftrl',
config=None,
partitioner=None):
return dnn_linear_combined.DNNLinearCombinedRegressor(
model_dir=model_dir,
linear_feature_columns=feature_columns,
linear_optimizer=optimizer,
label_dimension=label_dimension,
weight_feature_key=weight_feature_key,
input_layer_partitioner=partitioner,
config=config)
def _dnn_regressor_fn(hidden_units,
feature_columns,
model_dir=None,
label_dimension=1,
weight_feature_key=None,
optimizer='Adagrad',
config=None,
input_layer_partitioner=None):
return dnn_linear_combined.DNNLinearCombinedRegressor(
model_dir=model_dir,
dnn_hidden_units=hidden_units,
dnn_feature_columns=feature_columns,
dnn_optimizer=optimizer,
label_dimension=label_dimension,
weight_feature_key=weight_feature_key,
input_layer_partitioner=input_layer_partitioner,
config=config)
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))
