experiments
/
STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Move tf.keras.layers.featureDenseFeature back to Keras package. 

PiperOrigin-RevId: 312201284
Change-Id: I8e51198c62a8e79ef493a173d7f4f8ab65f300eb
This commit is contained in:
Scott Zhu 2020-05-18 19:27:50 -07:00 committed by TensorFlower Gardener
parent efd77d2e45
commit d98a0e6017
17 changed files with 545 additions and 498 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
tensorflow/python/feature_column/BUILD
View File

@ -55,8 +55,6 @@ py_library(
py_library( py_library(
name = "feature_column_v2", name = "feature_column_v2",
srcs = [ srcs = [
"dense_features.py",
"dense_features_v2.py",
"feature_column_v2.py", "feature_column_v2.py",
"sequence_feature_column.py", "sequence_feature_column.py",
"serialization.py", "serialization.py",
@ -126,15 +124,6 @@ tf_py_test(
], ],
) )
tf_py_test(
name = "dense_features_test",
srcs = ["dense_features_test.py"],
tags = ["no_pip"],
deps = [
":feature_column_test_main_lib",
],
)
py_library( py_library(
name = "feature_column_test_main_lib", name = "feature_column_test_main_lib",
srcs = ["feature_column_test.py"], srcs = ["feature_column_test.py"],
@ -177,15 +166,6 @@ tf_py_test(
deps = [":feature_column_v2_test_main_lib"], deps = [":feature_column_v2_test_main_lib"],
) )
tf_py_test(
name = "dense_features_v2_test",
srcs = ["dense_features_v2_test.py"],
tags = ["no_pip"],
deps = [
":feature_column_v2_test_main_lib",
],
)
py_library( py_library(
name = "feature_column_v2_test_main_lib", name = "feature_column_v2_test_main_lib",
srcs = ["feature_column_v2_test.py"], srcs = ["feature_column_v2_test.py"],

8
tensorflow/python/feature_column/feature_column_lib.py
View File

@ -19,13 +19,13 @@ from __future__ import division
from __future__ import print_function from __future__ import print_function
# pylint: disable=unused-import,line-too-long,wildcard-import,g-bad-import-order # pylint: disable=unused-import,line-too-long,wildcard-import,g-bad-import-order
# We import dense_features_v2 first so that the V1 DenseFeatures is the default
# if users directly import feature_column_lib.
from tensorflow.python.feature_column.dense_features_v2 import *
from tensorflow.python.feature_column.dense_features import *
from tensorflow.python.feature_column.feature_column import * from tensorflow.python.feature_column.feature_column import *
from tensorflow.python.feature_column.feature_column_v2 import * from tensorflow.python.feature_column.feature_column_v2 import *
from tensorflow.python.feature_column.sequence_feature_column import * from tensorflow.python.feature_column.sequence_feature_column import *
from tensorflow.python.feature_column.serialization import * from tensorflow.python.feature_column.serialization import *
# We import dense_features_v2 first so that the V1 DenseFeatures is the default
# if users directly import feature_column_lib.
from tensorflow.python.keras.feature_column.dense_features_v2 import *
from tensorflow.python.keras.feature_column.dense_features import *
from tensorflow.python.keras.feature_column.sequence_feature_column import * from tensorflow.python.keras.feature_column.sequence_feature_column import *
# pylint: enable=unused-import,line-too-long # pylint: enable=unused-import,line-too-long

326
tensorflow/python/feature_column/feature_column_v2_test.py
View File

@ -31,7 +31,6 @@ from tensorflow.core.protobuf import rewriter_config_pb2
from tensorflow.python.client import session from tensorflow.python.client import session
from tensorflow.python.eager import backprop from tensorflow.python.eager import backprop
from tensorflow.python.eager import context from tensorflow.python.eager import context
from tensorflow.python.feature_column import dense_features as df
from tensorflow.python.feature_column import feature_column as fc_old from tensorflow.python.feature_column import feature_column as fc_old
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.feature_column import serialization from tensorflow.python.feature_column import serialization
@ -5582,23 +5581,6 @@ class IndicatorColumnTest(test.TestCase):
self.evaluate(weight_var.assign([[1.], [2.], [3.], [4.]])) self.evaluate(weight_var.assign([[1.], [2.], [3.], [4.]]))
self.assertAllClose([[2. + 3.]], self.evaluate(predictions)) self.assertAllClose([[2. + 3.]], self.evaluate(predictions))
@test_util.run_deprecated_v1
def test_dense_features(self):
animal = fc.indicator_column(
fc.categorical_column_with_identity('animal', num_buckets=4))
with ops.Graph().as_default():
features = {
'animal':
sparse_tensor.SparseTensor(
indices=[[0, 0], [0, 1]], values=[1, 2], dense_shape=[1, 2])
}
net = df.DenseFeatures([animal])(features)
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllClose([[0., 1., 1., 0.]], self.evaluate(net))
@test_util.run_deprecated_v1 @test_util.run_deprecated_v1
def test_input_layer(self): def test_input_layer(self):
animal = fc.indicator_column( animal = fc.indicator_column(
@ -6271,191 +6253,6 @@ class EmbeddingColumnTest(test.TestCase, parameterized.TestCase):
self.assertAllClose(((94.,), (29.,), (0.,), (42.,)), self.assertAllClose(((94.,), (29.,), (0.,), (42.,)),
self.evaluate(predictions)) self.evaluate(predictions))
@parameterized.named_parameters(
{
'testcase_name': 'use_safe_embedding_lookup',
'use_safe_embedding_lookup': True,
'partition_variables': False,
}, {
'testcase_name': 'dont_use_safe_embedding_lookup',
'use_safe_embedding_lookup': False,
'partition_variables': False,
}, {
'testcase_name': 'use_safe_embedding_lookup_partitioned',
'use_safe_embedding_lookup': True,
'partition_variables': True,
}, {
'testcase_name': 'dont_use_safe_embedding_lookup_partitioned',
'use_safe_embedding_lookup': False,
'partition_variables': True,
})
@test_util.run_deprecated_v1
def test_dense_features(self, use_safe_embedding_lookup, partition_variables):
# Inputs.
vocabulary_size = 4
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
# example 2, ids []
# example 3, ids [1]
indices=((0, 0), (1, 0), (1, 4), (3, 0)),
values=(2, 0, 1, 1),
dense_shape=(4, 5))
# Embedding variable.
embedding_dimension = 2
embedding_values = (
(1., 2.), # id 0
(3., 5.), # id 1
(7., 11.), # id 2
(9., 13.) # id 3
)
def _initializer(shape, dtype, partition_info=None):
if partition_variables:
self.assertEqual([vocabulary_size, embedding_dimension],
partition_info.full_shape)
self.assertAllEqual((2, embedding_dimension), shape)
else:
self.assertAllEqual((vocabulary_size, embedding_dimension), shape)
self.assertIsNone(partition_info)
self.assertEqual(dtypes.float32, dtype)
return embedding_values
# Expected lookup result, using combiner='mean'.
expected_lookups = (
# example 0, ids [2], embedding = [7, 11]
(7., 11.),
# example 1, ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
(2., 3.5),
# example 2, ids [], embedding = [0, 0]
(0., 0.),
# example 3, ids [1], embedding = [3, 5]
(3., 5.),
)
# Build columns.
categorical_column = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
partitioner = None
if partition_variables:
partitioner = partitioned_variables.fixed_size_partitioner(2, axis=0)
with variable_scope.variable_scope('vars', partitioner=partitioner):
embedding_column = fc.embedding_column(
categorical_column,
dimension=embedding_dimension,
initializer=_initializer,
use_safe_embedding_lookup=use_safe_embedding_lookup)
# Provide sparse input and get dense result.
l = df.DenseFeatures((embedding_column,))
dense_features = l({'aaa': sparse_input})
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
if partition_variables:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights/part_0:0',
'vars/dense_features/aaa_embedding/embedding_weights/part_1:0'),
tuple([v.name for v in global_vars]))
else:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights:0',),
tuple([v.name for v in global_vars]))
for v in global_vars:
self.assertIsInstance(v, variables_lib.Variable)
trainable_vars = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES)
if partition_variables:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights/part_0:0',
'vars/dense_features/aaa_embedding/embedding_weights/part_1:0'),
tuple([v.name for v in trainable_vars]))
else:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights:0',),
tuple([v.name for v in trainable_vars]))
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllEqual(embedding_values, self.evaluate(trainable_vars[0]))
self.assertAllEqual(expected_lookups, self.evaluate(dense_features))
if use_safe_embedding_lookup:
self.assertIn('SparseFillEmptyRows',
[x.type for x in ops.get_default_graph().get_operations()])
else:
self.assertNotIn(
'SparseFillEmptyRows',
[x.type for x in ops.get_default_graph().get_operations()])
@test_util.run_deprecated_v1
def test_dense_features_not_trainable(self):
# Inputs.
vocabulary_size = 3
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
# example 2, ids []
# example 3, ids [1]
indices=((0, 0), (1, 0), (1, 4), (3, 0)),
values=(2, 0, 1, 1),
dense_shape=(4, 5))
# Embedding variable.
embedding_dimension = 2
embedding_values = (
(1., 2.), # id 0
(3., 5.), # id 1
(7., 11.) # id 2
)
def _initializer(shape, dtype, partition_info=None):
self.assertAllEqual((vocabulary_size, embedding_dimension), shape)
self.assertEqual(dtypes.float32, dtype)
self.assertIsNone(partition_info)
return embedding_values
# Expected lookup result, using combiner='mean'.
expected_lookups = (
# example 0, ids [2], embedding = [7, 11]
(7., 11.),
# example 1, ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
(2., 3.5),
# example 2, ids [], embedding = [0, 0]
(0., 0.),
# example 3, ids [1], embedding = [3, 5]
(3., 5.),
)
# Build columns.
categorical_column = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
embedding_column = fc.embedding_column(
categorical_column,
dimension=embedding_dimension,
initializer=_initializer,
trainable=False)
# Provide sparse input and get dense result.
dense_features = df.DenseFeatures((embedding_column,))({
'aaa': sparse_input
})
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
self.assertCountEqual(('dense_features/aaa_embedding/embedding_weights:0',),
tuple([v.name for v in global_vars]))
self.assertCountEqual([],
ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES))
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllEqual(embedding_values, self.evaluate(global_vars[0]))
self.assertAllEqual(expected_lookups, self.evaluate(dense_features))
@test_util.run_deprecated_v1 @test_util.run_deprecated_v1
def test_input_layer(self): def test_input_layer(self):
# Inputs. # Inputs.
@ -7389,129 +7186,6 @@ class SharedEmbeddingColumnTest(test.TestCase, parameterized.TestCase):
# = [3*1 + 5*2, 3*0 +5*0] = [13, 0] # = [3*1 + 5*2, 3*0 +5*0] = [13, 0]
self.assertAllClose([[94. + 13.], [29.]], self.evaluate(predictions)) self.assertAllClose([[94. + 13.], [29.]], self.evaluate(predictions))
def _test_dense_features(self, trainable=True):
# Inputs.
vocabulary_size = 3
sparse_input_a = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 4)),
values=(2, 0, 1),
dense_shape=(2, 5))
sparse_input_b = sparse_tensor.SparseTensorValue(
# example 0, ids [0]
# example 1, ids []
indices=((0, 0),),
values=(0,),
dense_shape=(2, 5))
sparse_input_c = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 1), (1, 1), (1, 3)),
values=(2, 0, 1),
dense_shape=(2, 5))
sparse_input_d = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids []
indices=((0, 1),),
values=(2,),
dense_shape=(2, 5))
# Embedding variable.
embedding_dimension = 2
embedding_values = (
(1., 2.), # id 0
(3., 5.), # id 1
(7., 11.) # id 2
)
def _initializer(shape, dtype, partition_info=None):
self.assertAllEqual((vocabulary_size, embedding_dimension), shape)
self.assertEqual(dtypes.float32, dtype)
self.assertIsNone(partition_info)
return embedding_values
# Expected lookup result, using combiner='mean'.
expected_lookups = (
# example 0:
# A ids [2], embedding = [7, 11]
# B ids [0], embedding = [1, 2]
# C ids [2], embedding = [7, 11]
# D ids [2], embedding = [7, 11]
(7., 11., 1., 2., 7., 11., 7., 11.),
# example 1:
# A ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
# B ids [], embedding = [0, 0]
# C ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
# D ids [], embedding = [0, 0]
(2., 3.5, 0., 0., 2., 3.5, 0., 0.),
)
# Build columns.
categorical_column_a = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
categorical_column_b = fc.categorical_column_with_identity(
key='bbb', num_buckets=vocabulary_size)
categorical_column_c = fc.categorical_column_with_identity(
key='ccc', num_buckets=vocabulary_size)
categorical_column_d = fc.categorical_column_with_identity(
key='ddd', num_buckets=vocabulary_size)
embedding_column_a, embedding_column_b = fc.shared_embedding_columns_v2(
[categorical_column_a, categorical_column_b],
dimension=embedding_dimension,
initializer=_initializer,
trainable=trainable)
embedding_column_c, embedding_column_d = fc.shared_embedding_columns_v2(
[categorical_column_c, categorical_column_d],
dimension=embedding_dimension,
initializer=_initializer,
trainable=trainable)
features = {
'aaa': sparse_input_a,
'bbb': sparse_input_b,
'ccc': sparse_input_c,
'ddd': sparse_input_d
}
# Provide sparse input and get dense result.
dense_features = df.DenseFeatures(
feature_columns=(embedding_column_b, embedding_column_a,
embedding_column_c, embedding_column_d))(
features)
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
self.assertCountEqual(
['aaa_bbb_shared_embedding:0', 'ccc_ddd_shared_embedding:0'],
tuple([v.name for v in global_vars]))
for v in global_vars:
self.assertIsInstance(v, variables_lib.Variable)
trainable_vars = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES)
if trainable:
self.assertCountEqual(
['aaa_bbb_shared_embedding:0', 'ccc_ddd_shared_embedding:0'],
tuple([v.name for v in trainable_vars]))
else:
self.assertCountEqual([], tuple([v.name for v in trainable_vars]))
shared_embedding_vars = global_vars
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllEqual(embedding_values,
self.evaluate(shared_embedding_vars[0]))
self.assertAllEqual(expected_lookups, self.evaluate(dense_features))
@test_util.run_deprecated_v1
def test_dense_features(self):
self._test_dense_features()
@test_util.run_deprecated_v1
def test_dense_features_no_trainable(self):
self._test_dense_features(trainable=False)
@test_util.run_deprecated_v1 @test_util.run_deprecated_v1
def test_serialization(self): def test_serialization(self):

2
tensorflow/python/feature_column/keras_integration_test.py
View File

@ -23,12 +23,12 @@ import numpy as np
from tensorflow.python import keras from tensorflow.python import keras
from tensorflow.python import tf2 from tensorflow.python import tf2
from tensorflow.python.data.ops import dataset_ops from tensorflow.python.data.ops import dataset_ops
from tensorflow.python.feature_column import dense_features_v2
from tensorflow.python.feature_column import feature_column_lib as fc from tensorflow.python.feature_column import feature_column_lib as fc
from tensorflow.python.feature_column import feature_column_v2 from tensorflow.python.feature_column import feature_column_v2
from tensorflow.python.keras import keras_parameterized from tensorflow.python.keras import keras_parameterized
from tensorflow.python.keras import metrics as metrics_module from tensorflow.python.keras import metrics as metrics_module
from tensorflow.python.keras import testing_utils from tensorflow.python.keras import testing_utils
from tensorflow.python.keras.feature_column import dense_features_v2
from tensorflow.python.keras.optimizer_v2 import gradient_descent from tensorflow.python.keras.optimizer_v2 import gradient_descent
from tensorflow.python.keras.premade import linear from tensorflow.python.keras.premade import linear
from tensorflow.python.keras.premade import wide_deep from tensorflow.python.keras.premade import wide_deep

49
tensorflow/python/feature_column/sequence_feature_column_test.py
View File

@ -24,7 +24,6 @@ from absl.testing import parameterized
import numpy as np import numpy as np
from tensorflow.python.client import session from tensorflow.python.client import session
from tensorflow.python.feature_column import dense_features
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.feature_column import sequence_feature_column as sfc from tensorflow.python.feature_column import sequence_feature_column as sfc
from tensorflow.python.feature_column import serialization from tensorflow.python.feature_column import serialization
@ -111,54 +110,6 @@ class ConcatenateContextInputTest(test.TestCase, parameterized.TestCase):
sfc.concatenate_context_input(context_input, seq_input) sfc.concatenate_context_input(context_input, seq_input)
@test_util.run_all_in_graph_and_eager_modes
class DenseFeaturesTest(test.TestCase):
"""Tests DenseFeatures with sequence feature columns."""
def test_embedding_column(self):
"""Tests that error is raised for sequence embedding column."""
vocabulary_size = 3
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(2, 2))
categorical_column_a = sfc.sequence_categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
embedding_column_a = fc.embedding_column(
categorical_column_a, dimension=2)
input_layer = dense_features.DenseFeatures([embedding_column_a])
with self.assertRaisesRegexp(
ValueError,
r'In embedding_column: aaa_embedding\. categorical_column must not be '
r'of type SequenceCategoricalColumn\.'):
_ = input_layer({'aaa': sparse_input})
def test_indicator_column(self):
"""Tests that error is raised for sequence indicator column."""
vocabulary_size = 3
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(2, 2))
categorical_column_a = sfc.sequence_categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
indicator_column_a = fc.indicator_column(categorical_column_a)
input_layer = dense_features.DenseFeatures([indicator_column_a])
with self.assertRaisesRegexp(
ValueError,
r'In indicator_column: aaa_indicator\. categorical_column must not be '
r'of type SequenceCategoricalColumn\.'):
_ = input_layer({'aaa': sparse_input})
def _assert_sparse_tensor_value(test_case, expected, actual): def _assert_sparse_tensor_value(test_case, expected, actual):
_assert_sparse_tensor_indices_shape(test_case, expected, actual) _assert_sparse_tensor_indices_shape(test_case, expected, actual)

66
tensorflow/python/feature_column/serialization_test.py
View File

@ -20,7 +20,6 @@ from __future__ import print_function
from absl.testing import parameterized from absl.testing import parameterized
from tensorflow.python.feature_column import dense_features
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.feature_column import serialization from tensorflow.python.feature_column import serialization
from tensorflow.python.framework import test_util from tensorflow.python.framework import test_util
@ -114,71 +113,6 @@ class FeatureColumnSerializationTest(test.TestCase):
self.assertIs(new_price.normalizer_fn, _custom_fn) self.assertIs(new_price.normalizer_fn, _custom_fn)
@test_util.run_all_in_graph_and_eager_modes
class DenseFeaturesSerializationTest(test.TestCase, parameterized.TestCase):
@parameterized.named_parameters(
('default', None, None),
('trainable', True, 'trainable'),
('not_trainable', False, 'frozen'))
def test_get_config(self, trainable, name):
cols = [fc.numeric_column('a'),
fc.embedding_column(fc.categorical_column_with_identity(
key='b', num_buckets=3), dimension=2)]
orig_layer = dense_features.DenseFeatures(
cols, trainable=trainable, name=name)
config = orig_layer.get_config()
self.assertEqual(config['name'], orig_layer.name)
self.assertEqual(config['trainable'], trainable)
self.assertLen(config['feature_columns'], 2)
self.assertEqual(
config['feature_columns'][0]['class_name'], 'NumericColumn')
self.assertEqual(config['feature_columns'][0]['config']['shape'], (1,))
self.assertEqual(
config['feature_columns'][1]['class_name'], 'EmbeddingColumn')
@parameterized.named_parameters(
('default', None, None),
('trainable', True, 'trainable'),
('not_trainable', False, 'frozen'))
def test_from_config(self, trainable, name):
cols = [fc.numeric_column('a'),
fc.embedding_column(fc.categorical_column_with_vocabulary_list(
'b', vocabulary_list=['1', '2', '3']), dimension=2),
fc.indicator_column(fc.categorical_column_with_hash_bucket(
key='c', hash_bucket_size=3))]
orig_layer = dense_features.DenseFeatures(
cols, trainable=trainable, name=name)
config = orig_layer.get_config()
new_layer = dense_features.DenseFeatures.from_config(config)
self.assertEqual(new_layer.name, orig_layer.name)
self.assertEqual(new_layer.trainable, trainable)
self.assertLen(new_layer._feature_columns, 3)
self.assertEqual(new_layer._feature_columns[0].name, 'a')
self.assertEqual(new_layer._feature_columns[1].initializer.mean, 0.0)
self.assertEqual(new_layer._feature_columns[1].categorical_column.name, 'b')
self.assertIsInstance(new_layer._feature_columns[2], fc.IndicatorColumn)
def test_crossed_column(self):
a = fc.categorical_column_with_vocabulary_list(
'a', vocabulary_list=['1', '2', '3'])
b = fc.categorical_column_with_vocabulary_list(
'b', vocabulary_list=['1', '2', '3'])
ab = fc.crossed_column([a, b], hash_bucket_size=2)
cols = [fc.indicator_column(ab)]
orig_layer = dense_features.DenseFeatures(cols)
config = orig_layer.get_config()
new_layer = dense_features.DenseFeatures.from_config(config)
self.assertLen(new_layer._feature_columns, 1)
self.assertEqual(new_layer._feature_columns[0].name, 'a_X_b_indicator')
@test_util.run_all_in_graph_and_eager_modes @test_util.run_all_in_graph_and_eager_modes
class LinearModelLayerSerializationTest(test.TestCase, parameterized.TestCase): class LinearModelLayerSerializationTest(test.TestCase, parameterized.TestCase):

78
tensorflow/python/keras/feature_column/BUILD
View File

@ -12,11 +12,88 @@ exports_files(["LICENSE"])
py_library( py_library(
name = "feature_column", name = "feature_column",
srcs = ["__init__.py"],
deps = [ deps = [
":dense_features",
":dense_features_v2",
":sequence_feature_column", ":sequence_feature_column",
], ],
) )
py_library(
name = "dense_features",
srcs = [
"dense_features.py",
],
deps = [
"//tensorflow/python:framework_ops",
"//tensorflow/python:tf_export",
"//tensorflow/python:util",
"//tensorflow/python/feature_column:feature_column_v2",
"//tensorflow/python/keras:backend",
],
)
py_library(
name = "dense_features_v2",
srcs = [
"dense_features_v2.py",
],
deps = [
":dense_features",
"//tensorflow/python:framework_ops",
"//tensorflow/python:tf_export",
"//tensorflow/python/feature_column:feature_column_v2",
],
)
tf_py_test(
name = "dense_features_test",
srcs = ["dense_features_test.py"],
tags = ["no_pip"],
deps = [
":dense_features",
"//tensorflow/python:array_ops",
"//tensorflow/python:client_testlib",
"//tensorflow/python:constant_op",
"//tensorflow/python:dtypes",
"//tensorflow/python:errors",
"//tensorflow/python:framework_ops",
"//tensorflow/python:framework_test_lib",
"//tensorflow/python:lookup_ops",
"//tensorflow/python:partitioned_variables",
"//tensorflow/python:session",
"//tensorflow/python:sparse_tensor",
"//tensorflow/python:variables",
"//tensorflow/python/eager:backprop",
"//tensorflow/python/eager:context",
"//tensorflow/python/feature_column:feature_column_v2",
],
)
tf_py_test(
name = "dense_features_v2_test",
srcs = ["dense_features_v2_test.py"],
tags = ["no_pip"],
deps = [
":dense_features_v2",
"//tensorflow/python:array_ops",
"//tensorflow/python:client_testlib",
"//tensorflow/python:constant_op",
"//tensorflow/python:dtypes",
"//tensorflow/python:errors",
"//tensorflow/python:framework_ops",
"//tensorflow/python:framework_test_lib",
"//tensorflow/python:lookup_ops",
"//tensorflow/python:session",
"//tensorflow/python:sparse_tensor",
"//tensorflow/python:variables",
"//tensorflow/python/eager:backprop",
"//tensorflow/python/eager:context",
"//tensorflow/python/feature_column:feature_column_v2",
],
)
py_library( py_library(
name = "sequence_feature_column", name = "sequence_feature_column",
srcs = ["sequence_feature_column.py"], srcs = ["sequence_feature_column.py"],
@ -59,6 +136,7 @@ py_test(
srcs_version = "PY2AND3", srcs_version = "PY2AND3",
tags = ["no_pip"], tags = ["no_pip"],
deps = [ deps = [
":dense_features",
":sequence_feature_column", ":sequence_feature_column",
"//tensorflow/python:client_testlib", "//tensorflow/python:client_testlib",
"//tensorflow/python:framework_test_lib", "//tensorflow/python:framework_test_lib",

0
tensorflow/python/keras/feature_column/__init__.py Normal file
View File

5
tensorflow/python/feature_column/dense_features.py → tensorflow/python/keras/feature_column/dense_features.py
View File

@ -23,7 +23,6 @@ import json
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.framework import ops from tensorflow.python.framework import ops
from tensorflow.python.keras import backend from tensorflow.python.keras import backend
from tensorflow.python.keras.layers import serialization as layer_serialization
from tensorflow.python.util import serialization from tensorflow.python.util import serialization
from tensorflow.python.util.tf_export import keras_export from tensorflow.python.util.tf_export import keras_export
@ -173,7 +172,3 @@ class DenseFeatures(fc._BaseFeaturesLayer): # pylint: disable=protected-access
cols_to_output_tensors[column] = processed_tensors cols_to_output_tensors[column] = processed_tensors
output_tensors.append(processed_tensors) output_tensors.append(processed_tensors)
return self._verify_and_concat_tensors(output_tensors) return self._verify_and_concat_tensors(output_tensors)
layer_serialization.inject_feature_column_v1_objects(
'DenseFeatures', DenseFeatures)

452
tensorflow/python/feature_column/dense_features_test.py → tensorflow/python/keras/feature_column/dense_features_test.py
View File

@ -18,22 +18,25 @@ from __future__ import absolute_import
from __future__ import division from __future__ import division
from __future__ import print_function from __future__ import print_function
from absl.testing import parameterized
import numpy as np import numpy as np
from tensorflow.python.client import session from tensorflow.python.client import session
from tensorflow.python.eager import backprop from tensorflow.python.eager import backprop
from tensorflow.python.eager import context from tensorflow.python.eager import context
from tensorflow.python.feature_column import dense_features as df
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.feature_column import sequence_feature_column as sfc
from tensorflow.python.framework import constant_op from tensorflow.python.framework import constant_op
from tensorflow.python.framework import dtypes from tensorflow.python.framework import dtypes
from tensorflow.python.framework import errors from tensorflow.python.framework import errors
from tensorflow.python.framework import ops from tensorflow.python.framework import ops
from tensorflow.python.framework import sparse_tensor from tensorflow.python.framework import sparse_tensor
from tensorflow.python.framework import test_util from tensorflow.python.framework import test_util
from tensorflow.python.keras.feature_column import dense_features as df
from tensorflow.python.ops import array_ops from tensorflow.python.ops import array_ops
from tensorflow.python.ops import lookup_ops from tensorflow.python.ops import lookup_ops
from tensorflow.python.ops import partitioned_variables from tensorflow.python.ops import partitioned_variables
from tensorflow.python.ops import variable_scope
from tensorflow.python.ops import variables as variables_lib from tensorflow.python.ops import variables as variables_lib
from tensorflow.python.platform import test from tensorflow.python.platform import test
@ -676,5 +679,452 @@ class DenseFeaturesTest(test.TestCase):
sess.run(net, feed_dict={features['price']: np.array(1)}) sess.run(net, feed_dict={features['price']: np.array(1)})
class IndicatorColumnTest(test.TestCase):
@test_util.run_deprecated_v1
def test_dense_features(self):
animal = fc.indicator_column(
fc.categorical_column_with_identity('animal', num_buckets=4))
with ops.Graph().as_default():
features = {
'animal':
sparse_tensor.SparseTensor(
indices=[[0, 0], [0, 1]], values=[1, 2], dense_shape=[1, 2])
}
net = df.DenseFeatures([animal])(features)
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllClose([[0., 1., 1., 0.]], self.evaluate(net))
class EmbeddingColumnTest(test.TestCase, parameterized.TestCase):
@parameterized.named_parameters(
{
'testcase_name': 'use_safe_embedding_lookup',
'use_safe_embedding_lookup': True,
'partition_variables': False,
}, {
'testcase_name': 'dont_use_safe_embedding_lookup',
'use_safe_embedding_lookup': False,
'partition_variables': False,
}, {
'testcase_name': 'use_safe_embedding_lookup_partitioned',
'use_safe_embedding_lookup': True,
'partition_variables': True,
}, {
'testcase_name': 'dont_use_safe_embedding_lookup_partitioned',
'use_safe_embedding_lookup': False,
'partition_variables': True,
})
@test_util.run_deprecated_v1
def test_dense_features(self, use_safe_embedding_lookup, partition_variables):
# Inputs.
vocabulary_size = 4
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
# example 2, ids []
# example 3, ids [1]
indices=((0, 0), (1, 0), (1, 4), (3, 0)),
values=(2, 0, 1, 1),
dense_shape=(4, 5))
# Embedding variable.
embedding_dimension = 2
embedding_values = (
(1., 2.), # id 0
(3., 5.), # id 1
(7., 11.), # id 2
(9., 13.) # id 3
)
def _initializer(shape, dtype, partition_info=None):
if partition_variables:
self.assertEqual([vocabulary_size, embedding_dimension],
partition_info.full_shape)
self.assertAllEqual((2, embedding_dimension), shape)
else:
self.assertAllEqual((vocabulary_size, embedding_dimension), shape)
self.assertIsNone(partition_info)
self.assertEqual(dtypes.float32, dtype)
return embedding_values
# Expected lookup result, using combiner='mean'.
expected_lookups = (
# example 0, ids [2], embedding = [7, 11]
(7., 11.),
# example 1, ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
(2., 3.5),
# example 2, ids [], embedding = [0, 0]
(0., 0.),
# example 3, ids [1], embedding = [3, 5]
(3., 5.),
)
# Build columns.
categorical_column = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
partitioner = None
if partition_variables:
partitioner = partitioned_variables.fixed_size_partitioner(2, axis=0)
with variable_scope.variable_scope('vars', partitioner=partitioner):
embedding_column = fc.embedding_column(
categorical_column,
dimension=embedding_dimension,
initializer=_initializer,
use_safe_embedding_lookup=use_safe_embedding_lookup)
# Provide sparse input and get dense result.
l = df.DenseFeatures((embedding_column,))
dense_features = l({'aaa': sparse_input})
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
if partition_variables:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights/part_0:0',
'vars/dense_features/aaa_embedding/embedding_weights/part_1:0'),
tuple([v.name for v in global_vars]))
else:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights:0',),
tuple([v.name for v in global_vars]))
for v in global_vars:
self.assertIsInstance(v, variables_lib.Variable)
trainable_vars = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES)
if partition_variables:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights/part_0:0',
'vars/dense_features/aaa_embedding/embedding_weights/part_1:0'),
tuple([v.name for v in trainable_vars]))
else:
self.assertCountEqual(
('vars/dense_features/aaa_embedding/embedding_weights:0',),
tuple([v.name for v in trainable_vars]))
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllEqual(embedding_values, self.evaluate(trainable_vars[0]))
self.assertAllEqual(expected_lookups, self.evaluate(dense_features))
if use_safe_embedding_lookup:
self.assertIn('SparseFillEmptyRows',
[x.type for x in ops.get_default_graph().get_operations()])
else:
self.assertNotIn(
'SparseFillEmptyRows',
[x.type for x in ops.get_default_graph().get_operations()])
@test_util.run_deprecated_v1
def test_dense_features_not_trainable(self):
# Inputs.
vocabulary_size = 3
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
# example 2, ids []
# example 3, ids [1]
indices=((0, 0), (1, 0), (1, 4), (3, 0)),
values=(2, 0, 1, 1),
dense_shape=(4, 5))
# Embedding variable.
embedding_dimension = 2
embedding_values = (
(1., 2.), # id 0
(3., 5.), # id 1
(7., 11.) # id 2
)
def _initializer(shape, dtype, partition_info=None):
self.assertAllEqual((vocabulary_size, embedding_dimension), shape)
self.assertEqual(dtypes.float32, dtype)
self.assertIsNone(partition_info)
return embedding_values
# Expected lookup result, using combiner='mean'.
expected_lookups = (
# example 0, ids [2], embedding = [7, 11]
(7., 11.),
# example 1, ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
(2., 3.5),
# example 2, ids [], embedding = [0, 0]
(0., 0.),
# example 3, ids [1], embedding = [3, 5]
(3., 5.),
)
# Build columns.
categorical_column = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
embedding_column = fc.embedding_column(
categorical_column,
dimension=embedding_dimension,
initializer=_initializer,
trainable=False)
# Provide sparse input and get dense result.
dense_features = df.DenseFeatures((embedding_column,))({
'aaa': sparse_input
})
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
self.assertCountEqual(('dense_features/aaa_embedding/embedding_weights:0',),
tuple([v.name for v in global_vars]))
self.assertCountEqual([],
ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES))
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllEqual(embedding_values, self.evaluate(global_vars[0]))
self.assertAllEqual(expected_lookups, self.evaluate(dense_features))
class SharedEmbeddingColumnTest(test.TestCase, parameterized.TestCase):
def _test_dense_features(self, trainable=True):
# Inputs.
vocabulary_size = 3
sparse_input_a = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 4)),
values=(2, 0, 1),
dense_shape=(2, 5))
sparse_input_b = sparse_tensor.SparseTensorValue(
# example 0, ids [0]
# example 1, ids []
indices=((0, 0),),
values=(0,),
dense_shape=(2, 5))
sparse_input_c = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 1), (1, 1), (1, 3)),
values=(2, 0, 1),
dense_shape=(2, 5))
sparse_input_d = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids []
indices=((0, 1),),
values=(2,),
dense_shape=(2, 5))
# Embedding variable.
embedding_dimension = 2
embedding_values = (
(1., 2.), # id 0
(3., 5.), # id 1
(7., 11.) # id 2
)
def _initializer(shape, dtype, partition_info=None):
self.assertAllEqual((vocabulary_size, embedding_dimension), shape)
self.assertEqual(dtypes.float32, dtype)
self.assertIsNone(partition_info)
return embedding_values
# Expected lookup result, using combiner='mean'.
expected_lookups = (
# example 0:
# A ids [2], embedding = [7, 11]
# B ids [0], embedding = [1, 2]
# C ids [2], embedding = [7, 11]
# D ids [2], embedding = [7, 11]
(7., 11., 1., 2., 7., 11., 7., 11.),
# example 1:
# A ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
# B ids [], embedding = [0, 0]
# C ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
# D ids [], embedding = [0, 0]
(2., 3.5, 0., 0., 2., 3.5, 0., 0.),
)
# Build columns.
categorical_column_a = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
categorical_column_b = fc.categorical_column_with_identity(
key='bbb', num_buckets=vocabulary_size)
categorical_column_c = fc.categorical_column_with_identity(
key='ccc', num_buckets=vocabulary_size)
categorical_column_d = fc.categorical_column_with_identity(
key='ddd', num_buckets=vocabulary_size)
embedding_column_a, embedding_column_b = fc.shared_embedding_columns_v2(
[categorical_column_a, categorical_column_b],
dimension=embedding_dimension,
initializer=_initializer,
trainable=trainable)
embedding_column_c, embedding_column_d = fc.shared_embedding_columns_v2(
[categorical_column_c, categorical_column_d],
dimension=embedding_dimension,
initializer=_initializer,
trainable=trainable)
features = {
'aaa': sparse_input_a,
'bbb': sparse_input_b,
'ccc': sparse_input_c,
'ddd': sparse_input_d
}
# Provide sparse input and get dense result.
dense_features = df.DenseFeatures(
feature_columns=(embedding_column_b, embedding_column_a,
embedding_column_c, embedding_column_d))(
features)
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
self.assertCountEqual(
['aaa_bbb_shared_embedding:0', 'ccc_ddd_shared_embedding:0'],
tuple([v.name for v in global_vars]))
for v in global_vars:
self.assertIsInstance(v, variables_lib.Variable)
trainable_vars = ops.get_collection(ops.GraphKeys.TRAINABLE_VARIABLES)
if trainable:
self.assertCountEqual(
['aaa_bbb_shared_embedding:0', 'ccc_ddd_shared_embedding:0'],
tuple([v.name for v in trainable_vars]))
else:
self.assertCountEqual([], tuple([v.name for v in trainable_vars]))
shared_embedding_vars = global_vars
self.evaluate(variables_lib.global_variables_initializer())
self.evaluate(lookup_ops.tables_initializer())
self.assertAllEqual(embedding_values,
self.evaluate(shared_embedding_vars[0]))
self.assertAllEqual(expected_lookups, self.evaluate(dense_features))
@test_util.run_deprecated_v1
def test_dense_features(self):
self._test_dense_features()
@test_util.run_deprecated_v1
def test_dense_features_no_trainable(self):
self._test_dense_features(trainable=False)
@test_util.run_all_in_graph_and_eager_modes
class DenseFeaturesSerializationTest(test.TestCase, parameterized.TestCase):
@parameterized.named_parameters(
('default', None, None),
('trainable', True, 'trainable'),
('not_trainable', False, 'frozen'))
def test_get_config(self, trainable, name):
cols = [fc.numeric_column('a'),
fc.embedding_column(fc.categorical_column_with_identity(
key='b', num_buckets=3), dimension=2)]
orig_layer = df.DenseFeatures(
cols, trainable=trainable, name=name)
config = orig_layer.get_config()
self.assertEqual(config['name'], orig_layer.name)
self.assertEqual(config['trainable'], trainable)
self.assertLen(config['feature_columns'], 2)
self.assertEqual(
config['feature_columns'][0]['class_name'], 'NumericColumn')
self.assertEqual(config['feature_columns'][0]['config']['shape'], (1,))
self.assertEqual(
config['feature_columns'][1]['class_name'], 'EmbeddingColumn')
@parameterized.named_parameters(
('default', None, None),
('trainable', True, 'trainable'),
('not_trainable', False, 'frozen'))
def test_from_config(self, trainable, name):
cols = [fc.numeric_column('a'),
fc.embedding_column(fc.categorical_column_with_vocabulary_list(
'b', vocabulary_list=['1', '2', '3']), dimension=2),
fc.indicator_column(fc.categorical_column_with_hash_bucket(
key='c', hash_bucket_size=3))]
orig_layer = df.DenseFeatures(
cols, trainable=trainable, name=name)
config = orig_layer.get_config()
new_layer = df.DenseFeatures.from_config(config)
self.assertEqual(new_layer.name, orig_layer.name)
self.assertEqual(new_layer.trainable, trainable)
self.assertLen(new_layer._feature_columns, 3)
self.assertEqual(new_layer._feature_columns[0].name, 'a')
self.assertEqual(new_layer._feature_columns[1].initializer.mean, 0.0)
self.assertEqual(new_layer._feature_columns[1].categorical_column.name, 'b')
self.assertIsInstance(new_layer._feature_columns[2], fc.IndicatorColumn)
def test_crossed_column(self):
a = fc.categorical_column_with_vocabulary_list(
'a', vocabulary_list=['1', '2', '3'])
b = fc.categorical_column_with_vocabulary_list(
'b', vocabulary_list=['1', '2', '3'])
ab = fc.crossed_column([a, b], hash_bucket_size=2)
cols = [fc.indicator_column(ab)]
orig_layer = df.DenseFeatures(cols)
config = orig_layer.get_config()
new_layer = df.DenseFeatures.from_config(config)
self.assertLen(new_layer._feature_columns, 1)
self.assertEqual(new_layer._feature_columns[0].name, 'a_X_b_indicator')
@test_util.run_all_in_graph_and_eager_modes
class SequenceFeatureColumnsTest(test.TestCase):
"""Tests DenseFeatures with sequence feature columns."""
def test_embedding_column(self):
"""Tests that error is raised for sequence embedding column."""
vocabulary_size = 3
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(2, 2))
categorical_column_a = sfc.sequence_categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
embedding_column_a = fc.embedding_column(
categorical_column_a, dimension=2)
input_layer = df.DenseFeatures([embedding_column_a])
with self.assertRaisesRegexp(
ValueError,
r'In embedding_column: aaa_embedding\. categorical_column must not be '
r'of type SequenceCategoricalColumn\.'):
_ = input_layer({'aaa': sparse_input})
def test_indicator_column(self):
"""Tests that error is raised for sequence indicator column."""
vocabulary_size = 3
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(2, 2))
categorical_column_a = sfc.sequence_categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
indicator_column_a = fc.indicator_column(categorical_column_a)
input_layer = df.DenseFeatures([indicator_column_a])
with self.assertRaisesRegexp(
ValueError,
r'In indicator_column: aaa_indicator\. categorical_column must not be '
r'of type SequenceCategoricalColumn\.'):
_ = input_layer({'aaa': sparse_input})
if __name__ == '__main__': if __name__ == '__main__':
test.main() test.main()

7
tensorflow/python/feature_column/dense_features_v2.py → tensorflow/python/keras/feature_column/dense_features_v2.py
View File

@ -18,10 +18,9 @@ from __future__ import absolute_import
from __future__ import division from __future__ import division
from __future__ import print_function from __future__ import print_function
from tensorflow.python.feature_column import dense_features
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.framework import ops from tensorflow.python.framework import ops
from tensorflow.python.keras.layers import serialization as layer_serialization from tensorflow.python.keras.feature_column import dense_features
from tensorflow.python.util.tf_export import keras_export from tensorflow.python.util.tf_export import keras_export
@ -94,7 +93,3 @@ class DenseFeatures(dense_features.DenseFeatures):
# We would like to call Layer.build and not _DenseFeaturesHelper.build. # We would like to call Layer.build and not _DenseFeaturesHelper.build.
# pylint: disable=protected-access # pylint: disable=protected-access
super(fc._BaseFeaturesLayer, self).build(None) # pylint: disable=bad-super-call super(fc._BaseFeaturesLayer, self).build(None) # pylint: disable=bad-super-call
layer_serialization.inject_feature_column_v2_objects(
'DenseFeatures', DenseFeatures)

2
tensorflow/python/feature_column/dense_features_v2_test.py → tensorflow/python/keras/feature_column/dense_features_v2_test.py
View File

@ -23,7 +23,6 @@ import numpy as np
from tensorflow.python.client import session from tensorflow.python.client import session
from tensorflow.python.eager import backprop from tensorflow.python.eager import backprop
from tensorflow.python.eager import context from tensorflow.python.eager import context
from tensorflow.python.feature_column import dense_features_v2 as df
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.framework import constant_op from tensorflow.python.framework import constant_op
from tensorflow.python.framework import dtypes from tensorflow.python.framework import dtypes
@ -31,6 +30,7 @@ from tensorflow.python.framework import errors
from tensorflow.python.framework import ops from tensorflow.python.framework import ops
from tensorflow.python.framework import sparse_tensor from tensorflow.python.framework import sparse_tensor
from tensorflow.python.framework import test_util from tensorflow.python.framework import test_util
from tensorflow.python.keras.feature_column import dense_features_v2 as df
from tensorflow.python.ops import array_ops from tensorflow.python.ops import array_ops
from tensorflow.python.ops import lookup_ops from tensorflow.python.ops import lookup_ops
from tensorflow.python.ops import variables as variables_lib from tensorflow.python.ops import variables as variables_lib

2
tensorflow/python/keras/feature_column/sequence_feature_column_integration_test.py
View File

@ -24,11 +24,11 @@ from google.protobuf import text_format
from tensorflow.core.example import example_pb2 from tensorflow.core.example import example_pb2
from tensorflow.core.example import feature_pb2 from tensorflow.core.example import feature_pb2
from tensorflow.python.data.ops import dataset_ops from tensorflow.python.data.ops import dataset_ops
from tensorflow.python.feature_column import dense_features
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.feature_column import sequence_feature_column as sfc from tensorflow.python.feature_column import sequence_feature_column as sfc
from tensorflow.python.framework import sparse_tensor from tensorflow.python.framework import sparse_tensor
from tensorflow.python.framework import test_util from tensorflow.python.framework import test_util
from tensorflow.python.keras.feature_column import dense_features
from tensorflow.python.keras.feature_column import sequence_feature_column as ksfc from tensorflow.python.keras.feature_column import sequence_feature_column as ksfc
from tensorflow.python.keras.layers import recurrent from tensorflow.python.keras.layers import recurrent
from tensorflow.python.ops import init_ops_v2 from tensorflow.python.ops import init_ops_v2

18
tensorflow/python/keras/layers/serialization.py
View File

@ -64,23 +64,11 @@ ALL_V2_MODULES = (
recurrent_v2, recurrent_v2,
preprocessing_normalization preprocessing_normalization
) )
FEATURE_COLUMN_V1_OBJECTS = {}
FEATURE_COLUMN_V2_OBJECTS = {}
# ALL_OBJECTS is meant to be a global mutable. Hence we need to make it # ALL_OBJECTS is meant to be a global mutable. Hence we need to make it
# thread-local to avoid concurrent mutations. # thread-local to avoid concurrent mutations.
LOCAL = threading.local() LOCAL = threading.local()
def inject_feature_column_v1_objects(name, cls):
global FEATURE_COLUMN_V1_OBJECTS
FEATURE_COLUMN_V1_OBJECTS[name] = cls
def inject_feature_column_v2_objects(name, cls):
global FEATURE_COLUMN_V2_OBJECTS
FEATURE_COLUMN_V2_OBJECTS[name] = cls
def populate_deserializable_objects(): def populate_deserializable_objects():
"""Populates dict ALL_OBJECTS with every built-in layer. """Populates dict ALL_OBJECTS with every built-in layer.
""" """
@ -134,9 +122,11 @@ def populate_deserializable_objects():
LOCAL.ALL_OBJECTS['WideDeepModel'] = WideDeepModel LOCAL.ALL_OBJECTS['WideDeepModel'] = WideDeepModel
if tf2.enabled(): if tf2.enabled():
LOCAL.ALL_OBJECTS.update(FEATURE_COLUMN_V2_OBJECTS) from tensorflow.python.keras.feature_column.dense_features_v2 import DenseFeatures # pylint: disable=g-import-not-at-top
LOCAL.ALL_OBJECTS['DenseFeatures'] = DenseFeatures
else: else:
LOCAL.ALL_OBJECTS.update(FEATURE_COLUMN_V1_OBJECTS) from tensorflow.python.keras.feature_column.dense_features import DenseFeatures # pylint: disable=g-import-not-at-top
LOCAL.ALL_OBJECTS['DenseFeatures'] = DenseFeatures
# Merge layers, function versions. # Merge layers, function versions.
LOCAL.ALL_OBJECTS['add'] = merge.add LOCAL.ALL_OBJECTS['add'] = merge.add

2
tensorflow/python/keras/saving/saved_model/saved_model_test.py
View File

@ -39,7 +39,6 @@ from tensorflow.python.distribute import mirrored_strategy
from tensorflow.python.eager import context from tensorflow.python.eager import context
from tensorflow.python.eager import def_function from tensorflow.python.eager import def_function
from tensorflow.python.feature_column import feature_column_v2 as fc from tensorflow.python.feature_column import feature_column_v2 as fc
from tensorflow.python.feature_column.dense_features import DenseFeatures
from tensorflow.python.framework import constant_op from tensorflow.python.framework import constant_op
from tensorflow.python.framework import dtypes from tensorflow.python.framework import dtypes
from tensorflow.python.framework import ops from tensorflow.python.framework import ops
@ -48,6 +47,7 @@ from tensorflow.python.keras import combinations
from tensorflow.python.keras import keras_parameterized from tensorflow.python.keras import keras_parameterized
from tensorflow.python.keras import regularizers from tensorflow.python.keras import regularizers
from tensorflow.python.keras import testing_utils from tensorflow.python.keras import testing_utils
from tensorflow.python.keras.feature_column.dense_features import DenseFeatures
from tensorflow.python.keras.saving.saved_model import load as keras_load from tensorflow.python.keras.saving.saved_model import load as keras_load
from tensorflow.python.keras.saving.saved_model import save_impl as keras_save from tensorflow.python.keras.saving.saved_model import save_impl as keras_save
from tensorflow.python.keras.utils import generic_utils from tensorflow.python.keras.utils import generic_utils

2
tensorflow/tools/api/golden/v1/tensorflow.keras.layers.-dense-features.pbtxt
View File

@ -1,6 +1,6 @@
path: "tensorflow.keras.layers.DenseFeatures" path: "tensorflow.keras.layers.DenseFeatures"
tf_class { tf_class {
is_instance: "<class \'tensorflow.python.feature_column.dense_features.DenseFeatures\'>" is_instance: "<class \'tensorflow.python.keras.feature_column.dense_features.DenseFeatures\'>"
is_instance: "<class \'tensorflow.python.feature_column.feature_column_v2._BaseFeaturesLayer\'>" is_instance: "<class \'tensorflow.python.feature_column.feature_column_v2._BaseFeaturesLayer\'>"
is_instance: "<class \'tensorflow.python.keras.engine.base_layer.Layer\'>" is_instance: "<class \'tensorflow.python.keras.engine.base_layer.Layer\'>"
is_instance: "<class \'tensorflow.python.module.module.Module\'>" is_instance: "<class \'tensorflow.python.module.module.Module\'>"

4
tensorflow/tools/api/golden/v2/tensorflow.keras.layers.-dense-features.pbtxt
View File

@ -1,7 +1,7 @@
path: "tensorflow.keras.layers.DenseFeatures" path: "tensorflow.keras.layers.DenseFeatures"
tf_class { tf_class {
is_instance: "<class \'tensorflow.python.feature_column.dense_features_v2.DenseFeatures\'>" is_instance: "<class \'tensorflow.python.keras.feature_column.dense_features_v2.DenseFeatures\'>"
is_instance: "<class \'tensorflow.python.feature_column.dense_features.DenseFeatures\'>" is_instance: "<class \'tensorflow.python.keras.feature_column.dense_features.DenseFeatures\'>"
is_instance: "<class \'tensorflow.python.feature_column.feature_column_v2._BaseFeaturesLayer\'>" is_instance: "<class \'tensorflow.python.feature_column.feature_column_v2._BaseFeaturesLayer\'>"
is_instance: "<class \'tensorflow.python.keras.engine.base_layer.Layer\'>" is_instance: "<class \'tensorflow.python.keras.engine.base_layer.Layer\'>"
is_instance: "<class \'tensorflow.python.module.module.Module\'>" is_instance: "<class \'tensorflow.python.module.module.Module\'>"