def test_error_dense_shape_invalid(self):
categorical_column_input = fc_lib.categorical_column_with_identity(
key='inp', num_buckets=5)
with self.assertRaisesRegexp(ValueError,
'tensor_core_shape must be size 2'):
tpu_fc.shared_embedding_columns_v2([categorical_column_input],
dimension=20,
tensor_core_shape=[None, 20, 15])
def test_invalid_cases(self, shared):
# Inputs.
input_sparse_tensor = sparse_tensor.SparseTensorValue(
indices=((0, 0), (1, 0), (1, 1), (1, 4)),
values=(2, 0, 1, 3),
dense_shape=(2, 5))
input_features = {'inp': input_sparse_tensor}
# Build columns.
categorical_column_input = fc_lib.categorical_column_with_identity(
key='inp', num_buckets=3)
# Training on TPU with cpu embedding lookups is not supported.
if shared:
embedding_column = tpu_fc.shared_embedding_columns_v2(
[categorical_column_input],
dimension=2,
embedding_lookup_device='cpu',
tensor_core_shape=[None, 3])
else:
embedding_column = tpu_fc.embedding_column_v2(
categorical_column_input,
dimension=2,
embedding_lookup_device='cpu',
tensor_core_shape=[None, 3])
dense_features = fc_lib.DenseFeatures(embedding_column)
with self.assertRaisesRegexp(
ValueError,
r'.*embedding_lookup_device=\"cpu\" during training is not'):
dense_features(input_features)
# Inference on with TPU Embedding Hardware is not supported.
if shared:
embedding_column = tpu_fc.shared_embedding_columns_v2(
[categorical_column_input],
dimension=2,
embedding_lookup_device='tpu_embedding_core',
tensor_core_shape=[None, 3])
else:
embedding_column = tpu_fc.embedding_column_v2(
categorical_column_input,
dimension=2,
embedding_lookup_device='tpu_embedding_core',
tensor_core_shape=[None, 3])
context = tpu._TPUInferenceContext('tpu_inference')
context.Enter()
dense_features = fc_lib.DenseFeatures(embedding_column)
with self.assertRaisesRegexp(
ValueError,
r'Using embedding_lookup_device=tpu_embedding_core during inference is '
):
dense_features(input_features)
context.Exit()
def test_defaults(self):
vocabulary_size = 3
categorical_column_a = fc_lib.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
categorical_column_b = fc_lib.categorical_column_with_identity(
key='bbb', num_buckets=vocabulary_size)
embedding_dimension = 2
embedding_column_b, embedding_column_a = tpu_fc.shared_embedding_columns_v2(
[categorical_column_b, categorical_column_a],
dimension=embedding_dimension)
self.assertIs(categorical_column_a,
embedding_column_a.categorical_column)
self.assertIs(categorical_column_b,
embedding_column_b.categorical_column)
self.assertEqual((vocabulary_size, embedding_dimension),
embedding_column_a.get_embedding_table_size())
self.assertEqual((vocabulary_size, embedding_dimension),
embedding_column_a.get_embedding_table_size())
self.assertEqual('mean', embedding_column_a.combiner)
self.assertEqual('mean', embedding_column_b.combiner)
self.assertIsNotNone(embedding_column_a.get_initializer())
self.assertIsNotNone(embedding_column_b.get_initializer())
self.assertEqual('aaa_bbb_shared_embedding',
embedding_column_a.get_embedding_var_name())
self.assertEqual('aaa_bbb_shared_embedding',
embedding_column_b.get_embedding_var_name())
self.assertEqual('aaa_shared_embedding', embedding_column_a.name)
self.assertEqual('bbb_shared_embedding', embedding_column_b.name)
self.assertEqual((embedding_dimension, ),
embedding_column_a.variable_shape)
self.assertEqual((embedding_dimension, ),
embedding_column_b.variable_shape)
def test_all_constructor_args(self):
vocabulary_size = 3
categorical_column_a = fc_lib.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
categorical_column_b = fc_lib.categorical_column_with_identity(
key='bbb', num_buckets=vocabulary_size)
embedding_dimension = 2
embedding_column_a, embedding_column_b = tpu_fc.shared_embedding_columns_v2(
[categorical_column_a, categorical_column_b],
dimension=embedding_dimension,
combiner='my_combiner',
initializer=lambda: 'my_initializer',
shared_embedding_collection_name='var_scope_name')
self.assertIs(categorical_column_a, embedding_column_a.categorical_column)
self.assertIs(categorical_column_b, embedding_column_b.categorical_column)
self.assertEqual((vocabulary_size, embedding_dimension),
embedding_column_a.get_embedding_table_size())
self.assertEqual((vocabulary_size, embedding_dimension),
embedding_column_a.get_embedding_table_size())
self.assertEqual('my_combiner', embedding_column_a.combiner)
self.assertEqual('my_combiner', embedding_column_b.combiner)
self.assertEqual('my_initializer', embedding_column_a.get_initializer()())
self.assertEqual('my_initializer', embedding_column_b.get_initializer()())
self.assertEqual('var_scope_name',
embedding_column_a.get_embedding_var_name())
self.assertEqual('var_scope_name',
embedding_column_b.get_embedding_var_name())
self.assertEqual('aaa_shared_embedding', embedding_column_a.name)
self.assertEqual('bbb_shared_embedding', embedding_column_b.name)
self.assertEqual((embedding_dimension,), embedding_column_a.variable_shape)
self.assertEqual((embedding_dimension,), embedding_column_b.variable_shape)
def test_deepcopy(self):
vocabulary_size = 3
categorical_column_a = fc_lib.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
categorical_column_b = fc_lib.categorical_column_with_identity(
key='bbb', num_buckets=vocabulary_size)
embedding_dimension = 2
columns = tpu_fc.shared_embedding_columns_v2(
[categorical_column_b, categorical_column_a],
dimension=embedding_dimension)
columns_copy = copy.deepcopy(columns)
self.assertEqual(
[column._shared_embedding_collection_name for column in columns],
[column._shared_embedding_collection_name for column in columns_copy])
def test_dense_embedding_lookup(self, shared, combiner):
# Inputs.
vocabulary_size = 3
input_sparse_tensor = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1, 3]
indices=((0, 0), (1, 0), (1, 1), (1, 4)),
values=(2, 0, 1, 3),
dense_shape=(2, 5))
input_features = {'inp': input_sparse_tensor}
# Embedding variable.
embedding_dimension = 2
embedding_values = (
(1., 2.), # id 0
(3., 5.), # id 1
(7., 11.), # id 2
(13., 17.) # id 3
)
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
# Build columns.
categorical_column_input = fc_lib.categorical_column_with_identity(
key='inp', num_buckets=vocabulary_size)
# Set tensor_core_shape to be [None, 20] to ensure some padding and
# dynamic batch size.
if shared:
embedding_column = tpu_fc.shared_embedding_columns_v2(
[categorical_column_input],
dimension=embedding_dimension,
initializer=_initializer,
combiner=combiner,
embedding_lookup_device='tpu_tensor_core',
tensor_core_shape=[None, 3])
else:
embedding_column = tpu_fc.embedding_column_v2(
categorical_column_input,
dimension=embedding_dimension,
initializer=_initializer,
combiner=combiner,
embedding_lookup_device='tpu_tensor_core',
tensor_core_shape=[None, 3])
# Run in TPUInferenceContext so that we hit the intended densification case.
context = tpu._TPUInferenceContext('tpu_inference')
context.Enter()
dense_features = fc_lib.DenseFeatures(embedding_column)
# Sqrtn combiner not supported for now.
if combiner == 'sqrtn':
with self.assertRaisesRegexp(
ValueError,
'Dense TPU Embedding does not support combiner'):
embedding_lookup = dense_features(input_features)
return
if combiner == 'mean':
expected_lookups = (
# example 0:
(7., 11.), # ids [2], embedding = [7, 11]
# example 1:
(2., 3.5
), # ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
)
elif combiner == 'sum':
expected_lookups = (
# example 0:
(7., 11.), # ids [2], embedding = [7, 11]
# example 1:
(4., 7
), # ids [0, 1], embedding = sum([1, 2] + [3, 5]) = [4, 7]
)
embedding_lookup = dense_features(input_features)
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
if shared:
self.assertCountEqual(('inp_shared_embedding:0', ),
tuple([v.name for v in global_vars]))
else:
self.assertCountEqual(
('dense_features/inp_embedding/embedding_weights:0', ),
tuple([v.name for v in global_vars]))
embedding_var = global_vars[0]
with _initialized_session():
self.assertAllEqual(embedding_values, embedding_var.eval())
eval_res = embedding_lookup.eval()
self.assertAllEqual(expected_lookups, eval_res)
context.Exit()
def test_feature_layer_cpu(self):
# Inputs.
vocabulary_size = 3
input_a = 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))
input_b = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
# example 2, ids []
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(3, 2))
input_features = {'aaa': input_a, 'bbb': input_b}
# 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_a = (
# example 0:
(7., 11.), # ids [2], embedding = [7, 11]
# example 1:
(2., 3.5
), # ids [0, 1], embedding = mean([1, 2] + [3, 5]) = [2, 3.5]
)
expected_lookups_b = (
# example 0:
(
(7., 11.),
(0., 0.),
), # ids [2], embedding = [[7, 11], [0, 0]]
# example 1:
(
(1., 2.),
(3., 5.),
), # ids [0, 1], embedding = [[1, 2], [3, 5]]
# example 2:
(
(0., 0.),
(0., 0.),
), # ids [], embedding = [[0, 0], [0, 0]]
)
# Build columns.
categorical_column_a = fc_lib.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
categorical_column_b = fc_lib.sequence_categorical_column_with_identity(
key='bbb', num_buckets=vocabulary_size)
embedding_column_a, embedding_column_b = tpu_fc.shared_embedding_columns_v2(
[categorical_column_a, categorical_column_b],
dimension=embedding_dimension,
initializer=_initializer,
max_sequence_lengths=[0, 2])
# Provide sparse input and get dense result.
dense_features = fc_lib.DenseFeatures([embedding_column_a])
sequence_features = fc_lib.SequenceFeatures([embedding_column_b])
embedding_lookup_a = dense_features(input_features)
embedding_lookup_b = sequence_features(input_features)
# Assert expected embedding variable and lookups.
global_vars = ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES)
self.assertItemsEqual(('aaa_bbb_shared_embedding:0', ),
tuple([v.name for v in global_vars]))
embedding_var = global_vars[0]
with _initialized_session():
self.assertAllEqual(embedding_values, embedding_var.eval())
self.assertAllEqual(expected_lookups_a, embedding_lookup_a.eval())
self.assertAllEqual(expected_lookups_b,
embedding_lookup_b[0].eval())
