def test_load_embedding_initializer(self):
"""Tests for the load_embedding_initializer wrapper."""
embedding_loading_initializer = (checkpoint_ops._load_embedding_initializer(
new_vocab_file=self.new_feature_vocab_file,
old_vocab_file=self.old_feature_vocab_file,
new_vocab_size=5,
embedding_dim=16,
embedding_tensor_name='some_scope/embeddings',
ckpt_path=[self.checkpoint_file],
num_oov_buckets=1,
initializer=self.initializer))
# The new weight matrix is of size
# [5 feature vocab + 1 feature OOV, 16 (embedding dimension)], where the
# last vocab row (2nd last row) is newly initialized (wasn't found in
# previous vocab) and the actual last row is OOV and also newly initialized.
# Use a partitioned variable to confirm that the offset logic works.
expected_remapped_embeddings = np.concatenate(
[
np.reshape(range(64), [4, 16]),
np.reshape([self.init_val] * 32, [2, 16]),
],
axis=0)
remapped_embeddings = variable_scope.get_variable(
name='embedding/obtained_embedding_matrix',
shape=[6, 16],
initializer=embedding_loading_initializer,
partitioner=partitioned_variables.fixed_size_partitioner(2))
with self.cached_session():
self.evaluate(variables.global_variables_initializer())
self.assertAllClose(expected_remapped_embeddings,
remapped_embeddings.as_tensor())
def test_load_embedding_initializer(self):
"""Tests for the load_embedding_initializer wrapper."""
embedding_loading_initializer = (checkpoint_ops._load_embedding_initializer(
new_vocab_file=self.new_feature_vocab_file,
old_vocab_file=self.old_feature_vocab_file,
new_vocab_size=5,
embedding_dim=16,
embedding_tensor_name='some_scope/embeddings',
ckpt_path=[self.checkpoint_file],
num_oov_buckets=1,
initializer=self.initializer))
expected_remapped_embeddings = np.concatenate(
[
np.reshape(range(64), [4, 16]),
np.reshape([self.init_val] * 32, [2, 16]),
],
axis=0)
# The new weight matrix is of size
# [5 feature vocab + 1 feature OOV, 16 (embedding dimension)], where the
# last vocab row (2nd last row) is newly initialized (wasn't found in
# previous vocab) and the actual last row is OOV and also newly initialized.
# Use a partitioned variable to confirm that the offset logic works.
remapped_embeddings = variable_scope.get_variable(
name='embedding/obtained_embedding_matrix',
shape=[6, 16],
initializer=embedding_loading_initializer,
partitioner=partitioned_variables.fixed_size_partitioner(2))
with self.test_session():
variables.global_variables_initializer().run()
self.assertAllClose(expected_remapped_embeddings,
remapped_embeddings.as_tensor().eval())
def test_load_embedding_initializer_large_oov(self):
"""Tests for the large OOV case for load_embedding_initializer wrapper."""
self.new_feature_vocab_file = os.path.join(
self.get_temp_dir(), 'new_feature_vocab.txt')
with open(self.new_feature_vocab_file, 'w') as f:
f.write('\n'.join(['one', 'zero', 'two', 'four']) + '\n')
# Checkpoint has 5 entries, 3 of which correspond to OOV.
self.old_feature_vocab_file = os.path.join(
self.get_temp_dir(), 'old_feature_vocab.txt')
with open(self.old_feature_vocab_file, 'w') as f:
f.write('\n'.join(['zero', 'one']) + '\n')
embedding_loading_initializer = (checkpoint_ops._load_embedding_initializer(
new_vocab_file=self.new_feature_vocab_file,
old_vocab_file=self.old_feature_vocab_file,
new_vocab_size=4,
embedding_dim=16,
embedding_tensor_name='some_scope/embeddings',
ckpt_path=[self.checkpoint_file],
num_oov_buckets=5,
initializer=self.initializer))
expected_remapped_embeddings = np.concatenate(
[
np.reshape(range(16, 32), [1, 16]),
np.reshape(range(16), [1, 16]),
np.reshape([self.init_val] * 112, [7, 16]),
],
axis=0)
# The new weight matrix is of size
# [4 feature vocab + 5 feature OOV, 16 (embedding dimension)], where the
# 3rd and 4th rows are not found in the old vocabulary and therefore newly
# initialized. The last five rows are OOV and also newly initialized.
# Use a partitioned variable to confirm that the offset logic works.
remapped_embeddings = variable_scope.get_variable(
name='embedding/obtained_embedding_matrix',
shape=[9, 16],
initializer=embedding_loading_initializer,
partitioner=partitioned_variables.fixed_size_partitioner(2))
with self.test_session():
variables.global_variables_initializer().run()
self.assertAllClose(expected_remapped_embeddings,
remapped_embeddings.as_tensor().eval())
def test_load_embedding_initializer_large_oov(self):
"""Tests for the large OOV case for load_embedding_initializer wrapper."""
self.new_feature_vocab_file = os.path.join(self.get_temp_dir(),
'new_feature_vocab.txt')
with open(self.new_feature_vocab_file, 'w') as f:
f.write('\n'.join(['one', 'zero', 'two', 'four']) + '\n')
# Checkpoint has 5 entries, 3 of which correspond to OOV.
self.old_feature_vocab_file = os.path.join(self.get_temp_dir(),
'old_feature_vocab.txt')
with open(self.old_feature_vocab_file, 'w') as f:
f.write('\n'.join(['zero', 'one']) + '\n')
embedding_loading_initializer = (
checkpoint_ops._load_embedding_initializer(
new_vocab_file=self.new_feature_vocab_file,
old_vocab_file=self.old_feature_vocab_file,
new_vocab_size=4,
embedding_dim=16,
embedding_tensor_name='some_scope/embeddings',
ckpt_path=[self.checkpoint_file],
num_oov_buckets=5,
initializer=self.initializer))
expected_remapped_embeddings = np.concatenate([
np.reshape(range(16, 32), [1, 16]),
np.reshape(range(16), [1, 16]),
np.reshape([self.init_val] * 112, [7, 16]),
],
axis=0)
# The new weight matrix is of size
# [4 feature vocab + 5 feature OOV, 16 (embedding dimension)], where the
# 3rd and 4th rows are not found in the old vocabulary and therefore newly
# initialized. The last five rows are OOV and also newly initialized.
# Use a partitioned variable to confirm that the offset logic works.
remapped_embeddings = variable_scope.get_variable(
name='embedding/obtained_embedding_matrix',
shape=[9, 16],
initializer=embedding_loading_initializer,
partitioner=partitioned_variables.fixed_size_partitioner(2))
with self.test_session():
variables.global_variables_initializer().run()
self.assertAllClose(expected_remapped_embeddings,
remapped_embeddings.as_tensor().eval())
def test_load_embedding_initializer_old_row_vocab(self):
"""Tests for load_embedding_initializer where we constrain old vocab."""
embedding_loading_initializer = (
checkpoint_ops._load_embedding_initializer(
new_vocab_file=self.new_feature_vocab_file,
old_vocab_file=self.old_feature_vocab_file,
# Considered old vocabulary becomes ['zero', 'one', 'two']. This
# means 'three' in the new vocabulary is newly initialized.
old_vocab_size=3,
new_vocab_size=5,
embedding_dim=16,
embedding_tensor_name='some_scope/embeddings',
ckpt_path=[self.checkpoint_file],
num_oov_buckets=1,
initializer=self.initializer))
# The new weight matrix is of size
# [5 feature vocab + 1 feature OOV, 16 (embedding dimension)], where the
# last vocab row (2nd last row) is newly initialized (wasn't found in
# previous vocab) and the actual last row is OOV and also newly initialized.
# Use a partitioned variable to confirm that the offset logic works.
expected_remapped_embeddings = np.concatenate(
[
np.reshape(range(48), [3, 16]),
np.reshape([self.init_val] * 48, [3, 16]),
],
axis=0)
remapped_embeddings = variable_scope.get_variable(
name='embedding/obtained_embedding_matrix',
shape=[6, 16],
initializer=embedding_loading_initializer,
partitioner=partitioned_variables.fixed_size_partitioner(2))
with self.test_session():
variables.global_variables_initializer().run()
self.assertAllClose(expected_remapped_embeddings,
remapped_embeddings.as_tensor().eval())
