def test_layer_invocation_with_mask(self):
test_layer = transformer.Transformer(num_attention_heads=10,
intermediate_size=2048,
intermediate_activation='relu')
sequence_length = 21
width = 80
# Create a 3-dimensional input (the first dimension is implicit).
data_tensor = tf.keras.Input(shape=(sequence_length, width))
# Create a 2-dimensional input (the first dimension is implicit).
mask_tensor = tf.keras.Input(shape=(sequence_length, sequence_length))
output_tensor = test_layer([data_tensor, mask_tensor])
# Create a model from the test layer.
model = tf.keras.Model([data_tensor, mask_tensor], output_tensor)
# Invoke the model on test data. We can't validate the output data itself
# (the NN is too complex) but this will rule out structural runtime errors.
batch_size = 6
input_data = 10 * np.random.random_sample(
(batch_size, sequence_length, width))
# The attention mask should be of shape (batch, from_seq_len, to_seq_len),
# which here is (batch, sequence_length, sequence_length)
mask_data = np.random.randint(2,
size=(batch_size, sequence_length,
sequence_length))
_ = model.predict([input_data, mask_data])
def test_layer_creation(self):
test_layer = transformer.Transformer(num_attention_heads=10,
intermediate_size=2048,
intermediate_activation='relu')
sequence_length = 21
width = 80
# Create a 3-dimensional input (the first dimension is implicit).
data_tensor = tf.keras.Input(shape=(sequence_length, width))
output_tensor = test_layer(data_tensor)
# The default output of a transformer layer should be the same as the input.
self.assertEqual(data_tensor.shape.as_list(),
output_tensor.shape.as_list())
def test_layer_creation_with_incorrect_mask_fails(self):
test_layer = transformer.Transformer(num_attention_heads=10,
intermediate_size=2048,
intermediate_activation='relu')
sequence_length = 21
width = 80
# Create a 3-dimensional input (the first dimension is implicit).
data_tensor = tf.keras.Input(shape=(sequence_length, width))
# Create a 2-dimensional input (the first dimension is implicit).
mask_tensor = tf.keras.Input(shape=(sequence_length,
sequence_length - 3))
with self.assertRaisesRegex(ValueError,
'When passing a mask tensor.*'):
_ = test_layer([data_tensor, mask_tensor])
def test_dynamic_layer_sequence(self):
test_layer = transformer.Transformer(
num_attention_heads=10,
intermediate_size=2048,
intermediate_activation='relu',
kernel_initializer=tf.keras.initializers.TruncatedNormal(
stddev=0.02))
# Create a 3-dimensional input (the first dimension is implicit).
width = 30
input_tensor = tf.keras.Input(shape=(None, width))
output_tensor = test_layer(input_tensor)
model = tf.keras.Model(input_tensor, output_tensor)
input_length = 17
input_data = np.ones((1, input_length, width))
output_data = model.predict(input_data)
self.assertAllEqual([1, input_length, width], output_data.shape)
def test_layer_invocation(self):
test_layer = transformer.Transformer(num_attention_heads=10,
intermediate_size=2048,
intermediate_activation='relu')
sequence_length = 21
width = 80
# Create a 3-dimensional input (the first dimension is implicit).
data_tensor = tf.keras.Input(shape=(sequence_length, width))
output_tensor = test_layer(data_tensor)
# Create a model from the test layer.
model = tf.keras.Model(data_tensor, output_tensor)
# Invoke the model on test data. We can't validate the output data itself
# (the NN is too complex) but this will rule out structural runtime errors.
batch_size = 6
input_data = 10 * np.random.random_sample(
(batch_size, sequence_length, width))
_ = model.predict(input_data)
