def test_bert_trainer(self): """Validate that the Keras object can be created.""" # Build a transformer network to use within the BERT trainer. vocab_size = 100 sequence_length = 512 test_network = networks.TransformerEncoder( vocab_size=vocab_size, num_layers=2, sequence_length=sequence_length) # Create a BERT trainer with the created network. num_classes = 3 bert_trainer_model = bert_token_classifier.BertTokenClassifier( test_network, num_classes=num_classes) # Create a set of 2-dimensional inputs (the first dimension is implicit). word_ids = tf.keras.Input(shape=(sequence_length, ), dtype=tf.int32) mask = tf.keras.Input(shape=(sequence_length, ), dtype=tf.int32) type_ids = tf.keras.Input(shape=(sequence_length, ), dtype=tf.int32) # Invoke the trainer model on the inputs. This causes the layer to be built. sequence_outs = bert_trainer_model([word_ids, mask, type_ids]) # Validate that the outputs are of the expected shape. expected_classification_shape = [None, sequence_length, num_classes] self.assertAllEqual(expected_classification_shape, sequence_outs.shape.as_list())
def test_serialize_deserialize(self): """Validate that the BERT trainer can be serialized and deserialized.""" # Build a transformer network to use within the BERT trainer. (Here, we use # a short sequence_length for convenience.) test_network = networks.TransformerEncoder(vocab_size=100, num_layers=2, sequence_length=5) # Create a BERT trainer with the created network. (Note that all the args # are different, so we can catch any serialization mismatches.) bert_trainer_model = bert_token_classifier.BertTokenClassifier( test_network, num_classes=4, initializer='zeros', output='predictions') # Create another BERT trainer via serialization and deserialization. config = bert_trainer_model.get_config() new_bert_trainer_model = ( bert_token_classifier.BertTokenClassifier.from_config(config)) # Validate that the config can be forced to JSON. _ = new_bert_trainer_model.to_json() # If the serialization was successful, the new config should match the old. self.assertAllEqual(bert_trainer_model.get_config(), new_bert_trainer_model.get_config())
def test_bert_trainer_tensor_call(self): """Validate that the Keras object can be invoked.""" # Build a transformer network to use within the BERT trainer. (Here, we use # a short sequence_length for convenience.) test_network = networks.BertEncoder( vocab_size=100, num_layers=2, max_sequence_length=2) # Create a BERT trainer with the created network. bert_trainer_model = bert_token_classifier.BertTokenClassifier( test_network, num_classes=2) # Create a set of 2-dimensional data tensors to feed into the model. word_ids = tf.constant([[1, 1], [2, 2]], dtype=tf.int32) mask = tf.constant([[1, 1], [1, 0]], dtype=tf.int32) type_ids = tf.constant([[1, 1], [2, 2]], dtype=tf.int32) # Invoke the trainer model on the tensors. In Eager mode, this does the # actual calculation. (We can't validate the outputs, since the network is # too complex: this simply ensures we're not hitting runtime errors.) _ = bert_trainer_model([word_ids, mask, type_ids])