Spaces:
Runtime error
Runtime error
File size: 4,825 Bytes
5672777 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
# Copyright 2023 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tests for BERT trainer network."""
from absl.testing import parameterized
import tensorflow as tf, tf_keras
from official.nlp.modeling import layers
from official.nlp.modeling import networks
from official.nlp.modeling.models import bert_classifier
class BertClassifierTest(tf.test.TestCase, parameterized.TestCase):
@parameterized.named_parameters(('single_cls', 1, False), ('3_cls', 3, False),
('3_cls_dictoutputs', 3, True))
def test_bert_trainer(self, num_classes, dict_outputs):
"""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.BertEncoder(
vocab_size=vocab_size, num_layers=2, dict_outputs=dict_outputs)
# Create a BERT trainer with the created network.
bert_trainer_model = bert_classifier.BertClassifier(
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.
cls_outs = bert_trainer_model([word_ids, mask, type_ids])
# Validate that the outputs are of the expected shape.
expected_classification_shape = [None, num_classes]
self.assertAllEqual(expected_classification_shape, cls_outs.shape.as_list())
@parameterized.named_parameters(
('single_cls', 1, False),
('2_cls', 2, False),
('single_cls_custom_head', 1, True),
('2_cls_custom_head', 2, True))
def test_bert_trainer_tensor_call(self, num_classes, use_custom_head):
"""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)
cls_head = layers.GaussianProcessClassificationHead(
inner_dim=0, num_classes=num_classes) if use_custom_head else None
# Create a BERT trainer with the created network.
bert_trainer_model = bert_classifier.BertClassifier(
test_network, num_classes=num_classes, cls_head=cls_head)
# 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])
@parameterized.named_parameters(
('default_cls_head', None),
('sngp_cls_head', layers.GaussianProcessClassificationHead(
inner_dim=0, num_classes=4)))
def test_serialize_deserialize(self, cls_head):
"""Validate that the BERT trainer can be serialized and deserialized."""
# Build a transformer network to use within the BERT trainer.
test_network = networks.BertEncoder(vocab_size=100, num_layers=2)
# 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_classifier.BertClassifier(
test_network, num_classes=4, initializer='zeros', cls_head=cls_head)
# Create another BERT trainer via serialization and deserialization.
config = bert_trainer_model.get_config()
new_bert_trainer_model = bert_classifier.BertClassifier.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())
if __name__ == '__main__':
tf.test.main()
|