File size: 2,413 Bytes
25e57c6 | 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 | # 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 official.nlp.projects.bigbird.encoder."""
import numpy as np
import tensorflow as tf, tf_keras
from official.projects.bigbird import encoder
class BigBirdEncoderTest(tf.test.TestCase):
def test_encoder(self):
sequence_length = 1024
batch_size = 2
vocab_size = 1024
network = encoder.BigBirdEncoder(
num_layers=1, vocab_size=1024, max_position_embeddings=4096)
word_id_data = np.random.randint(
vocab_size, size=(batch_size, sequence_length))
mask_data = np.random.randint(2, size=(batch_size, sequence_length))
type_id_data = np.random.randint(2, size=(batch_size, sequence_length))
outputs = network([word_id_data, mask_data, type_id_data])
self.assertEqual(outputs["sequence_output"].shape,
(batch_size, sequence_length, 768))
def test_save_restore(self):
sequence_length = 1024
batch_size = 2
vocab_size = 1024
network = encoder.BigBirdEncoder(
num_layers=1, vocab_size=1024, max_position_embeddings=4096)
word_id_data = np.random.randint(
vocab_size, size=(batch_size, sequence_length))
mask_data = np.random.randint(2, size=(batch_size, sequence_length))
type_id_data = np.random.randint(2, size=(batch_size, sequence_length))
inputs = dict(
input_word_ids=word_id_data,
input_mask=mask_data,
input_type_ids=type_id_data)
ref_outputs = network(inputs)
model_path = self.get_temp_dir() + "/model"
network.save(model_path)
loaded = tf_keras.models.load_model(model_path)
outputs = loaded(inputs)
self.assertAllClose(outputs["sequence_output"],
ref_outputs["sequence_output"])
if __name__ == "__main__":
tf.test.main()
|