Spaces:
Sleeping
Sleeping
File size: 1,532 Bytes
15bcbe6 |
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 |
# Copyright 2022 Google.
#
# 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.
"""Add Tasks to registry."""
import functools
from transformer import text_dataset
import seqio
import t5.data
from t5.data import preprocessors
import tensorflow as tf
TaskRegistry = seqio.TaskRegistry
def define_pg19_task(name: str, vocab: seqio.Vocabulary):
seqio.TaskRegistry.add(
name,
seqio.TfdsDataSource(
tfds_name="pg19:0.1.1"
),
preprocessors=[
functools.partial(text_dataset.rekey_articles,
rekey={"book_text": "targets"},
keep={"book_title", "book_id", "publication_date"}),
seqio.preprocessors.tokenize,
],
output_features={
"targets": seqio.Feature(vocab,
add_eos=False, dtype=tf.int32),
}
)
T5_DEFAULT_VOCABULARY = t5.data.get_default_vocabulary()
define_pg19_task("pg19_bytes", seqio.ByteVocabulary())
define_pg19_task("pg19_tokens", T5_DEFAULT_VOCABULARY)
|