512 lines
18 KiB
Python
512 lines
18 KiB
Python
# Copyright (c) 2019 NVIDIA CORPORATION. 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.
|
|
|
|
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import collections
|
|
import json
|
|
import math
|
|
import os
|
|
import random
|
|
import modeling
|
|
import optimization
|
|
import tokenization
|
|
import six
|
|
import tensorflow as tf
|
|
import horovod.tensorflow as hvd
|
|
import time
|
|
import csv
|
|
|
|
flags = tf.flags
|
|
FLAGS = None
|
|
|
|
def extract_flags():
|
|
|
|
## Required parameters
|
|
flags.DEFINE_string(
|
|
"data_dir", None,
|
|
"The input data dir. Should contain the .tsv files (or other data files) "
|
|
"for the task.")
|
|
|
|
flags.DEFINE_string("task_name", None, "The name of the task to train.")
|
|
|
|
flags.DEFINE_string("vocab_file", None,
|
|
"The vocabulary file that the BERT model was trained on.")
|
|
|
|
flags.DEFINE_bool(
|
|
"do_lower_case", True,
|
|
"Whether to lower case the input text. Should be True for uncased "
|
|
"models and False for cased models.")
|
|
|
|
flags.DEFINE_integer(
|
|
"max_seq_length", 128,
|
|
"The maximum total input sequence length after WordPiece tokenization. "
|
|
"Sequences longer than this will be truncated, and sequences shorter "
|
|
"than this will be padded.")
|
|
|
|
flags.DEFINE_bool(
|
|
"verbose_logging", False,
|
|
"If true, all of the warnings related to data processing will be printed. "
|
|
"A number of warnings are expected for a normal SQuAD evaluation.")
|
|
flags.mark_flag_as_required("data_dir")
|
|
flags.mark_flag_as_required("task_name")
|
|
flags.mark_flag_as_required("vocab_file")
|
|
return flags.FLAGS
|
|
|
|
|
|
class InputExample(object):
|
|
"""A single training/test example for simple sequence classification."""
|
|
|
|
def __init__(self, guid, text_a, text_b=None, label=None):
|
|
"""Constructs a InputExample.
|
|
Args:
|
|
guid: Unique id for the example.
|
|
text_a: string. The untokenized text of the first sequence. For single
|
|
sequence tasks, only this sequence must be specified.
|
|
text_b: (Optional) string. The untokenized text of the second sequence.
|
|
Only must be specified for sequence pair tasks.
|
|
label: (Optional) string. The label of the example. This should be
|
|
specified for train and dev examples, but not for test examples.
|
|
"""
|
|
self.guid = guid
|
|
self.text_a = text_a
|
|
self.text_b = text_b
|
|
self.label = label
|
|
|
|
class PaddingInputExample(object):
|
|
"""Fake example so the num input examples is a multiple of the batch size.
|
|
|
|
When running eval/predict on the TPU, we need to pad the number of examples
|
|
to be a multiple of the batch size, because the TPU requires a fixed batch
|
|
size. The alternative is to drop the last batch, which is bad because it means
|
|
the entire output data won't be generated.
|
|
|
|
We use this class instead of `None` because treating `None` as padding
|
|
battches could cause silent errors.
|
|
"""
|
|
|
|
class InputFeatures(object):
|
|
"""A single set of features of data."""
|
|
|
|
def __init__(self,
|
|
input_ids,
|
|
input_mask,
|
|
segment_ids,
|
|
label_id,
|
|
is_real_example=True):
|
|
self.input_ids = input_ids
|
|
self.input_mask = input_mask
|
|
self.segment_ids = segment_ids
|
|
self.label_id = label_id
|
|
self.is_real_example = is_real_example
|
|
|
|
|
|
class DataProcessor(object):
|
|
"""Base class for data converters for sequence classification data sets."""
|
|
|
|
def get_train_examples(self, data_dir):
|
|
"""Gets a collection of `InputExample`s for the train set."""
|
|
raise NotImplementedError()
|
|
|
|
def get_dev_examples(self, data_dir):
|
|
"""Gets a collection of `InputExample`s for the dev set."""
|
|
raise NotImplementedError()
|
|
|
|
def get_test_examples(self, data_dir):
|
|
"""Gets a collection of `InputExample`s for prediction."""
|
|
raise NotImplementedError()
|
|
|
|
def get_labels(self):
|
|
"""Gets the list of labels for this data set."""
|
|
raise NotImplementedError()
|
|
|
|
@classmethod
|
|
def _read_tsv(cls, input_file, quotechar=None):
|
|
"""Reads a tab separated value file."""
|
|
with tf.gfile.Open(input_file, "r") as f:
|
|
reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
|
|
lines = []
|
|
for line in reader:
|
|
lines.append(line)
|
|
return lines
|
|
|
|
|
|
class XnliProcessor(DataProcessor):
|
|
"""Processor for the XNLI data set."""
|
|
|
|
def __init__(self):
|
|
self.language = "zh"
|
|
|
|
def get_train_examples(self, data_dir):
|
|
"""See base class."""
|
|
lines = self._read_tsv(
|
|
os.path.join(data_dir, "multinli",
|
|
"multinli.train.%s.tsv" % self.language))
|
|
examples = []
|
|
for (i, line) in enumerate(lines):
|
|
if i == 0:
|
|
continue
|
|
guid = "train-%d" % (i)
|
|
text_a = tokenization.convert_to_unicode(line[0])
|
|
text_b = tokenization.convert_to_unicode(line[1])
|
|
label = tokenization.convert_to_unicode(line[2])
|
|
if label == tokenization.convert_to_unicode("contradictory"):
|
|
label = tokenization.convert_to_unicode("contradiction")
|
|
examples.append(
|
|
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
|
|
return examples
|
|
|
|
def get_dev_examples(self, data_dir):
|
|
"""See base class."""
|
|
lines = self._read_tsv(os.path.join(data_dir, "xnli.dev.tsv"))
|
|
examples = []
|
|
for (i, line) in enumerate(lines):
|
|
if i == 0:
|
|
continue
|
|
guid = "dev-%d" % (i)
|
|
language = tokenization.convert_to_unicode(line[0])
|
|
if language != tokenization.convert_to_unicode(self.language):
|
|
continue
|
|
text_a = tokenization.convert_to_unicode(line[6])
|
|
text_b = tokenization.convert_to_unicode(line[7])
|
|
label = tokenization.convert_to_unicode(line[1])
|
|
examples.append(
|
|
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
|
|
return examples
|
|
|
|
def get_labels(self):
|
|
"""See base class."""
|
|
return ["contradiction", "entailment", "neutral"]
|
|
|
|
|
|
class MnliProcessor(DataProcessor):
|
|
"""Processor for the MultiNLI data set (GLUE version)."""
|
|
|
|
def get_train_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
|
|
|
|
def get_dev_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "dev_matched.tsv")),
|
|
"dev_matched")
|
|
|
|
def get_test_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "test_matched.tsv")), "test")
|
|
|
|
def get_labels(self):
|
|
"""See base class."""
|
|
return ["contradiction", "entailment", "neutral"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev sets."""
|
|
examples = []
|
|
for (i, line) in enumerate(lines):
|
|
if i == 0:
|
|
continue
|
|
guid = "%s-%s" % (set_type, tokenization.convert_to_unicode(line[0]))
|
|
text_a = tokenization.convert_to_unicode(line[8])
|
|
text_b = tokenization.convert_to_unicode(line[9])
|
|
if set_type == "test":
|
|
label = "contradiction"
|
|
else:
|
|
label = tokenization.convert_to_unicode(line[-1])
|
|
examples.append(
|
|
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
|
|
return examples
|
|
|
|
|
|
class MrpcProcessor(DataProcessor):
|
|
"""Processor for the MRPC data set (GLUE version)."""
|
|
|
|
def get_train_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
|
|
|
|
def get_dev_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
|
|
|
|
def get_test_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
|
|
|
|
def get_labels(self):
|
|
"""See base class."""
|
|
return ["0", "1"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev sets."""
|
|
examples = []
|
|
for (i, line) in enumerate(lines):
|
|
if i == 0:
|
|
continue
|
|
guid = "%s-%s" % (set_type, i)
|
|
text_a = tokenization.convert_to_unicode(line[3])
|
|
text_b = tokenization.convert_to_unicode(line[4])
|
|
if set_type == "test":
|
|
label = "0"
|
|
else:
|
|
label = tokenization.convert_to_unicode(line[0])
|
|
examples.append(
|
|
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
|
|
return examples
|
|
|
|
|
|
class ColaProcessor(DataProcessor):
|
|
"""Processor for the CoLA data set (GLUE version)."""
|
|
|
|
def get_train_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
|
|
|
|
def get_dev_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
|
|
|
|
def get_test_examples(self, data_dir):
|
|
"""See base class."""
|
|
return self._create_examples(
|
|
self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
|
|
|
|
def get_labels(self):
|
|
"""See base class."""
|
|
return ["0", "1"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev sets."""
|
|
examples = []
|
|
for (i, line) in enumerate(lines):
|
|
# Only the test set has a header
|
|
if set_type == "test" and i == 0:
|
|
continue
|
|
guid = "%s-%s" % (set_type, i)
|
|
if set_type == "test":
|
|
text_a = tokenization.convert_to_unicode(line[1])
|
|
label = "0"
|
|
else:
|
|
text_a = tokenization.convert_to_unicode(line[3])
|
|
label = tokenization.convert_to_unicode(line[1])
|
|
examples.append(
|
|
InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
|
|
return examples
|
|
|
|
|
|
def _truncate_seq_pair(tokens_a, tokens_b, max_length):
|
|
"""Truncates a sequence pair in place to the maximum length."""
|
|
|
|
# This is a simple heuristic which will always truncate the longer sequence
|
|
# one token at a time. This makes more sense than truncating an equal percent
|
|
# of tokens from each, since if one sequence is very short then each token
|
|
# that's truncated likely contains more information than a longer sequence.
|
|
while True:
|
|
total_length = len(tokens_a) + len(tokens_b)
|
|
if total_length <= max_length:
|
|
break
|
|
if len(tokens_a) > len(tokens_b):
|
|
tokens_a.pop()
|
|
else:
|
|
tokens_b.pop()
|
|
|
|
def convert_single_example(ex_index, example, label_list, max_seq_length,
|
|
tokenizer, verbose_logging=False):
|
|
"""Converts a single `InputExample` into a single `InputFeatures`."""
|
|
|
|
if isinstance(example, PaddingInputExample):
|
|
return InputFeatures(
|
|
input_ids=[0] * max_seq_length,
|
|
input_mask=[0] * max_seq_length,
|
|
segment_ids=[0] * max_seq_length,
|
|
label_id=0,
|
|
is_real_example=False)
|
|
|
|
label_map = {}
|
|
for (i, label) in enumerate(label_list):
|
|
label_map[label] = i
|
|
|
|
tokens_a = tokenizer.tokenize(example.text_a)
|
|
tokens_b = None
|
|
if example.text_b:
|
|
tokens_b = tokenizer.tokenize(example.text_b)
|
|
|
|
if tokens_b:
|
|
# Modifies `tokens_a` and `tokens_b` in place so that the total
|
|
# length is less than the specified length.
|
|
# Account for [CLS], [SEP], [SEP] with "- 3"
|
|
_truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3)
|
|
else:
|
|
# Account for [CLS] and [SEP] with "- 2"
|
|
if len(tokens_a) > max_seq_length - 2:
|
|
tokens_a = tokens_a[0:(max_seq_length - 2)]
|
|
|
|
# The convention in BERT is:
|
|
# (a) For sequence pairs:
|
|
# tokens: [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]
|
|
# type_ids: 0 0 0 0 0 0 0 0 1 1 1 1 1 1
|
|
# (b) For single sequences:
|
|
# tokens: [CLS] the dog is hairy . [SEP]
|
|
# type_ids: 0 0 0 0 0 0 0
|
|
#
|
|
# Where "type_ids" are used to indicate whether this is the first
|
|
# sequence or the second sequence. The embedding vectors for `type=0` and
|
|
# `type=1` were learned during pre-training and are added to the wordpiece
|
|
# embedding vector (and position vector). This is not *strictly* necessary
|
|
# since the [SEP] token unambiguously separates the sequences, but it makes
|
|
# it easier for the model to learn the concept of sequences.
|
|
#
|
|
# For classification tasks, the first vector (corresponding to [CLS]) is
|
|
# used as the "sentence vector". Note that this only makes sense because
|
|
# the entire model is fine-tuned.
|
|
tokens = []
|
|
segment_ids = []
|
|
tokens.append("[CLS]")
|
|
segment_ids.append(0)
|
|
for token in tokens_a:
|
|
tokens.append(token)
|
|
segment_ids.append(0)
|
|
tokens.append("[SEP]")
|
|
segment_ids.append(0)
|
|
|
|
if tokens_b:
|
|
for token in tokens_b:
|
|
tokens.append(token)
|
|
segment_ids.append(1)
|
|
tokens.append("[SEP]")
|
|
segment_ids.append(1)
|
|
|
|
input_ids = tokenizer.convert_tokens_to_ids(tokens)
|
|
|
|
# The mask has 1 for real tokens and 0 for padding tokens. Only real
|
|
# tokens are attended to.
|
|
input_mask = [1] * len(input_ids)
|
|
|
|
# Zero-pad up to the sequence length.
|
|
while len(input_ids) < max_seq_length:
|
|
input_ids.append(0)
|
|
input_mask.append(0)
|
|
segment_ids.append(0)
|
|
|
|
assert len(input_ids) == max_seq_length
|
|
assert len(input_mask) == max_seq_length
|
|
assert len(segment_ids) == max_seq_length
|
|
|
|
label_id = label_map[example.label]
|
|
if ex_index < 5 and verbose_logging:
|
|
tf.logging.info("*** Example ***")
|
|
tf.logging.info("guid: %s" % (example.guid))
|
|
tf.logging.info("tokens: %s" % " ".join(
|
|
[tokenization.printable_text(x) for x in tokens]))
|
|
tf.logging.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
|
|
tf.logging.info("input_mask: %s" % " ".join([str(x) for x in input_mask]))
|
|
tf.logging.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids]))
|
|
tf.logging.info("label: %s (id = %d)" % (example.label, label_id))
|
|
|
|
feature = InputFeatures(
|
|
input_ids=input_ids,
|
|
input_mask=input_mask,
|
|
segment_ids=segment_ids,
|
|
label_id=label_id,
|
|
is_real_example=True)
|
|
return feature
|
|
|
|
# This function is not used by this file but is still used by the Colab and
|
|
# people who depend on it.
|
|
def convert_examples_to_features(examples, label_list, max_seq_length,
|
|
tokenizer):
|
|
"""Convert a set of `InputExample`s to a list of `InputFeatures`."""
|
|
|
|
features = []
|
|
for (ex_index, example) in enumerate(examples):
|
|
if ex_index % 10000 == 0:
|
|
tf.logging.info("Writing example %d of %d" % (ex_index, len(examples)))
|
|
|
|
feature = convert_single_example(ex_index, example, label_list,
|
|
max_seq_length, tokenizer, FLAGS.verbose_logging)
|
|
|
|
features.append(feature)
|
|
return features
|
|
|
|
def file_based_convert_examples_to_features(
|
|
examples, label_list, max_seq_length, tokenizer, output_file):
|
|
"""Convert a set of `InputExample`s to a TFRecord file."""
|
|
|
|
writer = tf.python_io.TFRecordWriter(output_file)
|
|
|
|
for (ex_index, example) in enumerate(examples):
|
|
if ex_index % 10000 == 0:
|
|
tf.logging.info("Writing example %d of %d" % (ex_index, len(examples)))
|
|
|
|
feature = convert_single_example(ex_index, example, label_list,
|
|
max_seq_length, tokenizer)
|
|
|
|
def create_int_feature(values):
|
|
f = tf.train.Feature(int64_list=tf.train.Int64List(value=list(values)))
|
|
return f
|
|
|
|
features = collections.OrderedDict()
|
|
features["input_ids"] = create_int_feature(feature.input_ids)
|
|
features["input_mask"] = create_int_feature(feature.input_mask)
|
|
features["segment_ids"] = create_int_feature(feature.segment_ids)
|
|
features["label_ids"] = create_int_feature([feature.label_id])
|
|
features["is_real_example"] = create_int_feature(
|
|
[int(feature.is_real_example)])
|
|
|
|
tf_example = tf.train.Example(features=tf.train.Features(feature=features))
|
|
writer.write(tf_example.SerializeToString())
|
|
writer.close()
|
|
|
|
def main():
|
|
processors = {
|
|
"cola": ColaProcessor,
|
|
"mnli": MnliProcessor,
|
|
"mrpc": MrpcProcessor,
|
|
"xnli": XnliProcessor,
|
|
}
|
|
task_name = FLAGS.task_name.lower()
|
|
if task_name not in processors:
|
|
raise ValueError("Task not found: %s" % (task_name))
|
|
processor = processors[task_name]()
|
|
label_list = processor.get_labels()
|
|
|
|
tokenizer = tokenization.FullTokenizer(
|
|
vocab_file=FLAGS.vocab_file, do_lower_case=FLAGS.do_lower_case)
|
|
tf.gfile.MakeDirs(FLAGS.data_dir + "final_tfrecords_sharded")
|
|
train_examples = processor.get_train_examples(FLAGS.data_dir)
|
|
train_file = os.path.join(FLAGS.data_dir, "final_tfrecords_sharded/" + task_name + "train.tf_record")
|
|
file_based_convert_examples_to_features(
|
|
train_examples, label_list, FLAGS.max_seq_length, tokenizer, train_file)
|
|
|
|
eval_examples = processor.get_dev_examples(FLAGS.data_dir)
|
|
eval_file = os.path.join(FLAGS.data_dir, "final_tfrecords_sharded/" + task_name + "eval.tf_record")
|
|
file_based_convert_examples_to_features(
|
|
eval_examples, label_list, FLAGS.max_seq_length, tokenizer, eval_file)
|
|
|
|
predict_examples = processor.get_test_examples(FLAGS.data_dir)
|
|
predict_file = os.path.join(FLAGS.data_dir, "final_tfrecords_sharded/" + task_name + "predict.tf_record")
|
|
file_based_convert_examples_to_features(predict_examples, label_list,
|
|
FLAGS.max_seq_length, tokenizer,
|
|
predict_file)
|
|
|
|
if __name__ == "__main__":
|
|
main() |