demo.py

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import sys
sys.path.append("bert")
import collections
import csv
import os, sys, glob, re
import modeling
import optimization
import tokenization
import tensorflow as tf
import numpy as np
import linecache

flags = tf.flags

FLAGS = flags.FLAGS

from flask import Flask, request
from flask import jsonify 
app = Flask(__name__)

flags.DEFINE_string("task_name", 'supe', "The name of the task to train.")
flags.DEFINE_string("vocab_file", './bert/multi_cased_L-12_H-768_A-12/vocab.txt','')
flags.DEFINE_string("bert_config_file",'./bert/multi_cased_L-12_H-768_A-12/bert_config.json','')
flags.DEFINE_string('init_checkpoint','./bert/multi_cased_L-12_H-768_A-12/bert_model.ckpt','')
flags.DEFINE_integer("max_seq_length",512,'')
flags.DEFINE_string('output_dir','./bert/sentence-alignment-classification-model_Feb_11_2019/output_apr_30_2019/','')
flags.DEFINE_bool('do_lower_case',False,'')
flags.DEFINE_bool('use_tpu',False,'')
tf.flags.DEFINE_string("master", None, "[Optional] TensorFlow master URL.")

flags.DEFINE_integer("train_batch_size", 32, "Total batch size for training.")

flags.DEFINE_integer("eval_batch_size", 8, "Total batch size for eval.")

flags.DEFINE_integer("predict_batch_size", 8, "Total batch size for predict.")

flags.DEFINE_float("learning_rate", 5e-5, "The initial learning rate for Adam.")

flags.DEFINE_float("num_train_epochs", 3.0,
                   "Total number of training epochs to perform.")

flags.DEFINE_float(
    "warmup_proportion", 0.1,
    "Proportion of training to perform linear learning rate warmup for. "
    "E.g., 0.1 = 10% of training.")

flags.DEFINE_integer("save_checkpoints_steps", 1000,
                     "How often to save the model checkpoint.")

flags.DEFINE_integer("iterations_per_loop", 1000,
                     "How many steps to make in each estimator call.")
flags.DEFINE_integer(
    "num_tpu_cores", 8,
    "Only used if `use_tpu` is True. Total number of TPU cores to use.")


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((x.replace('\0','') for x in f), delimiter="\t", quotechar=quotechar)
      lines = []
      for line in reader:
        lines.append(line)
      return lines

class SupervisorProcessor(DataProcessor):
  """Processor for the Supervisor data."""

  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, filename):
    """See base class."""
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, filename)), "test")

  def get_labels(self):
    """See base class."""
    return ["great-aligned", "good-aligned", "not-aligned", "semi-aligned"]

  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)
      try:
        text_a = tokenization.convert_to_unicode(line[1])
      except:
        text_a = ' '
      try:
        text_b = tokenization.convert_to_unicode(line[2])
      except:
        text_b = ' '
      if text_a == ' ' or text_b == ' ':
        text_a = ' ' 
        text_b = ' '
      if set_type == "test":
        label = "great-aligned"
      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

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)

    features.append(feature)
  return features


def convert_single_example(ex_index, example, label_list, max_seq_length,
                           tokenizer):
  """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:
    total_length = len(tokens_a) + len(tokens_b)
    if total_length > max_seq_length:
      print("TOO LONG: "+str(total_length))    
    # 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]

  feature = InputFeatures(
      input_ids=input_ids,
      input_mask=input_mask,
      segment_ids=segment_ids,
      label_id=label_id,
      is_real_example=True)
  return feature


def create_model(bert_config, is_training, input_ids, input_mask, segment_ids,
                 labels, num_labels, use_one_hot_embeddings):
  """Creates a classification model."""
  model = modeling.BertModel(
      config=bert_config,
      is_training=is_training,
      input_ids=input_ids,
      input_mask=input_mask,
      token_type_ids=segment_ids,
      use_one_hot_embeddings=use_one_hot_embeddings)

  # In the demo, we are doing a simple classification task on the entire
  # segment.
  #
  # If you want to use the token-level output, use model.get_sequence_output()
  # instead.
  output_layer = model.get_pooled_output()

  hidden_size = output_layer.shape[-1].value

  output_weights = tf.get_variable(
      "output_weights", [num_labels, hidden_size],
      initializer=tf.truncated_normal_initializer(stddev=0.02))

  output_bias = tf.get_variable(
      "output_bias", [num_labels], initializer=tf.zeros_initializer())

  with tf.variable_scope("loss"):
    if is_training:
      # I.e., 0.1 dropout
      output_layer = tf.nn.dropout(output_layer, keep_prob=0.9)

    logits = tf.matmul(output_layer, output_weights, transpose_b=True)
    logits = tf.nn.bias_add(logits, output_bias)
    probabilities = tf.nn.softmax(logits, axis=-1)
    log_probs = tf.nn.log_softmax(logits, axis=-1)

    one_hot_labels = tf.one_hot(labels, depth=num_labels, dtype=tf.float32)

    per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
    loss = tf.reduce_mean(per_example_loss)

    return (loss, per_example_loss, logits, probabilities)



def model_fn_builder(bert_config, num_labels, init_checkpoint, learning_rate,
                     num_train_steps, num_warmup_steps, use_tpu,
                     use_one_hot_embeddings):
  """Returns `model_fn` closure for TPUEstimator."""

  def model_fn(features, labels, mode, params):  # pylint: disable=unused-argument
    """The `model_fn` for TPUEstimator."""

    tf.logging.info("*** Features ***")
    for name in sorted(features.keys()):
      tf.logging.info("  name = %s, shape = %s" % (name, features[name].shape))

    input_ids = features["input_ids"]
    input_mask = features["input_mask"]
    segment_ids = features["segment_ids"]
    label_ids = features["label_ids"]
    is_real_example = None
    if "is_real_example" in features:
      is_real_example = tf.cast(features["is_real_example"], dtype=tf.float32)
    else:
      is_real_example = tf.ones(tf.shape(label_ids), dtype=tf.float32)

    is_training = (mode == tf.estimator.ModeKeys.TRAIN)

    (total_loss, per_example_loss, logits, probabilities) = create_model(
        bert_config, is_training, input_ids, input_mask, segment_ids, label_ids,
        num_labels, use_one_hot_embeddings)

    tvars = tf.trainable_variables()
    initialized_variable_names = {}
    scaffold_fn = None
    if init_checkpoint:
      (assignment_map, initialized_variable_names
      ) = modeling.get_assignment_map_from_checkpoint(tvars, init_checkpoint)
      if use_tpu:

        def tpu_scaffold():
          tf.train.init_from_checkpoint(init_checkpoint, assignment_map)
          return tf.train.Scaffold()

        scaffold_fn = tpu_scaffold
      else:
        tf.train.init_from_checkpoint(init_checkpoint, assignment_map)

    tf.logging.info("**** Trainable Variables ****")
    for var in tvars:
      init_string = ""
      if var.name in initialized_variable_names:
        init_string = ", *INIT_FROM_CKPT*"
      tf.logging.info("  name = %s, shape = %s%s", var.name, var.shape,
                      init_string)

    output_spec = None
    if mode == tf.estimator.ModeKeys.TRAIN:

      train_op = optimization.create_optimizer(
          total_loss, learning_rate, num_train_steps, num_warmup_steps, use_tpu)

      output_spec = tf.contrib.tpu.TPUEstimatorSpec(
          mode=mode,
          loss=total_loss,
          train_op=train_op,
          scaffold_fn=scaffold_fn)
    elif mode == tf.estimator.ModeKeys.EVAL:

      def metric_fn(per_example_loss, label_ids, logits, is_real_example):
        predictions = tf.argmax(logits, axis=-1, output_type=tf.int32)
        accuracy = tf.metrics.accuracy(
            labels=label_ids, predictions=predictions, weights=is_real_example)
        loss = tf.metrics.mean(values=per_example_loss, weights=is_real_example)
        return {
            "eval_accuracy": accuracy,
            "eval_loss": loss,
        }

      eval_metrics = (metric_fn,
                      [per_example_loss, label_ids, logits, is_real_example])
      output_spec = tf.contrib.tpu.TPUEstimatorSpec(
          mode=mode,
          loss=total_loss,
          eval_metrics=eval_metrics,
          scaffold_fn=scaffold_fn)
    else:
      output_spec = tf.contrib.tpu.TPUEstimatorSpec(
          mode=mode,
          predictions={"probabilities": probabilities},
          scaffold_fn=scaffold_fn)
    return output_spec

  return model_fn

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()


# This function is not used by this file but is still used by the Colab and
# people who depend on it.
def input_fn_builder(features, seq_length, is_training, drop_remainder):
  """Creates an `input_fn` closure to be passed to TPUEstimator."""

  all_input_ids = []
  all_input_mask = []
  all_segment_ids = []
  all_label_ids = []

  for feature in features:
    all_input_ids.append(feature.input_ids)
    all_input_mask.append(feature.input_mask)
    all_segment_ids.append(feature.segment_ids)
    all_label_ids.append(feature.label_id)

  def input_fn(params):
    """The actual input function."""
    batch_size = params["batch_size"]

    num_examples = len(features)

    # This is for demo purposes and does NOT scale to large data sets. We do
    # not use Dataset.from_generator() because that uses tf.py_func which is
    # not TPU compatible. The right way to load data is with TFRecordReader.
    d = tf.data.Dataset.from_tensor_slices({
        "input_ids":
            tf.constant(
                all_input_ids, shape=[num_examples, seq_length],
                dtype=tf.int32),
        "input_mask":
            tf.constant(
                all_input_mask,
                shape=[num_examples, seq_length],
                dtype=tf.int32),
        "segment_ids":
            tf.constant(
                all_segment_ids,
                shape=[num_examples, seq_length],
                dtype=tf.int32),
        "label_ids":
            tf.constant(all_label_ids, shape=[num_examples], dtype=tf.int32),
    })

    if is_training:
      d = d.repeat()
      d = d.shuffle(buffer_size=100)

    d = d.batch(batch_size=batch_size, drop_remainder=drop_remainder)
    return d

  return input_fn


@app.route('/predict', methods=['GET', 'POST'])
def predict():

  processors = {"supe": SupervisorProcessor,}

  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file)

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  tf.gfile.MakeDirs(FLAGS.output_dir)

  task_name = FLAGS.task_name.lower()

  processor = processors[task_name]()

  label_list = processor.get_labels()

  tokenizer = tokenization.FullTokenizer(
      vocab_file=FLAGS.vocab_file, do_lower_case=FLAGS.do_lower_case)

  tpu_cluster_resolver = None
  if FLAGS.use_tpu and FLAGS.tpu_name:
    tpu_cluster_resolver = tf.contrib.cluster_resolver.TPUClusterResolver(
        FLAGS.tpu_name, zone=FLAGS.tpu_zone, project=FLAGS.gcp_project)

  is_per_host = tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2
  run_config = tf.contrib.tpu.RunConfig(
      cluster=tpu_cluster_resolver,
      master=FLAGS.master,
      model_dir=FLAGS.output_dir,
      save_checkpoints_steps=FLAGS.save_checkpoints_steps,
      tpu_config=tf.contrib.tpu.TPUConfig(
          iterations_per_loop=FLAGS.iterations_per_loop,
          num_shards=FLAGS.num_tpu_cores,
          per_host_input_for_training=is_per_host))

  train_examples = None
  num_train_steps = None
  num_warmup_steps = None

  model_fn = model_fn_builder(
      bert_config=bert_config,
      num_labels=len(label_list),
      init_checkpoint=FLAGS.init_checkpoint,
      learning_rate=FLAGS.learning_rate,
      num_train_steps=num_train_steps,
      num_warmup_steps=num_warmup_steps,
      use_tpu=FLAGS.use_tpu,
      use_one_hot_embeddings=FLAGS.use_tpu)

  # If TPU is not available, this will fall back to normal Estimator on CPU
  # or GPU.
  estimator = tf.contrib.tpu.TPUEstimator(
      use_tpu=FLAGS.use_tpu,
      model_fn=model_fn,
      config=run_config,
      train_batch_size=FLAGS.train_batch_size,
      eval_batch_size=FLAGS.eval_batch_size,
      predict_batch_size=FLAGS.predict_batch_size)

  if request.method == 'POST':
    sent_pairs = ['I am Erik Chan 我是Erik Chan']
    examples = []
    examples.append(InputExample(guid='1', text_a='I am Erik Chan', text_b='我是Erik Chan', label='great-aligned'))
    features = convert_examples_to_features(examples, label_list, FLAGS.max_seq_length, tokenizer)        

    predict_drop_remainder = True if FLAGS.use_tpu else False
    predict_input_fn = input_fn_builder(
        features=features,
        seq_length=FLAGS.max_seq_length,
        is_training=False,
        drop_remainder=predict_drop_remainder)

    result = estimator.predict(input_fn=predict_input_fn)
    
    probabilities = []
    for (i, prediction) in enumerate(result):
      probabilities.append(prediction["probabilities"].tolist())
    return jsonify(probabilities)

  if request.method == 'GET':
    return 'Server Works!'


if __name__ == '__main__':
  app.run(debug=True)