def __str__(self): s = "" s += "tokens: %s\n" % (" ".join( [tokenization.printable_text(x) for x in self.tokens])) s += "segment_ids: %s\n" % (" ".join( [str(x) for x in self.segment_ids])) s += "is_random_next: %s\n" % self.is_random_next s += "masked_lm_positions: %s\n" % (" ".join( [str(x) for x in self.masked_lm_positions])) s += "masked_lm_labels: %s\n" % (" ".join( [tokenization.printable_text(x) for x in self.masked_lm_labels])) s += "\n" return s
def write_instance_to_example_files(instances, tokenizer, max_seq_length, max_predictions_per_seq, output_files): """Create TF example files from `TrainingInstance`s.""" writers = [] for output_file in output_files: writers.append(tf.python_io.TFRecordWriter(output_file)) writer_index = 0 total_written = 0 for (inst_index, instance) in enumerate(instances): input_ids = tokenizer.convert_tokens_to_ids(instance.tokens) input_mask = [1] * len(input_ids) segment_ids = list(instance.segment_ids) assert len(input_ids) <= max_seq_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 masked_lm_positions = list(instance.masked_lm_positions) masked_lm_ids = tokenizer.convert_tokens_to_ids( instance.masked_lm_labels) masked_lm_weights = [1.0] * len(masked_lm_ids) while len(masked_lm_positions) < max_predictions_per_seq: masked_lm_positions.append(0) masked_lm_ids.append(0) masked_lm_weights.append(0.0) next_sentence_label = 1 if instance.is_random_next else 0 features = collections.OrderedDict() features["input_ids"] = create_int_feature(input_ids) features["input_mask"] = create_int_feature(input_mask) features["segment_ids"] = create_int_feature(segment_ids) features["masked_lm_positions"] = create_int_feature( masked_lm_positions) features["masked_lm_ids"] = create_int_feature(masked_lm_ids) features["masked_lm_weights"] = create_float_feature(masked_lm_weights) features["next_sentence_labels"] = create_int_feature( [next_sentence_label]) tf_example = tf.train.Example(features=tf.train.Features( feature=features)) writers[writer_index].write(tf_example.SerializeToString()) writer_index = (writer_index + 1) % len(writers) total_written += 1 if inst_index < 20: tf.logging.info("*** Example ***") tf.logging.info("tokens: %s" % " ".join( [tokenization.printable_text(x) for x in instance.tokens])) for feature_name in features.keys(): feature = features[feature_name] values = [] if feature.int64_list.value: values = feature.int64_list.value elif feature.float_list.value: values = feature.float_list.value tf.logging.info( "%s: %s" % (feature_name, " ".join([str(x) for x in values]))) for writer in writers: writer.close() tf.logging.info("Wrote %d total instances", total_written)
def convert_examples_to_features(examples, seq_length, tokenizer): """Loads a data file into a list of `InputBatch`s.""" features = [] for (ex_index, example) in enumerate(examples): 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, seq_length - 3) else: # Account for [CLS] and [SEP] with "- 2" if len(tokens_a) > seq_length - 2: tokens_a = tokens_a[0:(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 as the "sentence vector". Note that this only makes sense because # the entire model is fine-tuned. tokens = [] input_type_ids = [] tokens.append("[CLS]") input_type_ids.append(0) for token in tokens_a: tokens.append(token) input_type_ids.append(0) tokens.append("[SEP]") input_type_ids.append(0) if tokens_b: for token in tokens_b: tokens.append(token) input_type_ids.append(1) tokens.append("[SEP]") input_type_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) < seq_length: input_ids.append(0) input_mask.append(0) input_type_ids.append(0) assert len(input_ids) == seq_length assert len(input_mask) == seq_length assert len(input_type_ids) == seq_length if ex_index < 5: tf.logging.info("*** Example ***") tf.logging.info("unique_id: %s" % (example.unique_id)) 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("input_type_ids: %s" % " ".join([str(x) for x in input_type_ids])) features.append( InputFeatures(unique_id=example.unique_id, tokens=tokens, input_ids=input_ids, input_mask=input_mask, input_type_ids=input_type_ids)) return features