SYMBOL INDEX (133 symbols across 7 files) FILE: create_pretraining_data.py class TrainingInstance (line 70) | class TrainingInstance(object): method __init__ (line 73) | def __init__(self, tokens, segment_ids, masked_lm_positions, masked_lm... method __str__ (line 81) | def __str__(self): method __repr__ (line 94) | def __repr__(self): function write_instance_to_example_files (line 98) | def write_instance_to_example_files(instances, tokenizer, max_seq_length, function create_int_feature (line 172) | def create_int_feature(values): function create_float_feature (line 177) | def create_float_feature(values): function create_training_instances (line 182) | def create_training_instances(input_files, tokenizer, max_seq_length, function _is_chinese_char (line 229) | def _is_chinese_char(cp): function get_new_segment (line 250) | def get_new_segment(segment): # 新增的方法 #### function get_raw_instance (line 282) | def get_raw_instance(document,max_sequence_length): # 新增的方法 function create_instances_from_document (line 319) | def create_instances_from_document( # 新增的方法 function create_instances_from_document_original (line 376) | def create_instances_from_document_original( function create_masked_lm_predictions (line 501) | def create_masked_lm_predictions(tokens, masked_lm_prob, function truncate_seq_pair (line 579) | def truncate_seq_pair(tokens_a, tokens_b, max_num_tokens, rng): function main (line 597) | def main(_): FILE: modeling.py class BertConfig (line 31) | class BertConfig(object): method __init__ (line 34) | def __init__(self, method from_dict (line 83) | def from_dict(cls, json_object): method from_json_file (line 91) | def from_json_file(cls, json_file): method to_dict (line 97) | def to_dict(self): method to_json_string (line 102) | def to_json_string(self): class BertModel (line 107) | class BertModel(object): method __init__ (line 131) | def __init__(self, method get_pooled_output (line 234) | def get_pooled_output(self): method get_sequence_output (line 237) | def get_sequence_output(self): method get_all_encoder_layers (line 246) | def get_all_encoder_layers(self): method get_embedding_output (line 249) | def get_embedding_output(self): method get_embedding_table (line 260) | def get_embedding_table(self): function gelu (line 264) | def gelu(x): function get_activation (line 280) | def get_activation(activation_string): function get_assignment_map_from_checkpoint (line 317) | def get_assignment_map_from_checkpoint(tvars, init_checkpoint): function dropout (line 344) | def dropout(input_tensor, dropout_prob): function layer_norm (line 362) | def layer_norm(input_tensor, name=None): function layer_norm_and_dropout (line 368) | def layer_norm_and_dropout(input_tensor, dropout_prob, name=None): function create_initializer (line 375) | def create_initializer(initializer_range=0.02): function embedding_lookup (line 380) | def embedding_lookup(input_ids, function embedding_postprocessor (line 428) | def embedding_postprocessor(input_tensor, function create_attention_mask_from_input_mask (line 524) | def create_attention_mask_from_input_mask(from_tensor, to_mask): function attention_layer (line 558) | def attention_layer(from_tensor, function transformer_model (line 754) | def transformer_model(input_tensor, function get_shape_list (line 895) | def get_shape_list(tensor, expected_rank=None, name=None): function reshape_to_matrix (line 932) | def reshape_to_matrix(input_tensor): function reshape_from_matrix (line 946) | def reshape_from_matrix(output_tensor, orig_shape_list): function assert_rank (line 959) | def assert_rank(tensor, expected_rank, name=None): FILE: optimization.py function create_optimizer (line 25) | def create_optimizer(loss, init_lr, num_train_steps, num_warmup_steps, u... function find_train_variables (line 89) | def find_train_variables(tvars): class AdamWeightDecayOptimizer (line 116) | class AdamWeightDecayOptimizer(tf.train.Optimizer): method __init__ (line 119) | def __init__(self, method apply_gradients (line 137) | def apply_gradients(self, grads_and_vars, global_step=None, name=None): method _do_use_weight_decay (line 188) | def _do_use_weight_decay(self, param_name): method _get_variable_name (line 198) | def _get_variable_name(self, param_name): FILE: optimization_finetuning.py function create_optimizer (line 25) | def create_optimizer(loss, init_lr, num_train_steps, num_warmup_steps, u... class AdamWeightDecayOptimizer (line 87) | class AdamWeightDecayOptimizer(tf.train.Optimizer): method __init__ (line 90) | def __init__(self, method apply_gradients (line 108) | def apply_gradients(self, grads_and_vars, global_step=None, name=None): method _do_use_weight_decay (line 159) | def _do_use_weight_decay(self, param_name): method _get_variable_name (line 169) | def _get_variable_name(self, param_name): FILE: run_classifier.py class InputExample (line 128) | class InputExample(object): method __init__ (line 131) | def __init__(self, guid, text_a, text_b=None, label=None): class PaddingInputExample (line 148) | class PaddingInputExample(object): class InputFeatures (line 159) | class InputFeatures(object): method __init__ (line 162) | def __init__(self, class DataProcessor (line 175) | class DataProcessor(object): method get_train_examples (line 178) | def get_train_examples(self, data_dir): method get_dev_examples (line 182) | def get_dev_examples(self, data_dir): method get_test_examples (line 186) | def get_test_examples(self, data_dir): method get_labels (line 190) | def get_labels(self): method _read_tsv (line 195) | def _read_tsv(cls, input_file, quotechar=None): class LCQMCPairClassificationProcessor (line 205) | class LCQMCPairClassificationProcessor(DataProcessor): # TODO NEED CHANGE2 method __init__ (line 207) | def __init__(self): method get_train_examples (line 210) | def get_train_examples(self, data_dir): method get_dev_examples (line 216) | def get_dev_examples(self, data_dir): method get_test_examples (line 221) | def get_test_examples(self, data_dir): method get_labels (line 226) | def get_labels(self): method _create_examples (line 230) | def _create_examples(self, lines, set_type): method __init__ (line 647) | def __init__(self): method get_train_examples (line 650) | def get_train_examples(self, data_dir): method get_dev_examples (line 656) | def get_dev_examples(self, data_dir): method get_test_examples (line 661) | def get_test_examples(self, data_dir): method get_labels (line 666) | def get_labels(self): method _create_examples (line 671) | def _create_examples(self, lines, set_type): function convert_single_example (line 250) | def convert_single_example(ex_index, example, label_list, max_seq_length, function file_based_convert_examples_to_features (line 352) | def file_based_convert_examples_to_features( function file_based_input_fn_builder (line 382) | def file_based_input_fn_builder(input_file, seq_length, is_training, function _truncate_seq_pair (line 430) | def _truncate_seq_pair(tokens_a, tokens_b, max_length): function create_model (line 447) | def create_model(bert_config, is_training, input_ids, input_mask, segmen... function model_fn_builder (line 500) | def model_fn_builder(bert_config, num_labels, init_checkpoint, learning_... function input_fn_builder (line 594) | def input_fn_builder(features, seq_length, is_training, drop_remainder): class LCQMCPairClassificationProcessor (line 645) | class LCQMCPairClassificationProcessor(DataProcessor): # TODO NEED CHANGE2 method __init__ (line 207) | def __init__(self): method get_train_examples (line 210) | def get_train_examples(self, data_dir): method get_dev_examples (line 216) | def get_dev_examples(self, data_dir): method get_test_examples (line 221) | def get_test_examples(self, data_dir): method get_labels (line 226) | def get_labels(self): method _create_examples (line 230) | def _create_examples(self, lines, set_type): method __init__ (line 647) | def __init__(self): method get_train_examples (line 650) | def get_train_examples(self, data_dir): method get_dev_examples (line 656) | def get_dev_examples(self, data_dir): method get_test_examples (line 661) | def get_test_examples(self, data_dir): method get_labels (line 666) | def get_labels(self): method _create_examples (line 671) | def _create_examples(self, lines, set_type): class SentencePairClassificationProcessor (line 690) | class SentencePairClassificationProcessor(DataProcessor): method __init__ (line 692) | def __init__(self): method get_train_examples (line 695) | def get_train_examples(self, data_dir): method get_dev_examples (line 701) | def get_dev_examples(self, data_dir): method get_test_examples (line 706) | def get_test_examples(self, data_dir): method get_labels (line 711) | def get_labels(self): method _create_examples (line 716) | def _create_examples(self, lines, set_type): function convert_examples_to_features (line 737) | def convert_examples_to_features(examples, label_list, max_seq_length, function main (line 753) | def main(_): FILE: run_pretraining.py function model_fn_builder (line 109) | def model_fn_builder(bert_config, init_checkpoint, learning_rate, function get_masked_lm_output (line 243) | def get_masked_lm_output(bert_config, input_tensor, output_weights, posi... function get_next_sentence_output (line 287) | def get_next_sentence_output(bert_config, input_tensor, labels): function gather_indexes (line 310) | def gather_indexes(sequence_tensor, positions): function input_fn_builder (line 326) | def input_fn_builder(input_files, function _decode_record (line 393) | def _decode_record(record, name_to_features): function main (line 408) | def main(_): FILE: tokenization.py function validate_case_matches_checkpoint (line 28) | def validate_case_matches_checkpoint(do_lower_case, init_checkpoint): function convert_to_unicode (line 78) | def convert_to_unicode(text): function printable_text (line 98) | def printable_text(text): function load_vocab (line 121) | def load_vocab(vocab_file): function convert_by_vocab (line 136) | def convert_by_vocab(vocab, items): function convert_tokens_to_ids (line 146) | def convert_tokens_to_ids(vocab, tokens): function convert_ids_to_tokens (line 150) | def convert_ids_to_tokens(inv_vocab, ids): function whitespace_tokenize (line 154) | def whitespace_tokenize(text): class FullTokenizer (line 163) | class FullTokenizer(object): method __init__ (line 166) | def __init__(self, vocab_file, do_lower_case=True): method tokenize (line 172) | def tokenize(self, text): method convert_tokens_to_ids (line 180) | def convert_tokens_to_ids(self, tokens): method convert_ids_to_tokens (line 183) | def convert_ids_to_tokens(self, ids): class BasicTokenizer (line 187) | class BasicTokenizer(object): method __init__ (line 190) | def __init__(self, do_lower_case=True): method tokenize (line 198) | def tokenize(self, text): method _run_strip_accents (line 222) | def _run_strip_accents(self, text): method _run_split_on_punc (line 233) | def _run_split_on_punc(self, text): method _tokenize_chinese_chars (line 253) | def _tokenize_chinese_chars(self, text): method _is_chinese_char (line 266) | def _is_chinese_char(self, cp): method _clean_text (line 288) | def _clean_text(self, text): class WordpieceTokenizer (line 302) | class WordpieceTokenizer(object): method __init__ (line 305) | def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=... method tokenize (line 310) | def tokenize(self, text): function _is_whitespace (line 364) | def _is_whitespace(char): function _is_control (line 376) | def _is_control(char): function _is_punctuation (line 388) | def _is_punctuation(char):