SYMBOL INDEX (747 symbols across 86 files)

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/evaluate.py
  function get_tokenizer (line 15) | def get_tokenizer(dataset_config, split_fn=split_morphs):
  function main (line 22) | def main(args):

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/model/data.py
  class Corpus (line 8) | class Corpus(Dataset):
    method __init__ (line 10) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 19) | def __len__(self) -> int:
    method __getitem__ (line 22) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:
  function batchify (line 28) | def batchify(data: List[Tuple[torch.tensor, torch.tensor, torch.tensor]]...

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 26) | def acc(yhat, y):

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/model/net.py
  class SAN (line 9) | class SAN(nn.Module):
    method __init__ (line 11) | def __init__(self, num_classes: int, lstm_hidden_dim: int, da: int, r:...
    method forward (line 31) | def forward(self, x: torch.Tensor) -> Tuple[torch.tensor, torch.tensor]:

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/model/ops.py
  class Embedding (line 9) | class Embedding(nn.Module):
    method __init__ (line 11) | def __init__(self, vocab: Vocab, padding_idx: int = 1, freeze: bool = ...
    method forward (line 29) | def forward(self, x: torch.Tensor) -> Union[torch.Tensor, Tuple[torch....
  class Linker (line 39) | class Linker(nn.Module):
    method __init__ (line 41) | def __init__(self, permuting: bool = True):
    method forward (line 50) | def forward(self, x: Tuple[torch.Tensor, torch.Tensor]) -> PackedSeque...
  class BiLSTM (line 56) | class BiLSTM(nn.Module):
    method __init__ (line 58) | def __init__(self, input_size: int, hidden_size: int, using_sequence: ...
    method forward (line 70) | def forward(self, x: PackedSequence) -> torch.Tensor:
  class SelfAttention (line 81) | class SelfAttention(nn.Module):
    method __init__ (line 83) | def __init__(self, input_dim: int, da: int, r: int) -> None:
    method forward (line 95) | def forward(self, h: torch.Tensor) -> torch.Tensor:

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 167) | class Tokenizer:
    method __init__ (line 169) | def __init__(self, vocab: Vocab, split_fn: Callable[[str], List[str]],
    method split (line 181) | def split(self, string: str) -> List[str]:
    method transform (line 185) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 190) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 194) | def vocab(self):
  class PadSequence (line 198) | class PadSequence:
    method __init__ (line 200) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 211) | def __call__(self, sample):

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/train.py
  function get_tokenizer (line 19) | def get_tokenizer(dataset_config, split_fn=split_morphs):
  function get_data_loaders (line 26) | def get_data_loaders(dataset_config, tokenizer, batch_size, collate_fn):
  function regularize (line 35) | def regularize(attn_mat, r, device):
  function main (line 42) | def main(args):

FILE: A_Structured_Self-attentive_Sentence_Embedding_cls/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 22) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 30) | def update(self, json_path_or_dict) -> None:
    method dict (line 43) | def dict(self) -> dict:
  class CheckpointManager (line 47) | class CheckpointManager:
    method __init__ (line 50) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 63) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 71) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 84) | class SummaryManager:
    method __init__ (line 87) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 96) | def save(self, filename: str) -> None:
    method load (line 104) | def load(self, filename) -> None:
    method update (line 113) | def update(self, summary: dict) -> None:
    method reset (line 120) | def reset(self) -> None:
    method summary (line 125) | def summary(self):

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/evaluate.py
  function get_tokenizer (line 15) | def get_tokenizer(dataset_config, split_fn=split_morphs):
  function main (line 22) | def main(args):

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/model/data.py
  class Corpus (line 8) | class Corpus(Dataset):
    method __init__ (line 11) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 20) | def __len__(self) -> int:
    method __getitem__ (line 23) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:
  function batchify (line 31) | def batchify(

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 28) | def acc(yhat, y):

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/model/net.py
  class SAN (line 9) | class SAN(nn.Module):
    method __init__ (line 12) | def __init__(self, num_classes: int, lstm_hidden_dim: int, hidden_dim:...
    method forward (line 29) | def forward(self, x: Tuple[Tuple[torch.Tensor, torch.Tensor], Tuple[to...

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/model/ops.py
  class Embedding (line 9) | class Embedding(nn.Module):
    method __init__ (line 12) | def __init__(
    method forward (line 38) | def forward(
  class Linker (line 50) | class Linker(nn.Module):
    method __init__ (line 53) | def __init__(self, permuting: bool = True) -> None:
    method forward (line 62) | def forward(
  class BiLSTM (line 72) | class BiLSTM(nn.Module):
    method __init__ (line 75) | def __init__(
    method forward (line 91) | def forward(self, x: PackedSequence) -> torch.Tensor:
  class SelfAttention (line 102) | class SelfAttention(nn.Module):
    method __init__ (line 105) | def __init__(self, input_dim: int, da: int, r: int) -> None:
    method forward (line 117) | def forward(self, h: torch.Tensor) -> torch.Tensor:
  class SentenceEncoder (line 123) | class SentenceEncoder(nn.Module):
    method __init__ (line 126) | def __init__(self, lstm_hidden_dim: int, da: int, r: int, vocab: Vocab...
    method forward (line 149) | def forward(

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 171) | def __init__(
    method split (line 187) | def split(self, string: str) -> List[str]:
    method transform (line 191) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 196) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 200) | def vocab(self):
  class PadSequence (line 204) | class PadSequence:
    method __init__ (line 207) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 218) | def __call__(self, sample):

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/train.py
  function get_tokenizer (line 18) | def get_tokenizer(dataset_config, split_fn=split_morphs):
  function get_data_loaders (line 25) | def get_data_loaders(dataset_config, tokenizer, batch_size, collate_fn):
  function regularize (line 34) | def regularize(attn_mat, r, device):
  function main (line 41) | def main(args):

FILE: A_Structured_Self-attentive_Sentence_Embedding_ptc/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 22) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 30) | def update(self, json_path_or_dict) -> None:
    method dict (line 43) | def dict(self) -> dict:
  class CheckpointManager (line 47) | class CheckpointManager:
    method __init__ (line 50) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 63) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 71) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 84) | class SummaryManager:
    method __init__ (line 87) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 96) | def save(self, filename: str) -> None:
    method load (line 104) | def load(self, filename) -> None:
    method update (line 113) | def update(self, summary: dict) -> None:
    method reset (line 120) | def reset(self) -> None:
    method summary (line 125) | def summary(self):

FILE: BERT_pairwise_text_classification/evaluate.py
  function get_preprocessor (line 18) | def get_preprocessor(ptr_config_info, model_config):
  function main (line 33) | def main(args):

FILE: BERT_pairwise_text_classification/model/data.py
  class Corpus (line 7) | class Corpus(Dataset):
    method __init__ (line 9) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 19) | def __len__(self) -> int:
    method __getitem__ (line 22) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:

FILE: BERT_pairwise_text_classification/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 26) | def acc(yhat, y):

FILE: BERT_pairwise_text_classification/model/net.py
  class PairwiseClassifier (line 6) | class PairwiseClassifier(BertPreTrainedModel):
    method __init__ (line 7) | def __init__(self, config, num_classes, vocab) -> None:
    method forward (line 15) | def forward(self, input_ids, token_type_ids) -> torch.Tensor:

FILE: BERT_pairwise_text_classification/model/tokenization.py
  function load_vocab (line 59) | def load_vocab(vocab_file):
  function whitespace_tokenize (line 80) | def whitespace_tokenize(text):
  class BertTokenizer (line 89) | class BertTokenizer(object):
    method __init__ (line 92) | def __init__(self, vocab_file, do_lower_case=True, max_len=None,
    method tokenize (line 106) | def tokenize(self, text):
    method convert_tokens_to_ids (line 115) | def convert_tokens_to_ids(self, tokens):
    method convert_ids_to_tokens (line 128) | def convert_ids_to_tokens(self, ids):
    method from_pretrained (line 136) | def from_pretrained(cls, pretrained_model_name, cache_dir=None, *input...
  class BasicTokenizer (line 174) | class BasicTokenizer(object):
    method __init__ (line 177) | def __init__(self,
    method tokenize (line 188) | def tokenize(self, text):
    method _run_strip_accents (line 210) | def _run_strip_accents(self, text):
    method _run_split_on_punc (line 221) | def _run_split_on_punc(self, text):
    method _tokenize_chinese_chars (line 243) | def _tokenize_chinese_chars(self, text):
    method _is_chinese_char (line 256) | def _is_chinese_char(self, cp):
    method _clean_text (line 278) | def _clean_text(self, text):
  class WordpieceTokenizer (line 292) | class WordpieceTokenizer(object):
    method __init__ (line 295) | def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=...
    method tokenize (line 300) | def tokenize(self, text):
  function _is_whitespace (line 354) | def _is_whitespace(char):
  function _is_control (line 366) | def _is_control(char):
  function _is_punctuation (line 378) | def _is_punctuation(char):

FILE: BERT_pairwise_text_classification/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 170) | def __init__(self, vocab: Vocab, split_fn: Callable[[str], List[str]],
    method split (line 183) | def split(self, string: str) -> List[str]:
    method transform (line 187) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 192) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 196) | def vocab(self):
  class PadSequence (line 200) | class PadSequence:
    method __init__ (line 202) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 214) | def __call__(self, sample):
  class PreProcessor (line 225) | class PreProcessor(Tokenizer):
    method preprocess (line 226) | def preprocess(self, q1, q2):

FILE: BERT_pairwise_text_classification/pretrained/etri/tokenization.py
  function load_vocab (line 59) | def load_vocab(vocab_file):
  function whitespace_tokenize (line 80) | def whitespace_tokenize(text):
  class BertTokenizer (line 89) | class BertTokenizer(object):
    method __init__ (line 92) | def __init__(self, vocab_file, do_lower_case=True, max_len=None,
    method tokenize (line 106) | def tokenize(self, text):
    method convert_tokens_to_ids (line 115) | def convert_tokens_to_ids(self, tokens):
    method convert_ids_to_tokens (line 128) | def convert_ids_to_tokens(self, ids):
    method from_pretrained (line 136) | def from_pretrained(cls, pretrained_model_name, cache_dir=None, *input...
  class BasicTokenizer (line 174) | class BasicTokenizer(object):
    method __init__ (line 177) | def __init__(self,
    method tokenize (line 188) | def tokenize(self, text):
    method _run_strip_accents (line 210) | def _run_strip_accents(self, text):
    method _run_split_on_punc (line 221) | def _run_split_on_punc(self, text):
    method _tokenize_chinese_chars (line 243) | def _tokenize_chinese_chars(self, text):
    method _is_chinese_char (line 256) | def _is_chinese_char(self, cp):
    method _clean_text (line 278) | def _clean_text(self, text):
  class WordpieceTokenizer (line 292) | class WordpieceTokenizer(object):
    method __init__ (line 295) | def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=...
    method tokenize (line 300) | def tokenize(self, text):
  function _is_whitespace (line 354) | def _is_whitespace(char):
  function _is_control (line 366) | def _is_control(char):
  function _is_punctuation (line 378) | def _is_punctuation(char):

FILE: BERT_pairwise_text_classification/train.py
  function get_preprocessor (line 21) | def get_preprocessor(ptr_config_info, model_config):
  function get_data_loaders (line 36) | def get_data_loaders(dataset_config, preprocessor, batch_size):
  function main (line 44) | def main(args):

FILE: BERT_pairwise_text_classification/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 22) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 30) | def update(self, json_path_or_dict) -> None:
    method dict (line 43) | def dict(self) -> dict:
  class CheckpointManager (line 47) | class CheckpointManager:
    method __init__ (line 50) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 63) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 71) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 86) | class SummaryManager:
    method __init__ (line 89) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 98) | def save(self, filename: str) -> None:
    method load (line 106) | def load(self, filename) -> None:
    method update (line 115) | def update(self, summary: dict) -> None:
    method reset (line 122) | def reset(self) -> None:
    method summary (line 127) | def summary(self):

FILE: BERT_single_sentence_classification/evaluate.py
  function get_preprocessor (line 18) | def get_preprocessor(ptr_config_info, model_config):
  function main (line 33) | def main(args):

FILE: BERT_single_sentence_classification/model/data.py
  class Corpus (line 7) | class Corpus(Dataset):
    method __init__ (line 9) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 19) | def __len__(self) -> int:
    method __getitem__ (line 22) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:

FILE: BERT_single_sentence_classification/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 26) | def acc(yhat, y):

FILE: BERT_single_sentence_classification/model/net.py
  class SentenceClassifier (line 5) | class SentenceClassifier(BertPreTrainedModel):
    method __init__ (line 6) | def __init__(self, config, num_classes, vocab) -> None:
    method forward (line 14) | def forward(self, input_ids):

FILE: BERT_single_sentence_classification/model/tokenization.py
  function load_vocab (line 59) | def load_vocab(vocab_file):
  function whitespace_tokenize (line 80) | def whitespace_tokenize(text):
  class BertTokenizer (line 89) | class BertTokenizer(object):
    method __init__ (line 92) | def __init__(self, vocab_file, do_lower_case=True, max_len=None,
    method tokenize (line 106) | def tokenize(self, text):
    method convert_tokens_to_ids (line 115) | def convert_tokens_to_ids(self, tokens):
    method convert_ids_to_tokens (line 128) | def convert_ids_to_tokens(self, ids):
    method from_pretrained (line 136) | def from_pretrained(cls, pretrained_model_name, cache_dir=None, *input...
  class BasicTokenizer (line 174) | class BasicTokenizer(object):
    method __init__ (line 177) | def __init__(self,
    method tokenize (line 188) | def tokenize(self, text):
    method _run_strip_accents (line 210) | def _run_strip_accents(self, text):
    method _run_split_on_punc (line 221) | def _run_split_on_punc(self, text):
    method _tokenize_chinese_chars (line 243) | def _tokenize_chinese_chars(self, text):
    method _is_chinese_char (line 256) | def _is_chinese_char(self, cp):
    method _clean_text (line 278) | def _clean_text(self, text):
  class WordpieceTokenizer (line 292) | class WordpieceTokenizer(object):
    method __init__ (line 295) | def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=...
    method tokenize (line 300) | def tokenize(self, text):
  function _is_whitespace (line 354) | def _is_whitespace(char):
  function _is_control (line 366) | def _is_control(char):
  function _is_punctuation (line 378) | def _is_punctuation(char):

FILE: BERT_single_sentence_classification/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 171) | def __init__(
    method split (line 188) | def split(self, string: str) -> List[str]:
    method transform (line 192) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 197) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 201) | def vocab(self):
  class PadSequence (line 205) | class PadSequence:
    method __init__ (line 208) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 219) | def __call__(self, sample):
  class PreProcessor (line 230) | class PreProcessor(Tokenizer):
    method preprocess (line 231) | def preprocess(self, string):

FILE: BERT_single_sentence_classification/pretrained/etri/tokenization.py
  function load_vocab (line 59) | def load_vocab(vocab_file):
  function whitespace_tokenize (line 80) | def whitespace_tokenize(text):
  class BertTokenizer (line 89) | class BertTokenizer(object):
    method __init__ (line 92) | def __init__(self, vocab_file, do_lower_case=True, max_len=None,
    method tokenize (line 106) | def tokenize(self, text):
    method convert_tokens_to_ids (line 115) | def convert_tokens_to_ids(self, tokens):
    method convert_ids_to_tokens (line 128) | def convert_ids_to_tokens(self, ids):
    method from_pretrained (line 136) | def from_pretrained(cls, pretrained_model_name, cache_dir=None, *input...
  class BasicTokenizer (line 174) | class BasicTokenizer(object):
    method __init__ (line 177) | def __init__(self,
    method tokenize (line 188) | def tokenize(self, text):
    method _run_strip_accents (line 210) | def _run_strip_accents(self, text):
    method _run_split_on_punc (line 221) | def _run_split_on_punc(self, text):
    method _tokenize_chinese_chars (line 243) | def _tokenize_chinese_chars(self, text):
    method _is_chinese_char (line 256) | def _is_chinese_char(self, cp):
    method _clean_text (line 278) | def _clean_text(self, text):
  class WordpieceTokenizer (line 292) | class WordpieceTokenizer(object):
    method __init__ (line 295) | def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=...
    method tokenize (line 300) | def tokenize(self, text):
  function _is_whitespace (line 354) | def _is_whitespace(char):
  function _is_control (line 366) | def _is_control(char):
  function _is_punctuation (line 378) | def _is_punctuation(char):

FILE: BERT_single_sentence_classification/train.py
  function get_preprocessor (line 21) | def get_preprocessor(ptr_config_info, model_config):
  function get_data_loaders (line 36) | def get_data_loaders(dataset_config, preprocessor, batch_size):
  function main (line 44) | def main(args):

FILE: BERT_single_sentence_classification/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 22) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 30) | def update(self, json_path_or_dict) -> None:
    method dict (line 43) | def dict(self) -> dict:
  class CheckpointManager (line 47) | class CheckpointManager:
    method __init__ (line 50) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 63) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 71) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 84) | class SummaryManager:
    method __init__ (line 87) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 96) | def save(self, filename: str) -> None:
    method load (line 104) | def load(self, filename) -> None:
    method update (line 113) | def update(self, summary: dict) -> None:
    method reset (line 120) | def reset(self) -> None:
    method summary (line 125) | def summary(self):

FILE: Character-level_Convolutional_Networks_for_Text_Classification/evaluate.py
  function get_tokenizer (line 15) | def get_tokenizer(dataset_config, model_config):
  function main (line 23) | def main(args):

FILE: Character-level_Convolutional_Networks_for_Text_Classification/model/data.py
  class Corpus (line 7) | class Corpus(Dataset):
    method __init__ (line 9) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 19) | def __len__(self) -> int:
    method __getitem__ (line 22) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:

FILE: Character-level_Convolutional_Networks_for_Text_Classification/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 26) | def acc(yhat, y):

FILE: Character-level_Convolutional_Networks_for_Text_Classification/model/net.py
  class CharCNN (line 7) | class CharCNN(nn.Module):
    method __init__ (line 9) | def __init__(self, num_classes: int, embedding_dim: int, vocab: Vocab)...
    method forward (line 46) | def forward(self, x: torch.Tensor) -> torch.Tensor:
    method _initailze (line 51) | def _initailze(self, layer):

FILE: Character-level_Convolutional_Networks_for_Text_Classification/model/ops.py
  class Flatten (line 5) | class Flatten(nn.Module):
    method forward (line 7) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class Permute (line 11) | class Permute(nn.Module):
    method forward (line 13) | def forward(self, x: torch.Tensor) -> torch.Tensor:

FILE: Character-level_Convolutional_Networks_for_Text_Classification/model/split.py
  function split_to_jamo (line 5) | def split_to_jamo(string: str) -> List[str]:

FILE: Character-level_Convolutional_Networks_for_Text_Classification/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 171) | def __init__(
    method split (line 187) | def split(self, string: str) -> List[str]:
    method transform (line 191) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 196) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 200) | def vocab(self):
  class PadSequence (line 204) | class PadSequence:
    method __init__ (line 207) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 218) | def __call__(self, sample):

FILE: Character-level_Convolutional_Networks_for_Text_Classification/train.py
  function get_tokenizer (line 19) | def get_tokenizer(dataset_config, model_config):
  function get_data_loaders (line 27) | def get_data_loaders(dataset_config, tokenizer, batch_size):
  function main (line 35) | def main(args):

FILE: Character-level_Convolutional_Networks_for_Text_Classification/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 23) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 32) | def update(self, json_path_or_dict) -> None:
    method dict (line 46) | def dict(self) -> dict:
  class CheckpointManager (line 50) | class CheckpointManager:
    method __init__ (line 53) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 67) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 76) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 91) | class SummaryManager:
    method __init__ (line 94) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 103) | def save(self, filename: str) -> None:
    method load (line 112) | def load(self, filename) -> None:
    method update (line 121) | def update(self, summary: dict) -> None:
    method reset (line 129) | def reset(self) -> None:
    method summary (line 134) | def summary(self):

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/evaluate.py
  function get_tokenizer (line 15) | def get_tokenizer(dataset_config, model_config):
  function main (line 25) | def main(args):

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/model/data.py
  class Corpus (line 7) | class Corpus(Dataset):
    method __init__ (line 10) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 20) | def __len__(self) -> int:
    method __getitem__ (line 23) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 28) | def acc(yhat, y):

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/model/net.py
  class SenCNN (line 7) | class SenCNN(nn.Module):
    method __init__ (line 10) | def __init__(self, num_classes: int, vocab: Vocab) -> None:
    method forward (line 24) | def forward(self, x: torch.Tensor) -> torch.Tensor:

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/model/ops.py
  class MultiChannelEmbedding (line 8) | class MultiChannelEmbedding(nn.Module):
    method __init__ (line 11) | def __init__(self, vocab: Vocab) -> None:
    method forward (line 29) | def forward(self, x: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
  class ConvolutionLayer (line 35) | class ConvolutionLayer(nn.Module):
    method __init__ (line 38) | def __init__(self, in_channels: int, out_channels: int) -> None:
    method forward (line 56) | def forward(
  class MaxOverTimePooling (line 70) | class MaxOverTimePooling(nn.Module):
    method forward (line 73) | def forward(

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 67) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 89) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 102) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 107) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 135) | def __len__(self):
    method token_to_idx (line 139) | def token_to_idx(self):
    method idx_to_token (line 143) | def idx_to_token(self):
    method padding_token (line 147) | def padding_token(self):
    method unknown_token (line 151) | def unknown_token(self):
    method bos_token (line 155) | def bos_token(self):
    method eos_token (line 159) | def eos_token(self):
    method embedding (line 163) | def embedding(self):
    method embedding (line 167) | def embedding(self, array):
  class Tokenizer (line 171) | class Tokenizer:
    method __init__ (line 174) | def __init__(
    method split (line 191) | def split(self, string: str) -> List[str]:
    method transform (line 195) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 200) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 204) | def vocab(self):
  class PadSequence (line 208) | class PadSequence:
    method __init__ (line 211) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 223) | def __call__(self, sample):

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/train.py
  function get_tokenizer (line 20) | def get_tokenizer(dataset_config, model_config):
  function get_data_loaders (line 30) | def get_data_loaders(dataset_config, tokenizer, batch_size):
  function main (line 40) | def main(args):

FILE: Convolutional_Neural_Networks_for_Sentence_Classification/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 23) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 32) | def update(self, json_path_or_dict) -> None:
    method dict (line 46) | def dict(self) -> dict:
  class CheckpointManager (line 50) | class CheckpointManager:
    method __init__ (line 53) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 67) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 76) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 93) | class SummaryManager:
    method __init__ (line 96) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 105) | def save(self, filename: str) -> None:
    method load (line 114) | def load(self, filename) -> None:
    method update (line 123) | def update(self, summary: dict) -> None:
    method reset (line 131) | def reset(self) -> None:
    method summary (line 136) | def summary(self):

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/evaluate.py
  function get_tokenizer (line 15) | def get_tokenizer(dataset_config):
  function main (line 22) | def main(args):

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/model/data.py
  class Corpus (line 8) | class Corpus(Dataset):
    method __init__ (line 10) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 26) | def __len__(self) -> int:
    method __getitem__ (line 29) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:
  function batchify (line 38) | def batchify(data: List[Tuple[torch.Tensor, torch.Tensor]]) -> Tuple[tor...

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 26) | def acc(yhat, y):

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/model/net.py
  class ConvRec (line 8) | class ConvRec(nn.Module):
    method __init__ (line 10) | def __init__(self, num_classes: int, embedding_dim: int, hidden_dim: i...
    method forward (line 32) | def forward(self, x: torch.Tensor) -> torch.Tensor:
    method _init_weights (line 36) | def _init_weights(self, layer) -> None:

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/model/ops.py
  class Embedding (line 8) | class Embedding(nn.Module):
    method __init__ (line 11) | def __init__(self, num_embeddings: int, embedding_dim: int, padding_id...
    method forward (line 28) | def forward(self, x: torch.Tensor) -> Union[torch.Tensor, Tuple[torch....
  class MaxPool1d (line 38) | class MaxPool1d(nn.Module):
    method __init__ (line 41) | def __init__(self, kernel_size: int, stride: int, tracking: bool = Tru...
    method forward (line 56) | def forward(self, x: Union[torch.Tensor, Tuple[torch.Tensor, torch.Ten...
  class Conv1d (line 68) | class Conv1d(nn.Module):
    method __init__ (line 71) | def __init__(self, in_channels: int, out_channels: int, kernel_size: i...
    method forward (line 92) | def forward(self, x: Union[torch.Tensor, Tuple[torch.Tensor, torch.Ten...
  class Linker (line 104) | class Linker(nn.Module):
    method __init__ (line 107) | def __init__(self, permuting: bool = True) -> None:
    method forward (line 116) | def forward(self, x: Tuple[torch.Tensor, torch.Tensor]) -> PackedSeque...
  class BiLSTM (line 122) | class BiLSTM(nn.Module):
    method __init__ (line 125) | def __init__(self, input_size: int, hidden_size: int, using_sequence: ...
    method forward (line 137) | def forward(self, x: PackedSequence) -> torch.Tensor:

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/model/split.py
  function split_to_jamo (line 5) | def split_to_jamo(string: str) -> List[str]:

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 170) | def __init__(self, vocab: Vocab, split_fn: Callable[[str], List[str]],
    method split (line 182) | def split(self, string: str) -> List[str]:
    method transform (line 186) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 191) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 195) | def vocab(self):
  class PadSequence (line 199) | class PadSequence:
    method __init__ (line 201) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 212) | def __call__(self, sample):

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/train.py
  function get_tokenizer (line 19) | def get_tokenizer(dataset_config):
  function get_data_loaders (line 26) | def get_data_loaders(dataset_config, model_config, tokenizer, batch_size...
  function main (line 37) | def main(args):

FILE: Efficient_Character-level_Document_Classification_by_Combining_Convolution_and_Recurrent_Layers/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 23) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 32) | def update(self, json_path_or_dict) -> None:
    method dict (line 46) | def dict(self) -> dict:
  class CheckpointManager (line 50) | class CheckpointManager:
    method __init__ (line 53) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 67) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 76) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 91) | class SummaryManager:
    method __init__ (line 94) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 103) | def save(self, filename: str) -> None:
    method load (line 112) | def load(self, filename) -> None:
    method update (line 121) | def update(self, summary: dict) -> None:
    method reset (line 129) | def reset(self) -> None:
    method summary (line 134) | def summary(self):

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/evaluate.py
  function get_tokenizer (line 15) | def get_tokenizer(dataset_config, split_fn):
  function main (line 22) | def main(args):

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/model/data.py
  class Corpus (line 8) | class Corpus(Dataset):
    method __init__ (line 11) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 21) | def __len__(self) -> int:
    method __getitem__ (line 24) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:
  function batchify (line 32) | def batchify(

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 28) | def acc(yhat, y):

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/model/net.py
  class MaLSTM (line 8) | class MaLSTM(nn.Module):
    method __init__ (line 11) | def __init__(self, num_classes: int, hidden_dim: int, vocab: Vocab) ->...
    method forward (line 29) | def forward(self, x: Tuple[torch.tensor, torch.tensor]) -> torch.Tensor:

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/model/ops.py
  class Embedding (line 8) | class Embedding(nn.Module):
    method __init__ (line 11) | def __init__(
    method forward (line 37) | def forward(
  class Linker (line 49) | class Linker(nn.Module):
    method __init__ (line 52) | def __init__(self, permuting: bool = True):
    method forward (line 61) | def forward(self, x: Tuple[torch.Tensor, torch.Tensor]) -> PackedSeque...
  class LSTMEncoder (line 69) | class LSTMEncoder(nn.Module):
    method __init__ (line 72) | def __init__(
    method forward (line 85) | def forward(self, x: PackedSequence) -> torch.Tensor:

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 171) | def __init__(
    method split (line 187) | def split(self, string: str) -> List[str]:
    method transform (line 191) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 196) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 200) | def vocab(self):
  class PadSequence (line 204) | class PadSequence:
    method __init__ (line 207) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 218) | def __call__(self, sample):

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/train.py
  function get_tokenizer (line 18) | def get_tokenizer(dataset_config, split_fn):
  function get_data_loaders (line 25) | def get_data_loaders(dataset_config, tokenizer, batch_size, collate_fn=b...
  function main (line 34) | def main(args):

FILE: Siamese_recurrent_architectures_for_learning_sentence_similarity/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 22) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 30) | def update(self, json_path_or_dict) -> None:
    method dict (line 43) | def dict(self) -> dict:
  class CheckpointManager (line 47) | class CheckpointManager:
    method __init__ (line 50) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 63) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 71) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 86) | class SummaryManager:
    method __init__ (line 89) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 98) | def save(self, filename: str) -> None:
    method load (line 106) | def load(self, filename) -> None:
    method update (line 115) | def update(self, summary: dict) -> None:
    method reset (line 122) | def reset(self) -> None:
    method summary (line 127) | def summary(self):

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/evaluate.py
  function get_preprocessor (line 14) | def get_preprocessor(dataset_config, coarse_split_fn, fine_split_fn):
  function main (line 26) | def main(args):

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/model/data.py
  class Corpus (line 8) | class Corpus(Dataset):
    method __init__ (line 11) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 21) | def __len__(self) -> int:
    method __getitem__ (line 24) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:
  function batchify (line 32) | def batchify(

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/model/metric.py
  function evaluate (line 6) | def evaluate(model, data_loader, metrics, device):
  function log_loss (line 30) | def log_loss(inputs, targets):
  function acc (line 36) | def acc(yhat, y):

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/model/net.py
  class SAN (line 10) | class SAN(nn.Module):
    method __init__ (line 11) | def __init__(self, num_classes, coarse_vocab, fine_vocab, fine_embeddi...
    method forward (line 28) | def forward(self, inputs: Tuple[torch.Tensor, torch.Tensor]) -> torch....
    method _one_step_predict (line 84) | def _one_step_predict(self, x: Tuple[torch.Tensor, torch.Tensor]) -> t...

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/model/ops.py
  class Embedding (line 9) | class Embedding(nn.Module):
    method __init__ (line 12) | def __init__(
    method forward (line 35) | def forward(
  class PreEmbedding (line 47) | class PreEmbedding(nn.Module):
    method __init__ (line 50) | def __init__(
    method forward (line 77) | def forward(
  class Conv1d (line 89) | class Conv1d(nn.Module):
    method __init__ (line 92) | def __init__(
    method forward (line 120) | def forward(
  class Linker (line 143) | class Linker(nn.Module):
    method __init__ (line 146) | def __init__(self, permuting: bool = True) -> None:
    method forward (line 154) | def forward(self, x: Tuple[torch.Tensor, torch.Tensor]) -> PackedSeque...
  class BiLSTM (line 162) | class BiLSTM(nn.Module):
    method __init__ (line 164) | def __init__(self, input_size: int, hidden_size: int, using_sequence: ...
    method forward (line 175) | def forward(self, x: PackedSequence) -> torch.Tensor:
  class MaxOut (line 186) | class MaxOut(nn.Module):
    method __init__ (line 187) | def __init__(self, input_size: int, hidden_size: int) -> None:
    method forward (line 192) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class LexiconEncoder (line 198) | class LexiconEncoder(nn.Module):
    method __init__ (line 199) | def __init__(self, coarse_vocab, fine_vocab, fine_embedding_dim):
    method forward (line 219) | def forward(self, inputs: Tuple[torch.Tensor, torch.Tensor]) -> Tuple[...
  class ContextualEncoder (line 239) | class ContextualEncoder(nn.Module):
    method __init__ (line 240) | def __init__(self, input_size, hidden_size) -> None:
    method forward (line 250) | def forward(self, inputs: Tuple[torch.Tensor, torch.Tensor]) -> Tuple[...

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/model/split.py
  function split_jamos (line 8) | def split_jamos(string: str) -> List[str]:

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 171) | def __init__(
    method split (line 187) | def split(self, string: str) -> List[str]:
    method transform (line 191) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 196) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 200) | def vocab(self):
  class PadSequence (line 204) | class PadSequence:
    method __init__ (line 207) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 218) | def __call__(self, sample):
  class PreProcessor (line 229) | class PreProcessor:
    method __init__ (line 230) | def __init__(self, coarse_vocab, fine_vocab, coarse_split_fn, fine_spl...
    method preprocess (line 237) | def preprocess(self, string):
    method coarse_vocab (line 244) | def coarse_vocab(self):
    method fine_vocab (line 248) | def fine_vocab(self):
    method _transform_fine (line 251) | def _transform_fine(self, token):

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/train.py
  function get_preprocessor (line 17) | def get_preprocessor(dataset_config, coarse_split_fn, fine_split_fn):
  function get_data_loaders (line 29) | def get_data_loaders(dataset_config, preprocessor, batch_size, collate_fn):
  function main (line 38) | def main(args):

FILE: Stochastic_Answer_Networks_for_Natural_Language_Inference/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 22) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 30) | def update(self, json_path_or_dict) -> None:
    method dict (line 43) | def dict(self) -> dict:
  class CheckpointManager (line 47) | class CheckpointManager:
    method __init__ (line 50) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 63) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 71) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 86) | class SummaryManager:
    method __init__ (line 89) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 98) | def save(self, filename: str) -> None:
    method load (line 106) | def load(self, filename) -> None:
    method update (line 115) | def update(self, summary: dict) -> None:
    method reset (line 122) | def reset(self) -> None:
    method summary (line 127) | def summary(self):

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/evaluate.py
  function get_tokenizer (line 15) | def get_tokenizer(dataset_config, model_config):
  function main (line 23) | def main(args):

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/model/data.py
  class Corpus (line 7) | class Corpus(Dataset):
    method __init__ (line 9) | def __init__(self, filepath: str, transform_fn: Callable[[str], List[i...
    method __len__ (line 18) | def __len__(self) -> int:
    method __getitem__ (line 21) | def __getitem__(self, idx: int) -> Tuple[torch.Tensor, torch.Tensor]:

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/model/metric.py
  function evaluate (line 5) | def evaluate(model, data_loader, metrics, device):
  function acc (line 26) | def acc(yhat, y):

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/model/net.py
  class VDCNN (line 7) | class VDCNN(nn.Module):
    method __init__ (line 9) | def __init__(self, num_classes: int, embedding_dim: int, k_max: int, v...
    method forward (line 42) | def forward(self, x: torch.Tensor) -> torch.Tensor:

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/model/ops.py
  class Flatten (line 6) | class Flatten(nn.Module):
    method forward (line 8) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class Permute (line 12) | class Permute(nn.Module):
    method forward (line 14) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class ConvBlock (line 18) | class ConvBlock(nn.Module):
    method __init__ (line 20) | def __init__(self, in_channels: int, out_channels: int) -> None:
    method forward (line 41) | def forward(self, x: torch.Tensor) -> torch.Tensor:

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/model/split.py
  function split_to_jamo (line 5) | def split_to_jamo(string: str) -> List[str]:

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/model/utils.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 7) | def __init__(
    method to_indices (line 66) | def to_indices(self, tokens: Union[str, List[str]]) -> Union[int, List...
    method to_tokens (line 87) | def to_tokens(self, indices: Union[int, List[int]]) -> Union[str, List...
    method _build (line 99) | def _build(self, list_of_tokens):
    method _sort_index_according_to_user_specification (line 104) | def _sort_index_according_to_user_specification(self, token_to_idx):
    method __len__ (line 132) | def __len__(self):
    method token_to_idx (line 136) | def token_to_idx(self):
    method idx_to_token (line 140) | def idx_to_token(self):
    method padding_token (line 144) | def padding_token(self):
    method unknown_token (line 148) | def unknown_token(self):
    method bos_token (line 152) | def bos_token(self):
    method eos_token (line 156) | def eos_token(self):
    method embedding (line 160) | def embedding(self):
    method embedding (line 164) | def embedding(self, array):
  class Tokenizer (line 168) | class Tokenizer:
    method __init__ (line 170) | def __init__(self, vocab: Vocab, split_fn: Callable[[str], List[str]],
    method split (line 182) | def split(self, string: str) -> List[str]:
    method transform (line 186) | def transform(self, list_of_tokens: List[str]) -> List[int]:
    method split_and_transform (line 191) | def split_and_transform(self, string: str) -> List[int]:
    method vocab (line 195) | def vocab(self):
  class PadSequence (line 199) | class PadSequence:
    method __init__ (line 201) | def __init__(self, length: int, pad_val: int = 0, clip: bool = True) -...
    method __call__ (line 212) | def __call__(self, sample):

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/train.py
  function get_tokenizer (line 19) | def get_tokenizer(dataset_config, model_config):
  function get_data_loaders (line 27) | def get_data_loaders(dataset_config, tokenizer, batch_size):
  function main (line 35) | def main(args):

FILE: Very_Deep_Convolutional_Networks_for_Text_Classification/utils.py
  class Config (line 7) | class Config:
    method __init__ (line 10) | def __init__(self, json_path_or_dict: Union[str, dict]) -> None:
    method save (line 23) | def save(self, json_path: Union[str, Path]) -> None:
    method update (line 32) | def update(self, json_path_or_dict) -> None:
    method dict (line 46) | def dict(self) -> dict:
  class CheckpointManager (line 50) | class CheckpointManager:
    method __init__ (line 53) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save_checkpoint (line 67) | def save_checkpoint(self, state: dict, filename: str) -> None:
    method load_checkpoint (line 76) | def load_checkpoint(self, filename: str, device: torch.device = None) ...
  class SummaryManager (line 91) | class SummaryManager:
    method __init__ (line 94) | def __init__(self, model_dir: Union[str, Path]) -> None:
    method save (line 103) | def save(self, filename: str) -> None:
    method load (line 112) | def load(self, filename) -> None:
    method update (line 121) | def update(self, summary: dict) -> None:
    method reset (line 129) | def reset(self) -> None:
    method summary (line 134) | def summary(self):