From 8291a87c64f9a5f18caec82201bea15579b49730 Mon Sep 17 00:00:00 2001 From: Gustaf Rydholm Date: Sun, 10 Oct 2021 18:04:50 +0200 Subject: Move data utils to submodules --- text_recognizer/data/emnist_mapping.py | 60 ---------------------------------- 1 file changed, 60 deletions(-) delete mode 100644 text_recognizer/data/emnist_mapping.py (limited to 'text_recognizer/data/emnist_mapping.py') diff --git a/text_recognizer/data/emnist_mapping.py b/text_recognizer/data/emnist_mapping.py deleted file mode 100644 index b2165d2..0000000 --- a/text_recognizer/data/emnist_mapping.py +++ /dev/null @@ -1,60 +0,0 @@ -"""Emnist mapping.""" -from typing import List, Optional, Set, Union - -import torch -from torch import Tensor - -from text_recognizer.data.base_mapping import AbstractMapping -from text_recognizer.data.emnist import emnist_mapping - - -class EmnistMapping(AbstractMapping): - """Mapping for EMNIST labels.""" - - def __init__( - self, extra_symbols: Optional[Set[str]] = None, lower: bool = True - ) -> None: - self.extra_symbols = set(extra_symbols) if extra_symbols is not None else None - self.mapping, self.inverse_mapping, self.input_size = emnist_mapping( - self.extra_symbols - ) - if lower: - self._to_lower() - super().__init__(self.input_size, self.mapping, self.inverse_mapping) - - def _to_lower(self) -> None: - """Converts mapping to lowercase letters only.""" - - def _filter(x: int) -> int: - if 40 <= x: - return x - 26 - return x - - self.inverse_mapping = {v: _filter(k) for k, v in enumerate(self.mapping)} - self.mapping = [c for c in self.mapping if not c.isupper()] - - def get_token(self, index: Union[int, Tensor]) -> str: - """Returns token for index value.""" - if (index := int(index)) <= len(self.mapping): - return self.mapping[index] - raise KeyError(f"Index ({index}) not in mapping.") - - def get_index(self, token: str) -> Tensor: - """Returns index value of token.""" - if token in self.inverse_mapping: - return torch.LongTensor([self.inverse_mapping[token]]) - raise KeyError(f"Token ({token}) not found in inverse mapping.") - - def get_text(self, indices: Union[List[int], Tensor]) -> str: - """Returns the text from a list of indices.""" - if isinstance(indices, Tensor): - indices = indices.tolist() - return "".join([self.mapping[index] for index in indices]) - - def get_indices(self, text: str) -> Tensor: - """Returns tensor of indices for a string.""" - return Tensor([self.inverse_mapping[token] for token in text]) - - def __getitem__(self, x: Union[int, Tensor]) -> str: - """Returns text for a list of indices.""" - return self.get_token(x) -- cgit v1.2.3-70-g09d2