Spaces:
Runtime error
Runtime error
File size: 1,488 Bytes
153628e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
# Copyright (C) 2021-2024, Mindee.
# This program is licensed under the Apache License 2.0.
# See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
from typing import List, Tuple
import numpy as np
from ....datasets import encode_sequences
from ..core import RecognitionPostProcessor
class _ViTSTR:
vocab: str
max_length: int
def build_target(
self,
gts: List[str],
) -> Tuple[np.ndarray, List[int]]:
"""Encode a list of gts sequences into a np array and gives the corresponding*
sequence lengths.
Args:
----
gts: list of ground-truth labels
Returns:
-------
A tuple of 2 tensors: Encoded labels and sequence lengths (for each entry of the batch)
"""
encoded = encode_sequences(
sequences=gts,
vocab=self.vocab,
target_size=self.max_length,
eos=len(self.vocab),
sos=len(self.vocab) + 1,
)
seq_len = [len(word) for word in gts]
return encoded, seq_len
class _ViTSTRPostProcessor(RecognitionPostProcessor):
"""Abstract class to postprocess the raw output of the model
Args:
----
vocab: string containing the ordered sequence of supported characters
"""
def __init__(
self,
vocab: str,
) -> None:
super().__init__(vocab)
self._embedding = list(vocab) + ["<eos>", "<sos>"]
|