/
processing_trocr.py
74 lines (64 loc) 路 3.16 KB
/
processing_trocr.py
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
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
# coding=utf-8
# Copyright 2021 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Processor class for TrOCR.
"""
from contextlib import contextmanager
from ...processing_utils import ProcessorMixin
class TrOCRProcessor(ProcessorMixin):
r"""
Constructs a TrOCR processor which wraps a vision feature extractor and a TrOCR tokenizer into a single processor.
[`TrOCRProcessor`] offers all the functionalities of [`ViTFeatureExtractor`/`DeiTFeatureExtractor`] and
[`RobertaTokenizer`/`XLMRobertaTokenizer`]. See the [`~TrOCRProcessor.__call__`] and [`~TrOCRProcessor.decode`] for
more information.
Args:
feature_extractor ([`ViTFeatureExtractor`/`DeiTFeatureExtractor`]):
An instance of [`ViTFeatureExtractor`/`DeiTFeatureExtractor`]. The feature extractor is a required input.
tokenizer ([`RobertaTokenizer`/`XLMRobertaTokenizer`]):
An instance of [`RobertaTokenizer`/`XLMRobertaTokenizer`]. The tokenizer is a required input.
"""
feature_extractor_class = "AutoFeatureExtractor"
tokenizer_class = "AutoTokenizer"
def __init__(self, feature_extractor, tokenizer):
super().__init__(feature_extractor, tokenizer)
self.current_processor = self.feature_extractor
def __call__(self, *args, **kwargs):
"""
When used in normal mode, this method forwards all its arguments to AutoFeatureExtractor's
[`~AutoFeatureExtractor.__call__`] and returns its output. If used in the context
[`~TrOCRProcessor.as_target_processor`] this method forwards all its arguments to TrOCRTokenizer's
[`~TrOCRTokenizer.__call__`]. Please refer to the doctsring of the above two methods for more information.
"""
return self.current_processor(*args, **kwargs)
def batch_decode(self, *args, **kwargs):
"""
This method forwards all its arguments to TrOCRTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer
to the docstring of this method for more information.
"""
return self.tokenizer.batch_decode(*args, **kwargs)
def decode(self, *args, **kwargs):
"""
This method forwards all its arguments to TrOCRTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the
docstring of this method for more information.
"""
return self.tokenizer.decode(*args, **kwargs)
@contextmanager
def as_target_processor(self):
"""
Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning TrOCR.
"""
self.current_processor = self.tokenizer
yield
self.current_processor = self.feature_extractor