File size: 6,731 Bytes
d1ceb73 |
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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
# coding=utf-8
# Copyright 2023 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 Nougat.
"""
from typing import Dict, List, Optional, Union
from transformers.tokenization_utils_base import PreTokenizedInput, TextInput, TruncationStrategy
from ...processing_utils import ProcessorMixin
from ...utils import PaddingStrategy, TensorType
class NougatProcessor(ProcessorMixin):
r"""
Constructs a Nougat processor which wraps a Nougat image processor and a Nougat tokenizer into a single processor.
[`NougatProcessor`] offers all the functionalities of [`NougatImageProcessor`] and [`NougatTokenizerFast`]. See the
[`~NougatProcessor.__call__`] and [`~NougatProcessor.decode`] for more information.
Args:
image_processor ([`NougatImageProcessor`]):
An instance of [`NougatImageProcessor`]. The image processor is a required input.
tokenizer ([`NougatTokenizerFast`]):
An instance of [`NougatTokenizerFast`]. The tokenizer is a required input.
"""
attributes = ["image_processor", "tokenizer"]
image_processor_class = "AutoImageProcessor"
tokenizer_class = "AutoTokenizer"
def __init__(self, image_processor, tokenizer):
super().__init__(image_processor, tokenizer)
self.current_processor = self.image_processor
def __call__(
self,
images=None,
text=None,
do_crop_margin: bool = None,
do_resize: bool = None,
size: Dict[str, int] = None,
resample: "PILImageResampling" = None, # noqa: F821
do_thumbnail: bool = None,
do_align_long_axis: bool = None,
do_pad: bool = None,
do_rescale: bool = None,
rescale_factor: Union[int, float] = None,
do_normalize: bool = None,
image_mean: Optional[Union[float, List[float]]] = None,
image_std: Optional[Union[float, List[float]]] = None,
data_format: Optional["ChannelDimension"] = "channels_first", # noqa: F821
input_data_format: Optional[Union[str, "ChannelDimension"]] = None, # noqa: F821
text_pair: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]] = None,
text_target: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
text_pair_target: Optional[
Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]
] = None,
add_special_tokens: bool = True,
padding: Union[bool, str, PaddingStrategy] = False,
truncation: Union[bool, str, TruncationStrategy] = None,
max_length: Optional[int] = None,
stride: int = 0,
is_split_into_words: bool = False,
pad_to_multiple_of: Optional[int] = None,
return_tensors: Optional[Union[str, TensorType]] = None,
return_token_type_ids: Optional[bool] = None,
return_attention_mask: Optional[bool] = None,
return_overflowing_tokens: bool = False,
return_special_tokens_mask: bool = False,
return_offsets_mapping: bool = False,
return_length: bool = False,
verbose: bool = True,
):
if images is None and text is None:
raise ValueError("You need to specify either an `images` or `text` input to process.")
if images is not None:
inputs = self.image_processor(
images,
do_crop_margin=do_crop_margin,
do_resize=do_resize,
size=size,
resample=resample,
do_thumbnail=do_thumbnail,
do_align_long_axis=do_align_long_axis,
do_pad=do_pad,
do_rescale=do_rescale,
rescale_factor=rescale_factor,
do_normalize=do_normalize,
image_mean=image_mean,
image_std=image_std,
return_tensors=return_tensors,
data_format=data_format,
input_data_format=input_data_format,
)
if text is not None:
encodings = self.tokenizer(
text,
text_pair=text_pair,
text_target=text_target,
text_pair_target=text_pair_target,
add_special_tokens=add_special_tokens,
padding=padding,
truncation=truncation,
max_length=max_length,
stride=stride,
is_split_into_words=is_split_into_words,
pad_to_multiple_of=pad_to_multiple_of,
return_tensors=return_tensors,
return_token_type_ids=return_token_type_ids,
return_attention_mask=return_attention_mask,
return_overflowing_tokens=return_overflowing_tokens,
return_special_tokens_mask=return_special_tokens_mask,
return_offsets_mapping=return_offsets_mapping,
return_length=return_length,
verbose=verbose,
)
if text is None:
return inputs
elif images is None:
return encodings
else:
inputs["labels"] = encodings["input_ids"]
return inputs
def batch_decode(self, *args, **kwargs):
"""
This method forwards all its arguments to NougatTokenizer'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 NougatTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to
the docstring of this method for more information.
"""
return self.tokenizer.decode(*args, **kwargs)
def post_process_generation(self, *args, **kwargs):
"""
This method forwards all its arguments to NougatTokenizer's [`~PreTrainedTokenizer.post_process_generation`].
Please refer to the docstring of this method for more information.
"""
return self.tokenizer.post_process_generation(*args, **kwargs)
|