You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
70 lines
2.3 KiB
70 lines
2.3 KiB
# 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 ...image_processing_utils import BatchFeature
|
|
from ...image_utils import ImageInput
|
|
from ...processing_utils import ProcessingKwargs, ProcessorMixin, Unpack
|
|
from ...tokenization_utils_base import PreTokenizedInput, TextInput
|
|
from ...utils import auto_docstring
|
|
|
|
|
|
class TrOCRProcessorKwargs(ProcessingKwargs, total=False):
|
|
_defaults = {}
|
|
|
|
|
|
@auto_docstring
|
|
class TrOCRProcessor(ProcessorMixin):
|
|
def __init__(self, image_processor=None, tokenizer=None, **kwargs):
|
|
super().__init__(image_processor, tokenizer)
|
|
|
|
@auto_docstring
|
|
def __call__(
|
|
self,
|
|
images: ImageInput | None = None,
|
|
text: TextInput | PreTokenizedInput | list[TextInput] | list[PreTokenizedInput] | None = None,
|
|
**kwargs: Unpack[TrOCRProcessorKwargs],
|
|
) -> BatchFeature:
|
|
if images is None and text is None:
|
|
raise ValueError("You need to specify either an `images` or `text` input to process.")
|
|
|
|
output_kwargs = self._merge_kwargs(
|
|
TrOCRProcessorKwargs,
|
|
tokenizer_init_kwargs=self.tokenizer.init_kwargs,
|
|
**kwargs,
|
|
)
|
|
|
|
if images is not None:
|
|
inputs = self.image_processor(images, **output_kwargs["images_kwargs"])
|
|
if text is not None:
|
|
encodings = self.tokenizer(text, **output_kwargs["text_kwargs"])
|
|
|
|
if text is None:
|
|
return inputs
|
|
elif images is None:
|
|
return encodings
|
|
else:
|
|
inputs["labels"] = encodings["input_ids"]
|
|
return inputs
|
|
|
|
@property
|
|
def model_input_names(self):
|
|
image_processor_input_names = self.image_processor.model_input_names
|
|
return image_processor_input_names + ["labels"]
|
|
|
|
|
|
__all__ = ["TrOCRProcessor"]
|