FM / layoutlmv2

/usr/local/lib/python3.6/site-packages/transformers/models/layoutlmv2/

/usr/local/lib/python3.6/site-packages/transformers/models/layoutlmv2

Name	Size	Mode	Actions
__pycache__/	-	0755	rm
configuration_layoutlmv2.py	11224	0644	edit dl rm
feature_extraction_layoutlmv2.py	9827	0644	edit dl rm
modeling_layoutlmv2.py	58513	0644	edit dl rm
processing_layoutlmv2.py	6171	0644	edit dl rm
tokenization_layoutlmv2.py	68128	0644	edit dl rm
tokenization_layoutlmv2_fast.py	37857	0644	edit dl rm
__init__.py	2722	0644	edit dl rm

Edit: /usr/local/lib/python3.6/site-packages/transformers/models/layoutlmv2/processing_layoutlmv2.py (6171B)

# 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 LayoutLMv2.
"""
from typing import List, Optional, Union

from ...processing_utils import ProcessorMixin
from ...tokenization_utils_base import BatchEncoding, PaddingStrategy, PreTokenizedInput, TextInput, TruncationStrategy
from ...utils import TensorType

class LayoutLMv2Processor(ProcessorMixin):
    r"""
    Constructs a LayoutLMv2 processor which combines a LayoutLMv2 feature extractor and a LayoutLMv2 tokenizer into a
    single processor.

[`LayoutLMv2Processor`] offers all the functionalities you need to prepare data for the model.

It first uses [`LayoutLMv2FeatureExtractor`] to resize document images to a fixed size, and optionally applies OCR
    to get words and normalized bounding boxes. These are then provided to [`LayoutLMv2Tokenizer`] or
    [`LayoutLMv2TokenizerFast`], which turns the words and bounding boxes into token-level `input_ids`,
    `attention_mask`, `token_type_ids`, `bbox`. Optionally, one can provide integer `word_labels`, which are turned
    into token-level `labels` for token classification tasks (such as FUNSD, CORD).

Args:
        feature_extractor (`LayoutLMv2FeatureExtractor`):
            An instance of [`LayoutLMv2FeatureExtractor`]. The feature extractor is a required input.
        tokenizer (`LayoutLMv2Tokenizer` or `LayoutLMv2TokenizerFast`):
            An instance of [`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`]. The tokenizer is a required input.
    """
    feature_extractor_class = "LayoutLMv2FeatureExtractor"
    tokenizer_class = ("LayoutLMv2Tokenizer", "LayoutLMv2TokenizerFast")

def __call__(
        self,
        images,
        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
        text_pair: Optional[Union[PreTokenizedInput, List[PreTokenizedInput]]] = None,
        boxes: Union[List[List[int]], List[List[List[int]]]] = None,
        word_labels: Optional[Union[List[int], List[List[int]]]] = None,
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = False,
        max_length: Optional[int] = None,
        stride: int = 0,
        pad_to_multiple_of: Optional[int] = 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,
        return_tensors: Optional[Union[str, TensorType]] = None,
        **kwargs
    ) -> BatchEncoding:
        """
        This method first forwards the `images` argument to [`~LayoutLMv2FeatureExtractor.__call__`]. In case
        [`LayoutLMv2FeatureExtractor`] was initialized with `apply_ocr` set to `True`, it passes the obtained words and
        bounding boxes along with the additional arguments to [`~LayoutLMv2Tokenizer.__call__`] and returns the output,
        together with resized `images`. In case [`LayoutLMv2FeatureExtractor`] was initialized with `apply_ocr` set to
        `False`, it passes the words (`text`/``text_pair`) and `boxes` specified by the user along with the additional
        arguments to [`~LayoutLMv2Tokenizer.__call__`] and returns the output, together with resized `images``.

Please refer to the docstring of the above two methods for more information.
        """
        # verify input
        if self.feature_extractor.apply_ocr and (boxes is not None):
            raise ValueError(
                "You cannot provide bounding boxes "
                "if you initialized the feature extractor with apply_ocr set to True."
            )

if self.feature_extractor.apply_ocr and (word_labels is not None):
            raise ValueError(
                "You cannot provide word labels "
                "if you initialized the feature extractor with apply_ocr set to True."
            )

# first, apply the feature extractor
        features = self.feature_extractor(images=images, return_tensors=return_tensors)

# second, apply the tokenizer
        if text is not None and self.feature_extractor.apply_ocr and text_pair is None:
            if isinstance(text, str):
                text = [text]  # add batch dimension (as the feature extractor always adds a batch dimension)
            text_pair = features["words"]

encoded_inputs = self.tokenizer(
            text=text if text is not None else features["words"],
            text_pair=text_pair if text_pair is not None else None,
            boxes=boxes if boxes is not None else features["boxes"],
            word_labels=word_labels,
            add_special_tokens=add_special_tokens,
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            stride=stride,
            pad_to_multiple_of=pad_to_multiple_of,
            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,
            return_tensors=return_tensors,
            **kwargs,
        )

# add pixel values
        encoded_inputs["image"] = features.pop("pixel_values")

return encoded_inputs

cmd: