pip install -q transformers datasets

pip install 'git+https://github.com/facebookresearch/detectron2.git'
pip install torchvision

sudo apt install tesseract-ocr
pip install -q pytesseract

>>> from huggingface_hub import notebook_login

>>> notebook_login()

>>> model_checkpoint = "microsoft/layoutlmv2-base-uncased"
>>> batch_size = 4

>>> from datasets import load_dataset

>>> dataset = load_dataset("nielsr/docvqa_1200_examples")
>>> dataset
DatasetDict({
    train: Dataset({
        features: ['id', 'image', 'query', 'answers', 'words', 'bounding_boxes', 'answer'],
        num_rows: 1000
    })
    test: Dataset({
        features: ['id', 'image', 'query', 'answers', 'words', 'bounding_boxes', 'answer'],
        num_rows: 200
    })
})

>>> dataset["train"].features

>>> updated_dataset = dataset.map(lambda example: {"question": example["query"]["en"]}, remove_columns=["query"])
>>> updated_dataset = updated_dataset.map(
...     lambda example: {"answer": example["answers"][0]}, remove_columns=["answer", "answers"]
... )

>>> updated_dataset = updated_dataset.filter(lambda x: len(x["words"]) + len(x["question"].split()) < 512)

>>> updated_dataset = updated_dataset.remove_columns("words")
>>> updated_dataset = updated_dataset.remove_columns("bounding_boxes")

>>> updated_dataset["train"][11]["image"]

>>> from transformers import AutoProcessor

>>> processor = AutoProcessor.from_pretrained(model_checkpoint)

>>> image_processor = processor.image_processor


>>> def get_ocr_words_and_boxes(examples):
...     images = [image.convert("RGB") for image in examples["image"]]
...     encoded_inputs = image_processor(images)

...     examples["image"] = encoded_inputs.pixel_values
...     examples["words"] = encoded_inputs.words
...     examples["boxes"] = encoded_inputs.boxes

...     return examples

>>> dataset_with_ocr = updated_dataset.map(get_ocr_words_and_boxes, batched=True, batch_size=2)

>>> tokenizer = processor.tokenizer

>>> def subfinder(words_list, answer_list):
...     matches = []
...     start_indices = []
...     end_indices = []
...     for idx, i in enumerate(range(len(words_list))):
...         if words_list[i] == answer_list[0] and words_list[i : i + len(answer_list)] == answer_list:
...             matches.append(answer_list)
...             start_indices.append(idx)
...             end_indices.append(idx + len(answer_list) - 1)
...     if matches:
...         return matches[0], start_indices[0], end_indices[0]
...     else:
...         return None, 0, 0

>>> example = dataset_with_ocr["train"][1]
>>> words = [word.lower() for word in example["words"]]
>>> match, word_idx_start, word_idx_end = subfinder(words, example["answer"].lower().split())
>>> print("Question: ", example["question"])
>>> print("Words:", words)
>>> print("Answer: ", example["answer"])
>>> print("start_index", word_idx_start)
>>> print("end_index", word_idx_end)
Question:  Who is in  cc in this letter?
Words: ['wie', 'baw', 'brown', '&', 'williamson', 'tobacco', 'corporation', 'research', '&', 'development', 'internal', 'correspondence', 'to:', 'r.', 'h.', 'honeycutt', 'ce:', 't.f.', 'riehl', 'from:', '.', 'c.j.', 'cook', 'date:', 'may', '8,', '1995', 'subject:', 'review', 'of', 'existing', 'brainstorming', 'ideas/483', 'the', 'major', 'function', 'of', 'the', 'product', 'innovation', 'graup', 'is', 'to', 'develop', 'marketable', 'nove!', 'products', 'that', 'would', 'be', 'profitable', 'to', 'manufacture', 'and', 'sell.', 'novel', 'is', 'defined', 'as:', 'of', 'a', 'new', 'kind,', 'or', 'different', 'from', 'anything', 'seen', 'or', 'known', 'before.', 'innovation', 'is', 'defined', 'as:', 'something', 'new', 'or', 'different', 'introduced;', 'act', 'of', 'innovating;', 'introduction', 'of', 'new', 'things', 'or', 'methods.', 'the', 'products', 'may', 'incorporate', 'the', 'latest', 'technologies,', 'materials', 'and', 'know-how', 'available', 'to', 'give', 'then', 'a', 'unique', 'taste', 'or', 'look.', 'the', 'first', 'task', 'of', 'the', 'product', 'innovation', 'group', 'was', 'to', 'assemble,', 'review', 'and', 'categorize', 'a', 'list', 'of', 'existing', 'brainstorming', 'ideas.', 'ideas', 'were', 'grouped', 'into', 'two', 'major', 'categories', 'labeled', 'appearance', 'and', 'taste/aroma.', 'these', 'categories', 'are', 'used', 'for', 'novel', 'products', 'that', 'may', 'differ', 'from', 'a', 'visual', 'and/or', 'taste/aroma', 'point', 'of', 'view', 'compared', 'to', 'canventional', 'cigarettes.', 'other', 'categories', 'include', 'a', 'combination', 'of', 'the', 'above,', 'filters,', 'packaging', 'and', 'brand', 'extensions.', 'appearance', 'this', 'category', 'is', 'used', 'for', 'novel', 'cigarette', 'constructions', 'that', 'yield', 'visually', 'different', 'products', 'with', 'minimal', 'changes', 'in', 'smoke', 'chemistry', 'two', 'cigarettes', 'in', 'cne.', 'emulti-plug', 'te', 'build', 'yaur', 'awn', 'cigarette.', 'eswitchable', 'menthol', 'or', 'non', 'menthol', 'cigarette.', '*cigarettes', 'with', 'interspaced', 'perforations', 'to', 'enable', 'smoker', 'to', 'separate', 'unburned', 'section', 'for', 'future', 'smoking.', '«short', 'cigarette,', 'tobacco', 'section', '30', 'mm.', '«extremely', 'fast', 'buming', 'cigarette.', '«novel', 'cigarette', 'constructions', 'that', 'permit', 'a', 'significant', 'reduction', 'iretobacco', 'weight', 'while', 'maintaining', 'smoking', 'mechanics', 'and', 'visual', 'characteristics.', 'higher', 'basis', 'weight', 'paper:', 'potential', 'reduction', 'in', 'tobacco', 'weight.', '«more', 'rigid', 'tobacco', 'column;', 'stiffing', 'agent', 'for', 'tobacco;', 'e.g.', 'starch', '*colored', 'tow', 'and', 'cigarette', 'papers;', 'seasonal', 'promotions,', 'e.g.', 'pastel', 'colored', 'cigarettes', 'for', 'easter', 'or', 'in', 'an', 'ebony', 'and', 'ivory', 'brand', 'containing', 'a', 'mixture', 'of', 'all', 'black', '(black', 'paper', 'and', 'tow)', 'and', 'ail', 'white', 'cigarettes.', '499150498']
Answer:  T.F. Riehl
start_index 17
end_index 18

>>> encoding = tokenizer(example["question"], example["words"], example["boxes"])
>>> tokenizer.decode(encoding["input_ids"])
[CLS] who is in cc in this letter? [SEP] wie baw brown & williamson tobacco corporation research & development ...

>>> def encode_dataset(examples, max_length=512):
...     questions = examples["question"]
...     words = examples["words"]
...     boxes = examples["boxes"]
...     answers = examples["answer"]

...     # encode the batch of examples and initialize the start_positions and end_positions
...     encoding = tokenizer(questions, words, boxes, max_length=max_length, padding="max_length", truncation=True)
...     start_positions = []
...     end_positions = []

...     # loop through the examples in the batch
...     for i in range(len(questions)):
...         cls_index = encoding["input_ids"][i].index(tokenizer.cls_token_id)

...         # find the position of the answer in example's words
...         words_example = [word.lower() for word in words[i]]
...         answer = answers[i]
...         match, word_idx_start, word_idx_end = subfinder(words_example, answer.lower().split())

...         if match:
...             # if match is found, use `token_type_ids` to find where words start in the encoding
...             token_type_ids = encoding["token_type_ids"][i]
...             token_start_index = 0
...             while token_type_ids[token_start_index] != 1:
...                 token_start_index += 1

...             token_end_index = len(encoding["input_ids"][i]) - 1
...             while token_type_ids[token_end_index] != 1:
...                 token_end_index -= 1

...             word_ids = encoding.word_ids(i)[token_start_index : token_end_index + 1]
...             start_position = cls_index
...             end_position = cls_index

...             # loop over word_ids and increase `token_start_index` until it matches the answer position in words
...             # once it matches, save the `token_start_index` as the `start_position` of the answer in the encoding
...             for id in word_ids:
...                 if id == word_idx_start:
...                     start_position = token_start_index
...                 else:
...                     token_start_index += 1

...             # similarly loop over `word_ids` starting from the end to find the `end_position` of the answer
...             for id in word_ids[::-1]:
...                 if id == word_idx_end:
...                     end_position = token_end_index
...                 else:
...                     token_end_index -= 1

...             start_positions.append(start_position)
...             end_positions.append(end_position)

...         else:
...             start_positions.append(cls_index)
...             end_positions.append(cls_index)

...     encoding["image"] = examples["image"]
...     encoding["start_positions"] = start_positions
...     encoding["end_positions"] = end_positions

...     return encoding

>>> encoded_train_dataset = dataset_with_ocr["train"].map(
...     encode_dataset, batched=True, batch_size=2, remove_columns=dataset_with_ocr["train"].column_names
... )
>>> encoded_test_dataset = dataset_with_ocr["test"].map(
...     encode_dataset, batched=True, batch_size=2, remove_columns=dataset_with_ocr["test"].column_names
... )

>>> encoded_train_dataset.features
{'image': Sequence(feature=Sequence(feature=Sequence(feature=Value(dtype='uint8', id=None), length=-1, id=None), length=-1, id=None), length=-1, id=None),
 'input_ids': Sequence(feature=Value(dtype='int32', id=None), length=-1, id=None),
 'token_type_ids': Sequence(feature=Value(dtype='int8', id=None), length=-1, id=None),
 'attention_mask': Sequence(feature=Value(dtype='int8', id=None), length=-1, id=None),
 'bbox': Sequence(feature=Sequence(feature=Value(dtype='int64', id=None), length=-1, id=None), length=-1, id=None),
 'start_positions': Value(dtype='int64', id=None),
 'end_positions': Value(dtype='int64', id=None)}

>>> from transformers import AutoModelForDocumentQuestionAnswering

>>> model = AutoModelForDocumentQuestionAnswering.from_pretrained(model_checkpoint)

>>> from transformers import TrainingArguments

>>> # REPLACE THIS WITH YOUR REPO ID
>>> repo_id = "MariaK/layoutlmv2-base-uncased_finetuned_docvqa"

>>> training_args = TrainingArguments(
...     output_dir=repo_id,
...     per_device_train_batch_size=4,
...     num_train_epochs=20,
...     save_steps=200,
...     logging_steps=50,
...     eval_strategy="steps",
...     learning_rate=5e-5,
...     save_total_limit=2,
...     remove_unused_columns=False,
...     push_to_hub=True,
... )

>>> from transformers import DefaultDataCollator

>>> data_collator = DefaultDataCollator()

>>> from transformers import Trainer

>>> trainer = Trainer(
...     model=model,
...     args=training_args,
...     data_collator=data_collator,
...     train_dataset=encoded_train_dataset,
...     eval_dataset=encoded_test_dataset,
...     tokenizer=processor,
... )

>>> trainer.train()

>>> trainer.create_model_card()
>>> trainer.push_to_hub()

>>> example = dataset["test"][2]
>>> question = example["query"]["en"]
>>> image = example["image"]
>>> print(question)
>>> print(example["answers"])
'Who is ‘presiding’ TRRF GENERAL SESSION (PART 1)?'
['TRRF Vice President', 'lee a. waller']

>>> from transformers import pipeline

>>> qa_pipeline = pipeline("document-question-answering", model="MariaK/layoutlmv2-base-uncased_finetuned_docvqa")
>>> qa_pipeline(image, question)
[{'score': 0.9949808120727539,
  'answer': 'Lee A. Waller',
  'start': 55,
  'end': 57}]

>>> import torch
>>> from transformers import AutoProcessor
>>> from transformers import AutoModelForDocumentQuestionAnswering

>>> processor = AutoProcessor.from_pretrained("MariaK/layoutlmv2-base-uncased_finetuned_docvqa")
>>> model = AutoModelForDocumentQuestionAnswering.from_pretrained("MariaK/layoutlmv2-base-uncased_finetuned_docvqa")

>>> with torch.no_grad():
...     encoding = processor(image.convert("RGB"), question, return_tensors="pt")
...     outputs = model(**encoding)
...     start_logits = outputs.start_logits
...     end_logits = outputs.end_logits
...     predicted_start_idx = start_logits.argmax(-1).item()
...     predicted_end_idx = end_logits.argmax(-1).item()

>>> processor.tokenizer.decode(encoding.input_ids.squeeze()[predicted_start_idx : predicted_end_idx + 1])
'lee a. waller'