https://github.com/deepdoctection/notebooks

Repository for deepdoctection tutorial notebooks
https://github.com/deepdoctection/notebooks

Last synced: 24 days ago
JSON representation

Repository for deepdoctection tutorial notebooks

• Host: GitHub
• URL: https://github.com/deepdoctection/notebooks
• Owner: deepdoctection
• License: apache-2.0
• Created: 2022-12-04T13:20:56.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-21T21:14:45.000Z (9 months ago)
• Last Synced: 2024-07-21T22:37:36.122Z (9 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 22.4 MB
• Stars: 33
• Watchers: 2
• Forks: 15
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        



  

  


  A Document AI Package - Jupyter notebook tutorials

  


# Breaking changes

With the latest release of **deep**doctection v.0.33.0 the package has been refactored and is not compatible with 

previous releases. If you are on a previous version, please update to the latest version or choose the repo

version that is tagged with v.0.32.0

# Jupyter Notebooks for **deep**doctection 

In this repo you will find jupyter notebooks that used to be in the main repo [**deep**doctection](https://github.com/deepdoctection/deepdoctection). If you encouter problems, feel free to open an issue in the **deep**doctection repository.

In addition, the repo contains a folder with examples that are used in the notebooks.git 

[Get_Started.ipynb](Get_Started.ipynb): 

- Introduction to **deep**doctection

- Analyzer 

- Output structure: Page, Layouts, Tables

- Saving and reading a parsed document

[Pipelines.ipynb](Pipelines.ipynb):

- Pipelines

- Analyzer configuration

- Pipeline components

- Layout detection models

- OCR matching and reading order

[Analyzer_Configuration.ipynb](Analyzer_Configuration.ipynb)

- Analyzer Configuration

- How to change configuration

- High level Configuration

- Layout models

- Table transformer

- Custom model

- Table segmentation

- Text extraction

- PDFPlumber

- Tesseract

- DocTr

- AWS Textract

- Word matching

- Text ordering

[Analyzer_with_Table_Transformer.ipynb](Analyzer_with_Table_Transformer.ipynb):

- Analyzer configuration for running Table Transformer

- General configuration

- Table segmentation

[Doclaynet_with_YOLO.ipynb](Doclaynet_with_YOLO.ipynb)

- Writing a predictor from a third party library

- Adding the model wrapper for YOLO

- Adding the model to the `ModelCatalog`

- Modifying the factory class to build the Analyzer

- Running the Analyzer with the YoloDetector

[Doclaynet_Analyzer_Config.ipynb](Doclaynet_Analyzer_Config.ipynb)

- Advanced Analyzer Configuration

- Adding the model wrapper for YOLO

- Configuration to parse the page with respect to granular layout segments

- Extracting figures

- Relating captions to figures and tables

[Custom_Pipeline.ipynb](Custom_Pipeline.ipynb): 

- Model catalog and registries

- Predictors

- Instantiating Pipeline backbones

- Instantiating Pipelines

[Datasets_and_Eval.ipynb](Datasets_and_Eval.ipynb): 

- Creation of custom datasets

- Evaluation

- Fine tuning models

[Data_structure.ipynb](Data_structure.ipynb):

- Diving deeper into the data structure

- Page and Image

- `ObjectTypes`

- `ImageAnnotation` and sub categories

- Adding an `ImageAnnotation`

- Adding a `ContainerAnnotation` to an `ImageAnnotation`

- Sub images from given `ImageAnnotation`

[Using_LayoutLM_for_sequence_classification.ipynb](Using_LayoutLM_for_sequence_classification.ipynb): 

- Fine tuning LayoutLM for sequence classification on a custom dataset

- Evaluation 

- Building and running a production pipeline 

[Running_pre_trained_models_from_other_libraries.ipynb](Running_pre_trained_models_from_other_libraries.ipynb)

- Installing and running pre-trained models provided by Layout-Parser

- Adding new categories

The next three notebooks are experiments on a custom dataset for token classification that has been made available 

through [Huggingface](https://huggingface.co/datasets/deepdoctection/FRFPE). It shows, how to train and evaluate each 

model of the LayoutLM family and how to track experiments with W&B. 

[Layoutlm_v1_on_custom_token_classification.ipynb](Layoutlm_v1_on_custom_token_classification.ipynb)

- LayoutLMv1 for financial report NER

- Defining object types

- Visualization and display of ground truth

- Defining Dataflow and Dataset

- Defining a split and saving the split distribution as W&B artifact 

- LayoutLMv1 training

- Further exploration of evaluation

- Evaluation with confusion matrix

- Visualizing predictions and ground truth

- Evaluation on test set

- Changing training parameters and settings

[Layoutlm_v2_on_custom_token_classification.ipynb](Layoutlm_v2_on_custom_token_classification.ipynb)

- LayoutLMv2 for financial report NER

- Defining `ObjectTypes`, Dataset and Dataflow

- Loading W&B artifact and building dataset split

- Exporing the language distribustion across the split

- Evaluation

- LayoutXLM for financial report NER

- Training XLM models on separate languages

[Layoutlm_v3_on_custom_token_classification.ipynb](Layoutlm_v3_on_custom_token_classification.ipynb)

- LayoutLMv3 for financial report NER

- Evaluation

- Conclusion

To use the notebooks **deep**doctection must be installed.