deepdoctection 0.42.1__py3-none-any.whl → 0.43__py3-none-any.whl

deepdoctection-0.42.1.dist-info/METADATA

@@ -1,431 +0,0 @@
-Metadata-Version: 2.4
-Name: deepdoctection
-Version: 0.42.1
-Summary: Repository for Document AI
-Home-page: https://github.com/deepdoctection/deepdoctection
-Author: Dr. Janis Meyer
-License: Apache License 2.0
-Classifier: Development Status :: 4 - Beta
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Natural Language :: English
-Classifier: Operating System :: POSIX :: Linux
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: >=3.9
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: catalogue==2.0.10
-Requires-Dist: huggingface_hub>=0.26.0
-Requires-Dist: importlib-metadata>=5.0.0
-Requires-Dist: jsonlines==3.1.0
-Requires-Dist: lazy-imports==0.3.1
-Requires-Dist: mock==4.0.3
-Requires-Dist: networkx>=2.7.1
-Requires-Dist: numpy<2.0,>=1.21
-Requires-Dist: packaging>=20.0
-Requires-Dist: Pillow>=10.0.0
-Requires-Dist: pypdf>=3.16.0
-Requires-Dist: pypdfium2>=4.30.0
-Requires-Dist: pyyaml>=6.0.1
-Requires-Dist: pyzmq>=16
-Requires-Dist: scipy>=1.13.1
-Requires-Dist: termcolor>=1.1
-Requires-Dist: tabulate>=0.7.7
-Requires-Dist: tqdm>=4.64.0
-Provides-Extra: tf
-Requires-Dist: catalogue==2.0.10; extra == "tf"
-Requires-Dist: huggingface_hub>=0.26.0; extra == "tf"
-Requires-Dist: importlib-metadata>=5.0.0; extra == "tf"
-Requires-Dist: jsonlines==3.1.0; extra == "tf"
-Requires-Dist: lazy-imports==0.3.1; extra == "tf"
-Requires-Dist: mock==4.0.3; extra == "tf"
-Requires-Dist: networkx>=2.7.1; extra == "tf"
-Requires-Dist: numpy<2.0,>=1.21; extra == "tf"
-Requires-Dist: packaging>=20.0; extra == "tf"
-Requires-Dist: Pillow>=10.0.0; extra == "tf"
-Requires-Dist: pypdf>=3.16.0; extra == "tf"
-Requires-Dist: pypdfium2>=4.30.0; extra == "tf"
-Requires-Dist: pyyaml>=6.0.1; extra == "tf"
-Requires-Dist: pyzmq>=16; extra == "tf"
-Requires-Dist: scipy>=1.13.1; extra == "tf"
-Requires-Dist: termcolor>=1.1; extra == "tf"
-Requires-Dist: tabulate>=0.7.7; extra == "tf"
-Requires-Dist: tqdm>=4.64.0; extra == "tf"
-Requires-Dist: tensorpack==0.11; extra == "tf"
-Requires-Dist: protobuf==3.20.1; extra == "tf"
-Requires-Dist: tensorflow-addons>=0.17.1; extra == "tf"
-Requires-Dist: tf2onnx>=1.9.2; extra == "tf"
-Requires-Dist: python-doctr==0.9.0; extra == "tf"
-Requires-Dist: pycocotools>=2.0.2; extra == "tf"
-Requires-Dist: boto3==1.34.102; extra == "tf"
-Requires-Dist: pdfplumber>=0.11.0; extra == "tf"
-Requires-Dist: fasttext-wheel; extra == "tf"
-Requires-Dist: jdeskew>=0.2.2; extra == "tf"
-Requires-Dist: apted==1.0.3; extra == "tf"
-Requires-Dist: distance==0.1.3; extra == "tf"
-Requires-Dist: lxml>=4.9.1; extra == "tf"
-Provides-Extra: pt
-Requires-Dist: catalogue==2.0.10; extra == "pt"
-Requires-Dist: huggingface_hub>=0.26.0; extra == "pt"
-Requires-Dist: importlib-metadata>=5.0.0; extra == "pt"
-Requires-Dist: jsonlines==3.1.0; extra == "pt"
-Requires-Dist: lazy-imports==0.3.1; extra == "pt"
-Requires-Dist: mock==4.0.3; extra == "pt"
-Requires-Dist: networkx>=2.7.1; extra == "pt"
-Requires-Dist: numpy<2.0,>=1.21; extra == "pt"
-Requires-Dist: packaging>=20.0; extra == "pt"
-Requires-Dist: Pillow>=10.0.0; extra == "pt"
-Requires-Dist: pypdf>=3.16.0; extra == "pt"
-Requires-Dist: pypdfium2>=4.30.0; extra == "pt"
-Requires-Dist: pyyaml>=6.0.1; extra == "pt"
-Requires-Dist: pyzmq>=16; extra == "pt"
-Requires-Dist: scipy>=1.13.1; extra == "pt"
-Requires-Dist: termcolor>=1.1; extra == "pt"
-Requires-Dist: tabulate>=0.7.7; extra == "pt"
-Requires-Dist: tqdm>=4.64.0; extra == "pt"
-Requires-Dist: timm>=0.9.16; extra == "pt"
-Requires-Dist: transformers>=4.48.0; extra == "pt"
-Requires-Dist: accelerate>=0.29.1; extra == "pt"
-Requires-Dist: python-doctr==0.9.0; extra == "pt"
-Requires-Dist: boto3==1.34.102; extra == "pt"
-Requires-Dist: pdfplumber>=0.11.0; extra == "pt"
-Requires-Dist: fasttext-wheel; extra == "pt"
-Requires-Dist: jdeskew>=0.2.2; extra == "pt"
-Requires-Dist: apted==1.0.3; extra == "pt"
-Requires-Dist: distance==0.1.3; extra == "pt"
-Requires-Dist: lxml>=4.9.1; extra == "pt"
-Provides-Extra: docs
-Requires-Dist: tensorpack==0.11; extra == "docs"
-Requires-Dist: boto3==1.34.102; extra == "docs"
-Requires-Dist: transformers>=4.48.0; extra == "docs"
-Requires-Dist: accelerate>=0.29.1; extra == "docs"
-Requires-Dist: pdfplumber>=0.11.0; extra == "docs"
-Requires-Dist: lxml>=4.9.1; extra == "docs"
-Requires-Dist: lxml-stubs>=0.5.1; extra == "docs"
-Requires-Dist: jdeskew>=0.2.2; extra == "docs"
-Requires-Dist: jinja2==3.0.3; extra == "docs"
-Requires-Dist: mkdocs-material; extra == "docs"
-Requires-Dist: mkdocstrings-python; extra == "docs"
-Requires-Dist: griffe==0.25.0; extra == "docs"
-Provides-Extra: dev
-Requires-Dist: python-dotenv==1.0.0; extra == "dev"
-Requires-Dist: click; extra == "dev"
-Requires-Dist: black==23.7.0; extra == "dev"
-Requires-Dist: isort==5.13.2; extra == "dev"
-Requires-Dist: pylint==2.17.4; extra == "dev"
-Requires-Dist: mypy==1.4.1; extra == "dev"
-Requires-Dist: wandb; extra == "dev"
-Requires-Dist: types-PyYAML>=6.0.12.12; extra == "dev"
-Requires-Dist: types-termcolor>=1.1.3; extra == "dev"
-Requires-Dist: types-tabulate>=0.9.0.3; extra == "dev"
-Requires-Dist: types-tqdm>=4.66.0.5; extra == "dev"
-Requires-Dist: lxml-stubs>=0.5.1; extra == "dev"
-Requires-Dist: types-Pillow>=10.2.0.20240406; extra == "dev"
-Requires-Dist: types-urllib3>=1.26.25.14; extra == "dev"
-Provides-Extra: test
-Requires-Dist: pytest==8.0.2; extra == "test"
-Requires-Dist: pytest-cov; extra == "test"
-Dynamic: author
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license
-Dynamic: license-file
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-
-<p align="center">
-  <img src="https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/dd_logo.png" alt="Deep Doctection Logo" width="60%">
-  <h3 align="center">
-  A Document AI Package
-  </h3>
-</p>
-
-
-**deep**doctection is a Python library that orchestrates document extraction and document layout analysis tasks using deep learning models. It does 
-not implement models but enables you to build pipelines using highly acknowledged libraries for object detection, OCR 
-and selected NLP tasks and provides an integrated framework for fine-tuning, evaluating and running models. For more
- specific text processing tasks use one of the many other great NLP libraries.
-
-**deep**doctection focuses on applications and is made for those who want to solve real world problems related to 
-document extraction from PDFs or scans in various image formats.
-
-Check the demo of a document layout analysis pipeline with OCR on 
-:hugs: [**Hugging Face spaces**](https://huggingface.co/spaces/deepdoctection/deepdoctection).
-
-# Overview
-
-**deep**doctection provides model wrappers of supported libraries for various tasks to be integrated into 
-pipelines. Its core function does not depend on any specific deep learning library. Selected models for the following 
- tasks are currently supported:       
-
- - Document layout analysis including table recognition in Tensorflow with [**Tensorpack**](https://github.com/tensorpack), 
-   or PyTorch with [**Detectron2**](https://github.com/facebookresearch/detectron2/tree/main/detectron2),
- - OCR with support of [**Tesseract**](https://github.com/tesseract-ocr/tesseract), [**DocTr**](https://github.com/mindee/doctr)
-   (Tensorflow and PyTorch implementations available) and a wrapper to an API for a commercial solution, 
- - Text mining for native PDFs with  [**pdfplumber**](https://github.com/jsvine/pdfplumber), 
- - Language detection with [**fastText**](https://github.com/facebookresearch/fastText),
- - Deskewing and rotating images with [**jdeskew**](https://github.com/phamquiluan/jdeskew). 
- - Document and token classification with all LayoutLM models provided by the 
-   [**Transformer library**](https://github.com/huggingface/transformers). 
-   (Yes, you can use any LayoutLM-model with any of the provided OCR-or pdfplumber tools straight away!).
- - Table detection and table structure recognition with 
-   [**table-transformer**](https://github.com/microsoft/table-transformer). 
- - There is a small dataset for token classification [available](https://huggingface.co/datasets/deepdoctection/FRFPE)
-   and a lot of new [tutorials](https://github.com/deepdoctection/notebooks/blob/main/Layoutlm_v2_on_custom_token_classification.ipynb) 
-   to show, how to train and evaluate this dataset using LayoutLMv1, LayoutLMv2, LayoutXLM and LayoutLMv3.
- - Comprehensive configuration of **analyzer** like choosing different models, output parsing, OCR selection.
-   Check this [notebook](https://github.com/deepdoctection/notebooks/blob/main/Analyzer_Configuration.ipynb) or the 
-   [docs](https://deepdoctection.readthedocs.io/en/latest/tutorials/analyzer_configuration_notebook/) for more infos.
- - Document layout analysis and table recognition now runs with 
-   [**Torchscript**](https://pytorch.org/docs/stable/jit.html) (CPU) as well and [**Detectron2**](https://github.com/facebookresearch/detectron2/tree/main/detectron2) is not required 
-   anymore for basic inference.
- - More angle predictors for determining the rotation of a document based on [**Tesseract**](https://github.com/tesseract-ocr/tesseract) and [**DocTr**](https://github.com/mindee/doctr)
- - Token classification with [**LiLT**](https://github.com/jpWang/LiLT) via 
-   [**transformers**](https://github.com/huggingface/transformers). 
-   We have added a model wrapper for token classification with LiLT and added a some LiLT models to the model catalog 
-   that seem to look promising, especially if you want to train a model on non-english data. The training script for 
-   LayoutLM can be used for LiLT as well.
- - [**new**] There are two notebooks available that show, how to write a 
-   [custom predictor](https://github.com/deepdoctection/notebooks/blob/main/Doclaynet_Analyzer_Config.ipynb) based on 
-   a third party library that has not been supported yet and how to use 
-   [advanced configuration](https://github.com/deepdoctection/notebooks/blob/main/Doclaynet_Analyzer_Config.ipynb) to 
-   get links between layout segments e.g. captions and tables or figures.
-
-**deep**doctection provides on top of that methods for pre-processing inputs to models like cropping or resizing and to 
-post-process results, like validating duplicate outputs, relating words to detected layout segments or ordering words 
-into contiguous text. You will get an output in JSON format that you can customize even further by yourself. 
-     
-Have a look at the [**introduction notebook**](https://github.com/deepdoctection/notebooks/blob/main/Get_Started.ipynb) in the 
-[notebook repo](https://github.com/deepdoctection/notebooks) for an easy start.
-
-Check the [**release notes**](https://github.com/deepdoctection/deepdoctection/releases) for recent updates.
-
-## Models    
-
-**deep**doctection or its support libraries provide pre-trained models that are in most of the cases available at the 
-[**Hugging Face Model Hub**](https://huggingface.co/deepdoctection) or that will be automatically downloaded once 
-requested. For instance, you can find pre-trained object detection models from the Tensorpack or Detectron2 framework
- for coarse layout analysis, table cell detection and table recognition. 
-
-## Datasets and training scripts
-
-Training is a substantial part to get pipelines ready on some specific domain, let it be document layout analysis, 
-document classification or NER. **deep**doctection provides training scripts for models that are based on trainers
-developed from the library that hosts the model code. Moreover, **deep**doctection hosts code to some well established 
-datasets like **Publaynet** that makes it easy to experiment. It also contains mappings from widely used data 
-formats like COCO and it has a dataset framework (akin to [**datasets**](https://github.com/huggingface/datasets) so that
- setting up training on a custom dataset becomes very easy. [**This notebook**](https://github.com/deepdoctection/notebooks/blob/main/Datasets_and_Eval.ipynb)
-shows you how to do this.
-   
-## Evaluation
-
-**deep**doctection comes equipped with a framework that allows you to evaluate predictions of a single or multiple 
-models in a pipeline against some ground truth. Check again [**here**](https://github.com/deepdoctection/notebooks/blob/main/Datasets_and_Eval.ipynb) how it is 
-done.  
-
-## Inference
-
-Having set up a pipeline it takes you a few lines of code to instantiate the pipeline and after a for loop all pages will 
-be processed through the pipeline. 
-
-```python
-import deepdoctection as dd
-from IPython.core.display import HTML
-from matplotlib import pyplot as plt
-
-analyzer = dd.get_dd_analyzer()  # instantiate the built-in analyzer similar to the Hugging Face space demo
-
-df = analyzer.analyze(path = "/path/to/your/doc.pdf")  # setting up pipeline
-df.reset_state()                 # Trigger some initialization
-
-doc = iter(df)
-page = next(doc) 
-
-image = page.viz()
-plt.figure(figsize = (25,17))
-plt.axis('off')
-plt.imshow(image)
-```
-
-![text](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/dd_rm_sample.png)
-
-```
-HTML(page.tables[0].html)
-```
-
-![table](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/dd_rm_table.png)
-
-
-```
-print(page.text)
-```
-
-![table](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/dd_rm_text.png)
- 
-
-## Documentation
-
-There is an extensive [**documentation**](https://deepdoctection.readthedocs.io/en/latest/index.html#) available 
-containing tutorials, design concepts and the API. We want to present things as comprehensively and understandably 
-as possible. However, we are aware that there are still many areas where significant improvements can be made in terms 
-of clarity, grammar and correctness. We look forward to every hint and comment that increases the quality of the 
-documentation.
-
-
-## Requirements
-
-![requirements](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/requirements_deepdoctection_081124.png)
-
-Everything in the overview listed below the **deep**doctection layer are necessary requirements and have to be installed 
-separately. 
-
-- Linux or macOS. (Windows is not supported but there is a [Dockerfile](./docker/pytorch-cpu-jupyter/Dockerfile) available)
-- Python >= 3.9
-- 1.13 <= PyTorch  **or** 2.11 <= Tensorflow < 2.16. (For lower Tensorflow versions the code will only run on a GPU).
-In general, if you want to train or fine-tune models, a GPU is required.
-
-- With respect to the Deep Learning framework, you must decide between [Tensorflow](https://www.tensorflow.org/install?hl=en)
-  and [PyTorch](https://pytorch.org/get-started/locally/).
-- [Tesseract](https://github.com/tesseract-ocr/tesseract) OCR engine will be used through a Python wrapper. The core 
-  engine has to be installed separately.
-
-
-- For release `v.0.34.0` and below **deep**doctection uses Python wrappers for [Poppler](https://poppler.freedesktop.org/) to convert PDF
-  documents into images. For release `v.0.35.0` this dependency will be optional.
-
-The following overview shows the availability of the models in conjunction with the DL framework.
-
-| Task                                          | PyTorch | Torchscript    |  Tensorflow  |
-|-----------------------------------------------|:-------:|----------------|:------------:|
-| Layout detection via Detectron2/Tensorpack    |    ✅    | ✅ (CPU only)   | ✅ (GPU only) |
-| Table recognition via Detectron2/Tensorpack   |    ✅    | ✅ (CPU only)   | ✅ (GPU only) |
-| Table transformer via Transformers            |    ✅    | ❌              |      ❌       |
-| DocTr                                         |    ✅    | ❌              |      ✅       |
-| LayoutLM (v1, v2, v3, XLM) via Transformers   |    ✅    | ❌              | ❌            |
-
-
-
-## Installation
-
-We recommend using a virtual environment. You can install the package via pip or from source. 
-
-### Install with pip from PyPi
-
-#### Minimal installation 
-
-If you want to get started with a minimal setting (e.g. running the **deep**doctection analyzer with 
-default configuration or trying the 'Get started notebook'), install **deep**doctection with
-
-```
-pip install deepdoctection
-```
-
-If you want to use the Tensorflow framework, please install Tensorpack separately. Detectron2 will not be installed 
-and layout models/ table recognition models will run with Torchscript on a CPU.
-
-#### Full installation
-
-The following installation will give you ALL models available within the Deep Learning framework as well as all models
-that are independent of Tensorflow/PyTorch. Please note, that the dependencies are very complex. We try hard to keep 
-the requirements up to date though.
-
-For **Tensorflow**, run
-
-```
-pip install deepdoctection[tf]
-```
-
-For **PyTorch**, 
-
-first install **Detectron2** separately as it is not distributed via PyPi. Check the instruction 
-[here](https://detectron2.readthedocs.io/en/latest/tutorials/install.html). Then run
-
-```
-pip install deepdoctection[pt]
-```
-
-This will install **deep**doctection with all dependencies listed above the **deep**doctection layer. Use this setting, 
-if you want to get started or want to explore all features. 
-
-If you want to have more control with your installation and are looking for fewer dependencies then 
-install **deep**doctection with the basic setup only.
-
-```
-pip install deepdoctection
-```
-
-This will ignore all model libraries (layers above the **deep**doctection layer in the diagram) and you 
-will be responsible to install them by yourself. Note, that you will not be able to run any pipeline with this setup.
-
-For further information, please consult the [**full installation instructions**](https://deepdoctection.readthedocs.io/en/latest/install/).
-
-
-### Installation from source
-
-Download the repository or clone via
-
-```
-git clone https://github.com/deepdoctection/deepdoctection.git
-```
-
-To get started with **Tensorflow**, run:
-
-```
-cd deepdoctection
-pip install ".[tf]"
-```
-
-Installing the full **PyTorch** setup from source will also install **Detectron2** for you:
- 
-```
-cd deepdoctection
-pip install ".[source-pt]"
-```
-
-### Running a Docker container from Docker hub
-
-Starting from release `v.0.27.0`, pre-existing Docker images can be downloaded from the 
-[Docker hub](https://hub.docker.com/r/deepdoctection/deepdoctection).
-
-```
-docker pull deepdoctection/deepdoctection:<release_tag> 
-```
-
-To start the container, you can use the Docker compose file `./docker/pytorch-gpu/docker-compose.yaml`. 
-In the `.env` file provided, specify the host directory where **deep**doctection's cache should be stored. 
-This directory will be mounted. Additionally, specify a working directory to mount files to be processed into the 
-container.
-
-```
-docker compose up -d
-```
-
-will start the container.
-
-## Credits
-
-We thank all libraries that provide high quality code and pre-trained models. Without, it would have been impossible 
-to develop this framework.
-
-## Problems
-
-We try hard to eliminate bugs. We also know that the code is not free of issues. We welcome all issues relevant to this
-repo and try to address them as quickly as possible. Bug fixes or enhancements will be deployed in a new release every 10 
-to 12 weeks.
-
-## If you like **deep**doctection ...
- 
- ...you can easily support the project by making it more visible. Leaving a star or a recommendation will help. 
-
-
-## License
-
-Distributed under the Apache 2.0 License. Check [LICENSE](https://github.com/deepdoctection/deepdoctection/blob/master/LICENSE) 
-for additional information.

deepdoctection-0.42.1.dist-info/RECORD

@@ -1,148 +0,0 @@
-deepdoctection/__init__.py,sha256=rNPP6I2lwOt7lHvcnYd1UJq9oNzYMcH9Zsd8sbs9iaQ,12882
-deepdoctection/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-deepdoctection/analyzer/__init__.py,sha256=icClxrd20XutD6LxLgEPIWceSs4j_QfI3szCE-9BL2w,729
-deepdoctection/analyzer/_config.py,sha256=nJoTP4OZEKFxdNcMqJZFE3xCbtTGZ0w8V5nW1BCMBVQ,5124
-deepdoctection/analyzer/dd.py,sha256=Mnt3cwRWNSlQ8Vf2_fgRC30aU2J39QjYJWQSU22JiRY,6255
-deepdoctection/analyzer/factory.py,sha256=py6e2NlKG8-LYzw8k8dgvfp9o1VOuy-OMRDQelKWI9o,34520
-deepdoctection/configs/__init__.py,sha256=TX_P6tqDOF1LK1mi9ruAl7x0mtv1Asm8cYWCz3Pe2dk,646
-deepdoctection/configs/conf_dd_one.yaml,sha256=qnrDAST1PHBtdIKE_hdkZexW22FqVvNTI-PEo9wvinM,3025
-deepdoctection/configs/conf_tesseract.yaml,sha256=oF6szDyoi15FHvq7yFUNIEjfA_jNLhGxoowiRsz_zY4,35
-deepdoctection/dataflow/__init__.py,sha256=CWRHMpmJaPk4xY_oIIFubCt-z11SguWrMWxHZ7rdrvY,845
-deepdoctection/dataflow/base.py,sha256=z4DCComSj5wStEPjtk0093cNNGfUMiDqx8dqz36nS_o,6221
-deepdoctection/dataflow/common.py,sha256=MyGA2VWlNMjQdIN_Jd-o0Ec3bDJmjQit4Nv0v43OCSQ,10119
-deepdoctection/dataflow/custom.py,sha256=3CK_1oL9p6nbOq8WtH5_vQUo70_8Z8pXY7kG0OFqzug,6803
-deepdoctection/dataflow/custom_serialize.py,sha256=WocuiYo2gkih5Z9lWAoIIfUewwYSDOhHzG7ZZjKlUic,22827
-deepdoctection/dataflow/parallel_map.py,sha256=8FhxJBWV-kjJrJ27jQtP3yYF6Ev6rz98worO60oi96c,15837
-deepdoctection/dataflow/serialize.py,sha256=4pYC7m9h53JCu99waVeKpHDpsCDDdYCrSZpP2QYSsgs,4555
-deepdoctection/dataflow/stats.py,sha256=Bsr6v7lcesKXUYtO9wjqlzx_Yq_uyIF3Lel-tQ0i4wI,9619
-deepdoctection/datapoint/__init__.py,sha256=3K406GbOPhoEp8koVaSbMocmSsmWifnSZ1SPb7C1lOY,1643
-deepdoctection/datapoint/annotation.py,sha256=FEgz4COxVDfjic0gG7kS6iHnWLBIgFnquQ63Cbj2a4Y,22531
-deepdoctection/datapoint/box.py,sha256=XPhC_xHqLZJjzafg1pIS_CxnVB5-0_yk-twsZZ3ncUU,30093
-deepdoctection/datapoint/convert.py,sha256=h3ky-Qn6YA8Qoyy5SMUkjJq___cK0hbcwFygDyqqm-4,7123
-deepdoctection/datapoint/image.py,sha256=_jN46UJUsOi6GC6VEUcp3L_vLL-iYRW05RKcFLWb6Dc,34048
-deepdoctection/datapoint/view.py,sha256=Gj47_nlIVoaDvTtypQHzxHLJLXN2uxOhhVRHERDQJlE,52135
-deepdoctection/datasets/__init__.py,sha256=-A3aR90aDsHPmVM35JavfnQ2itYSCn3ujl4krRni1QU,1076
-deepdoctection/datasets/adapter.py,sha256=Ly_vbOAgVI73V41FUccnSX1ECTOyesW_qsuvQuvOZbw,7796
-deepdoctection/datasets/base.py,sha256=X5Sr0yyal9x8rqWaWYr5mA_bE11UzN1iFXmWu605q2Y,22713
-deepdoctection/datasets/dataflow_builder.py,sha256=cYU2zV3gZW2bFvMHimlO9VIl3BAUaCwML08cCIQ8Em4,4107
-deepdoctection/datasets/info.py,sha256=sC1QCOdLWFMooVmiShZ43sLUpAi3FK4d0fsLyl_9-gA,20548
-deepdoctection/datasets/registry.py,sha256=utiB-PnE6vc5HvjcudO0O4Urp2BC3snqswY6d8uPQAo,3388
-deepdoctection/datasets/save.py,sha256=Y9508Qqp8gIGN7pbGgVBBnkiC6NdCb9L2YR4wVvEUxM,3350
-deepdoctection/datasets/instances/__init__.py,sha256=XEc_4vT5lDn6bbZID9ujDEumWu8Ec2W-QS4pI_bfWWE,1388
-deepdoctection/datasets/instances/doclaynet.py,sha256=Az7USCqF0lMk1n1Dk59uUrBgBNAbKEjtUvZnCgdUH70,12286
-deepdoctection/datasets/instances/fintabnet.py,sha256=rOaKD5bruokkbZwjRhEz-5uAKZiMAXzmre_Ecc0YMTk,12250
-deepdoctection/datasets/instances/funsd.py,sha256=K6WQQOaEJrw1TcevScHET-AY9l9aj64dhLRyZ1J86p0,7183
-deepdoctection/datasets/instances/iiitar13k.py,sha256=HGBqR_PeTqpzLV9npWh5VdlHUg0t8vUTcrm3Z2kL6Qk,6923
-deepdoctection/datasets/instances/layouttest.py,sha256=nNYDUNcgWA0PilN0w0vAourwXvpcRupVStvlESTc1e0,4515
-deepdoctection/datasets/instances/publaynet.py,sha256=jUKq9iYW0qD5qXMe2xFz8xNxsL0KBTufuwSMkfzwaxA,5447
-deepdoctection/datasets/instances/pubtables1m.py,sha256=KtEHh8G98e-RjIqRbe5fbLNrD52oWA9kKDb3sUPqAk0,12524
-deepdoctection/datasets/instances/pubtabnet.py,sha256=TidllHJdxM8Ii0_gjliLWOWTtTaKjl89Khe1o0jLW4M,8806
-deepdoctection/datasets/instances/rvlcdip.py,sha256=8Vb_iCuR85N8Mx7d5KJ-lXe6PiZPjG0Jfq6EwY1qtkw,6831
-deepdoctection/datasets/instances/xfund.py,sha256=effTZfWI8MvGXCyRhdtwphHCr7WNF8sQOOjUCcKaTVE,9002
-deepdoctection/datasets/instances/xsl/__init__.py,sha256=TX_P6tqDOF1LK1mi9ruAl7x0mtv1Asm8cYWCz3Pe2dk,646
-deepdoctection/datasets/instances/xsl/pascal_voc.xsl,sha256=DlzFV2P8NtQKXVe96i-mIcPWmL6tsW7NQjgCuz2pCL4,1952
-deepdoctection/eval/__init__.py,sha256=rbns4tSEQ30QLj8h0mm3A0dCaKuN9LDxxpVypKKSXSE,932
-deepdoctection/eval/accmetric.py,sha256=4bND-xz9AZu9ACYRkEzn9V6Jn8MEiqnF7kxSp4k_baE,19655
-deepdoctection/eval/base.py,sha256=gCvhTdwEaCKplYTWPMjGvtB_0Vbq2KBJWFHq8mMlLPA,4814
-deepdoctection/eval/cocometric.py,sha256=4cpNmF3xZjInCOWOoVU_7itQxLI-zr0O6suNjPU2xWc,11020
-deepdoctection/eval/eval.py,sha256=B9PUZBjj6KzXHLOxUVn3QHiOcBQogfJmp9mjopbMo9k,19721
-deepdoctection/eval/registry.py,sha256=v4mp-s67vBVRu1nQzuGlYPViQnMSeIXEcF_WmvfUCoU,1051
-deepdoctection/eval/tedsmetric.py,sha256=rKw-734Y9CpBtIfkBSPQF2vAZxnIdWrI9Zc723P7RxI,9529
-deepdoctection/eval/tp_eval_callback.py,sha256=SXsXumoyxq-MIH9Cep5eUOwnNshMbKmC6mYOGwCg0pM,5283
-deepdoctection/extern/__init__.py,sha256=9Iks9b4Q_LynjcV167TVCoK8YsQRUcA2jjmAmDNA_X8,1056
-deepdoctection/extern/base.py,sha256=oRuoAduVchsR3H7Ddm-KAe_smt0N6PlQftPqJ75FWfA,28944
-deepdoctection/extern/d2detect.py,sha256=zrKv1yurApnjD7QZIZk_8LYCahjmN82MQUjHjv8zvkQ,22127
-deepdoctection/extern/deskew.py,sha256=iax1ztkguGDfD4KQMDyuvanR4J2VgpCRuVWWDTwViu4,3083
-deepdoctection/extern/doctrocr.py,sha256=htlFswrdRncEqC3PKjzXIifEu4ua3i09CNtrfEnlgBg,24723
-deepdoctection/extern/fastlang.py,sha256=F4gK-SEwcCujjxH327ZDzMGWToJ49xS_dCKcePQ9IlY,4780
-deepdoctection/extern/hfdetr.py,sha256=JzHrrTyzS9qh6T2TsvKboAGZkIhno2txmSoLQ5Vd-lo,12077
-deepdoctection/extern/hflayoutlm.py,sha256=tFaf90FRbZzhSycdp8rGkeiPywQa6UcTEEwbayIXkr0,57023
-deepdoctection/extern/hflm.py,sha256=kwS6kcSlY_2m9u0RzBLTRq-UMM7c1PhyUaDTvSdejus,9217
-deepdoctection/extern/model.py,sha256=lbVwDa3vD6VwCD_dsozcI8b4xDZs4KJ1628SxaDdtHQ,55378
-deepdoctection/extern/pdftext.py,sha256=KS_t27SUiYn_IOS_J2lF9lSSo22vLagxmxvYCY3CqXA,7228
-deepdoctection/extern/tessocr.py,sha256=gRYJsk0jBRMG_ZLXbuJeRYPSPuVjXNwThs4op1hHpoA,17450
-deepdoctection/extern/texocr.py,sha256=yMt5ZzKtsjd7ogrcNXba7zccGGGF9LXK194EtER6YNQ,5804
-deepdoctection/extern/tpdetect.py,sha256=yAk1duQdoX-_pHLHgvhU7OOSiDy863q6XUMpjpYR734,8477
-deepdoctection/extern/pt/__init__.py,sha256=3Cu0ZHjbYsJomru7-RQXEHihEQLegZrmLetlHiqS58I,742
-deepdoctection/extern/pt/nms.py,sha256=Zr1rwWSnMKg2Ukq1N4i9C-ey-9bS5TlfJ9YTL8d1RwA,1573
-deepdoctection/extern/pt/ptutils.py,sha256=AerrFR8nCN6-RrTbSqZhH3Q2Cn-WcC5RnE5XO9Pl1IM,1994
-deepdoctection/extern/tp/__init__.py,sha256=8QMkcA7tChCr1QXiA0551lZS2jTsECBrrL2YUanpFAk,706
-deepdoctection/extern/tp/tfutils.py,sha256=U586EuPGDLSuO6hbDrCHKshYoGmuV9WPP1jZjmQW9uw,3553
-deepdoctection/extern/tp/tpcompat.py,sha256=rPW_JrYtz9PbV20dZiMKm6DTrjS1A3rAdhrh8PG9BuM,5461
-deepdoctection/extern/tp/tpfrcnn/__init__.py,sha256=OzDaR5A8HGz9a4VwjLiR9rN1Nf1cSebv8DVEMxStFOw,703
-deepdoctection/extern/tp/tpfrcnn/common.py,sha256=fCxwi2u752ZlI_DtIkLC_x9j9tyo1nnirAi2PmnziD4,3830
-deepdoctection/extern/tp/tpfrcnn/predict.py,sha256=957dnhCByS-FZH13efFWADhodaV4lKto-ikLPetfvEQ,4338
-deepdoctection/extern/tp/tpfrcnn/preproc.py,sha256=oHN9keBurjdNQqXmsb5BgURB5nl-eEp0KHvO1DPRQL4,12009
-deepdoctection/extern/tp/tpfrcnn/config/__init__.py,sha256=RhJiXId6vUSw_Pi49SPwj0jrf61VxxptXoGeBKtT42M,705
-deepdoctection/extern/tp/tpfrcnn/config/config.py,sha256=-T8AwNAIPR-_5OL1oEqm-Qe9GbN6JjAPVUuUw_XfMVc,11405
-deepdoctection/extern/tp/tpfrcnn/modeling/__init__.py,sha256=RhJiXId6vUSw_Pi49SPwj0jrf61VxxptXoGeBKtT42M,705
-deepdoctection/extern/tp/tpfrcnn/modeling/backbone.py,sha256=H7xoWhRwCh-vlHAL5hCEolKBJ8Y2xe9duZuBuLs0ZwQ,9835
-deepdoctection/extern/tp/tpfrcnn/modeling/generalized_rcnn.py,sha256=4jgWyja-_V44zJVfK4ySmknhnhqfb9f6ruVwbh387aE,13752
-deepdoctection/extern/tp/tpfrcnn/modeling/model_box.py,sha256=UvZ8_34dNjCvxsTxCJvrlpqUpQb9gWxgwRoIKgedIog,7361
-deepdoctection/extern/tp/tpfrcnn/modeling/model_cascade.py,sha256=plovKReX6rFjnL_ravLUUCZ49ZFni87FlRJGK0fXqco,5777
-deepdoctection/extern/tp/tpfrcnn/modeling/model_fpn.py,sha256=Ejd0Z2uUrdAfRjXQoS-lBVPukLlw8geP0yXcF61-nk4,11486
-deepdoctection/extern/tp/tpfrcnn/modeling/model_frcnn.py,sha256=KsL08NNy4PEvBu53HV6bMio58oqIfVrcoqpti27pZOI,18166
-deepdoctection/extern/tp/tpfrcnn/modeling/model_mrcnn.py,sha256=B-rImWGWLNNe4UPJfhTpi4f1LUMCW8YJAbwoJFiG__o,4966
-deepdoctection/extern/tp/tpfrcnn/modeling/model_rpn.py,sha256=F7NGrvKyPZRxnl96zoFyezNzymFJvQghMjGslsc7iFg,9028
-deepdoctection/extern/tp/tpfrcnn/utils/__init__.py,sha256=kiPlXxHlTGN9eI7YE9BgwteOQ_nCYCuqqSLO5JfkCTQ,695
-deepdoctection/extern/tp/tpfrcnn/utils/box_ops.py,sha256=aBLqPg_ApaiimtBRaOsLKTZZFIBh87vVtqjLPMaX9fQ,2379
-deepdoctection/extern/tp/tpfrcnn/utils/np_box_ops.py,sha256=O-q1GQiOEd1lN1MQDsJvHwD2OmBO-qHNeqJ1Qnec93g,3539
-deepdoctection/mapper/__init__.py,sha256=Xqb34aCjslZDQnqQgCSvnloL5DbdT9eHhn-StpVPbzE,1130
-deepdoctection/mapper/cats.py,sha256=O06WGkpOIlSNMCy5VESl2HYOFDTuT9ls4aZIaWUv9VU,16602
-deepdoctection/mapper/cocostruct.py,sha256=GcbUpPFUg67pcOHQluWBFOFcGaYnlZcTmwBDERBVgCA,5978
-deepdoctection/mapper/d2struct.py,sha256=CPmjBIqGpBUEh-4hcLbHXQQPHIMTyNvcp9B5miCqZd0,11019
-deepdoctection/mapper/hfstruct.py,sha256=2PjGKsYturVJBimLT1CahYh09KSRAFEHz_QNtC162kQ,5551
-deepdoctection/mapper/laylmstruct.py,sha256=Es_aQOsfCkereJLOd1yaXhNAEEFJkODRuThUJ-d6hHU,42904
-deepdoctection/mapper/maputils.py,sha256=eI6ZcDg9W5uB6xQNBZpMIdEd86HlCxTtkJuyROdTqiw,8146
-deepdoctection/mapper/match.py,sha256=TBc2yAWdQbM3sS64TerOJZwhPPMxk9cmfSXctKdwIU8,10269
-deepdoctection/mapper/misc.py,sha256=vX-fV420Te00eD-cqTiWBV2twHqdBcBV2_7rAFRgPRg,7164
-deepdoctection/mapper/pascalstruct.py,sha256=TzVU1p0oiw0nOuxTFFbEB9vXJxH1v6VUvTJ7MD0manU,3828
-deepdoctection/mapper/prodigystruct.py,sha256=Re4Sd_zAp6qOvbXZLmMJeG0IGEfMQxebuyDeZgMcTa8,6827
-deepdoctection/mapper/pubstruct.py,sha256=PAJ2N1HSPNS6F2ZrIwlD7PiBhIM-rJscK_Ti8OR_IGs,23370
-deepdoctection/mapper/tpstruct.py,sha256=W8-K3DKM9U0LwsmAMqtEqpfol1F1t5rNXh2595GCPTk,5251
-deepdoctection/mapper/xfundstruct.py,sha256=_3r3c0K82fnF2h1HxA85h-9ETYrHwcERa6MNc6Ko6Z8,8807
-deepdoctection/pipe/__init__.py,sha256=ywTVoetftdL6plXg2YlBzMfmqBZupq7yXblSVyvvkcQ,1127
-deepdoctection/pipe/anngen.py,sha256=7wvp7eghDwrgcIyu1vjRxmVy4SADPbn-k4ud8y2bgjU,15338
-deepdoctection/pipe/base.py,sha256=wlza9aDOKnHKrXmaz8MLyLz0nMqqcIWQ-6Lu944aicE,15390
-deepdoctection/pipe/common.py,sha256=qnNa9ZzDJgMx62rlQ0bx_rtfhrHeLCK29swtSZjei3o,23058
-deepdoctection/pipe/concurrency.py,sha256=AAKRsVgaBEYNluntbDa46SBF1JZ_XqnWLDSWrNvAzEo,9657
-deepdoctection/pipe/doctectionpipe.py,sha256=bGW3ugky-fb-nEe-3bvO6Oc_4_6w82cQboGM_6p2eIo,12530
-deepdoctection/pipe/language.py,sha256=5zI0UQC6Fh12_r2pfVL42HoCGz2hpHrOhpXAn5m-rYw,5451
-deepdoctection/pipe/layout.py,sha256=ThULc0b1f9KyaXYk9z0qbuJ0nhIodah9PcrEq2xKpAY,5670
-deepdoctection/pipe/lm.py,sha256=x9NoYpivdjQF1r76a7PPrUuBEmuHP7ZukuXFDkXhXBc,17572
-deepdoctection/pipe/order.py,sha256=0KNiMinedjfuDVVHxJSaDL1yl4Sub-miMPcEC4gGwPA,39423
-deepdoctection/pipe/refine.py,sha256=dTfI396xydPdbzpfo4yqFcuxl3UAB1y-WbSQn1o76ec,22367
-deepdoctection/pipe/registry.py,sha256=aFx-Tn0xhVA5l5H18duNW5QoTNKQltybsEUEzsMgUfg,902
-deepdoctection/pipe/segment.py,sha256=lR_aCY7yJm0GCygLPRVQBv_WgWvCNgG9F_B-37qrbMU,59846
-deepdoctection/pipe/sub_layout.py,sha256=D73H5b2Zl35fN58TaY0_nGhwI9Nwj3wqDdDPz8ce9Fg,13538
-deepdoctection/pipe/text.py,sha256=tLlJtneM__WsrAvp4pQFqwNlmq2RLqKqiPXlJ2lkniU,10483
-deepdoctection/pipe/transform.py,sha256=eCSRbyxHLz11owOHFA9UDX7tOJPZG2eiPWIGJv2odbk,4890
-deepdoctection/train/__init__.py,sha256=YFTRAZF1F7cEAKTdAIi1BLyYb6rSRcwq09Ui5Lu8d6E,1071
-deepdoctection/train/d2_frcnn_train.py,sha256=sFc_G-mEpaM8d1CCE0_6Gl4nBh11X2RYRBA3p_ylFJQ,16000
-deepdoctection/train/hf_detr_train.py,sha256=cFZdV0XEYsReMBCrIYZsNFT6E2OBpp6vb1FJAE-qGRs,12073
-deepdoctection/train/hf_layoutlm_train.py,sha256=8kiGp_8GEyqCkLgeMgCJOLJWSVoKWkUBHsZtDjZOcRk,22556
-deepdoctection/train/tp_frcnn_train.py,sha256=pEpXokSVGveqo82pRnhnAmHPmjQ_8wQWpqM4ZyNHJgs,13049
-deepdoctection/utils/__init__.py,sha256=brBceRWeov9WXMiJTjyJOF2rHMP8trGGRRjhMdZ61nI,2371
-deepdoctection/utils/concurrency.py,sha256=nIhpkSncmv0LBB8PtcOLY-BsRGlfcDpz7foVdgzZd20,4598
-deepdoctection/utils/context.py,sha256=VSnJnTtRGuq3w-0-syTf9DXOhR7WsPvWLLWTxKIBYec,4186
-deepdoctection/utils/develop.py,sha256=4HyTarkFbJwctL-Hgu1TU_LSJppHvaroDbcyHsxhIA8,3444
-deepdoctection/utils/env_info.py,sha256=TnCA-LOTj4WIHd9yvn1AaoPWsLmPgc42l-BJmGV6zmM,19147
-deepdoctection/utils/error.py,sha256=_3q9VepKfEhsM3H033_Fu0hwBzMSjsWALsjyJbGAZr8,2367
-deepdoctection/utils/file_utils.py,sha256=IRElrcND0YEiU1QELw5hfXeNA39uE2_nyzh9-X7YcxI,19477
-deepdoctection/utils/fs.py,sha256=x842BxUP5bbjJ2cofw-g4dKJv4QAaGzda4qnAazabO4,10281
-deepdoctection/utils/identifier.py,sha256=QkNaGGqPynHwDPnd3_m8iur4Cv64rcQa7qolCE7Qphk,2159
-deepdoctection/utils/logger.py,sha256=J0OVKiXP_2A82MWbbJoOeMEJ-75aZu5npgaS_yI6mVA,10003
-deepdoctection/utils/metacfg.py,sha256=hD76KQ_RnD_5B02qLI2Zxf3WfnsnXhEI_KUTKpw91RI,5711
-deepdoctection/utils/mocks.py,sha256=IkN3-IzAl4eX0ibgKIHg8IY7ykVw6BnpF6XnxKnKaZI,2389
-deepdoctection/utils/pdf_utils.py,sha256=Fi0eZ2GbnO7N61Rd8b8YRKRff4dalHAzkcn3zpGPoic,13119
-deepdoctection/utils/settings.py,sha256=nmA7aqzHTMrAhodNbPjr-afLRt2EWjpx8ipQeE-bqqs,12590
-deepdoctection/utils/tqdm.py,sha256=cBUtR0L1x0KMeYrLP2rrzyzCamCjpQAKroHXLv81_pk,1820
-deepdoctection/utils/transform.py,sha256=5mY5D6hhk6cKFp0T1LJ2_jMjjBxJopcFZffAN5PKvFU,13699
-deepdoctection/utils/types.py,sha256=ti4WdtIJSg3TGK_YPkkoY9PYGMnR2tTX6Xfik8U1pNk,2986
-deepdoctection/utils/utils.py,sha256=csVs_VvCq4QBETPoE2JdTTL4MFYnD4xh-Js5vRb612g,6492
-deepdoctection/utils/viz.py,sha256=Jf8ePNYWlpuyaS6SeTYQ4OyA3eNhtgjvAQZnGNdgHC0,27051
-deepdoctection-0.42.1.dist-info/licenses/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
-deepdoctection-0.42.1.dist-info/METADATA,sha256=ckwg7bNCfNi-IPFAnYURuZULlHgrf2SfikingNB8ztM,19763
-deepdoctection-0.42.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-deepdoctection-0.42.1.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
-deepdoctection-0.42.1.dist-info/RECORD,,