python-doctr 0.7.0__tar.gz → 0.8.1__tar.gz

{python-doctr-0.7.0/python_doctr.egg-info → python-doctr-0.8.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-doctr
-Version: 0.7.0
+Version: 0.8.1
 Summary: Document Text Recognition (docTR): deep Learning for high-performance OCR on documents.
 Author-email: Mindee <contact@mindee.com>
 Maintainer: François-Guillaume Fernandez, Charles Gaillard, Olivier Dulcy, Felix Dittrich
@@ -209,7 +209,7 @@ License:                                  Apache License
 Project-URL: documentation, https://mindee.github.io/doctr
 Project-URL: repository, https://github.com/mindee/doctr
 Project-URL: tracker, https://github.com/mindee/doctr/issues
-Project-URL: changelog, https://github.com/mindee/doctr/latest/changelog.html
+Project-URL: changelog, https://mindee.github.io/doctr/changelog.html
 Keywords: OCR,deep learning,computer vision,tensorflow,pytorch,text detection,text recognition
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
@@ -236,17 +236,17 @@ Requires-Dist: pyclipper<2.0.0,>=1.2.0
 Requires-Dist: shapely<3.0.0,>=1.6.0
 Requires-Dist: langdetect<2.0.0,>=1.0.9
 Requires-Dist: rapidfuzz<4.0.0,>=3.0.0
+Requires-Dist: huggingface-hub<1.0.0,>=0.20.0
 Requires-Dist: matplotlib>=3.1.0
 Requires-Dist: weasyprint>=55.0
-Requires-Dist: Pillow>=10.0.0
+Requires-Dist: Pillow>=9.2.0
 Requires-Dist: defusedxml>=0.7.0
 Requires-Dist: mplcursors>=0.3
 Requires-Dist: unidecode>=1.0.0
 Requires-Dist: tqdm>=4.30.0
-Requires-Dist: huggingface-hub>=0.5.0
 Provides-Extra: tf
-Requires-Dist: tensorflow<3.0.0,>=2.11.0; extra == "tf"
-Requires-Dist: tf2onnx<2.0.0,>=1.15.1; extra == "tf"
+Requires-Dist: tensorflow<2.16.0,>=2.11.0; extra == "tf"
+Requires-Dist: tf2onnx<2.0.0,>=1.16.0; extra == "tf"
 Provides-Extra: torch
 Requires-Dist: torch<3.0.0,>=1.12.0; extra == "torch"
 Requires-Dist: torchvision>=0.13.0; extra == "torch"
@@ -259,11 +259,8 @@ Requires-Dist: onnxruntime>=1.11.0; extra == "testing"
 Requires-Dist: requests>=2.20.0; extra == "testing"
 Requires-Dist: psutil>=5.9.5; extra == "testing"
 Provides-Extra: quality
-Requires-Dist: ruff>=0.0.260; extra == "quality"
-Requires-Dist: isort>=5.7.0; extra == "quality"
-Requires-Dist: black>=22.1; extra == "quality"
+Requires-Dist: ruff>=0.1.5; extra == "quality"
 Requires-Dist: mypy>=0.812; extra == "quality"
-Requires-Dist: pydocstyle[toml]>=6.1.1; extra == "quality"
 Requires-Dist: pre-commit>=2.17.0; extra == "quality"
 Provides-Extra: docs
 Requires-Dist: sphinx!=3.5.0,>=3.0.0; extra == "docs"
@@ -275,8 +272,8 @@ Requires-Dist: sphinx-markdown-tables>=0.0.15; extra == "docs"
 Requires-Dist: sphinx-tabs>=3.3.0; extra == "docs"
 Requires-Dist: furo>=2022.3.4; extra == "docs"
 Provides-Extra: dev
-Requires-Dist: tensorflow<3.0.0,>=2.11.0; extra == "dev"
-Requires-Dist: tf2onnx<2.0.0,>=1.15.1; extra == "dev"
+Requires-Dist: tensorflow<2.16.0,>=2.11.0; extra == "dev"
+Requires-Dist: tf2onnx<2.0.0,>=1.16.0; extra == "dev"
 Requires-Dist: torch<3.0.0,>=1.12.0; extra == "dev"
 Requires-Dist: torchvision>=0.13.0; extra == "dev"
 Requires-Dist: onnx<3.0.0,>=1.12.0; extra == "dev"
@@ -286,11 +283,8 @@ Requires-Dist: hdf5storage>=0.1.18; extra == "dev"
 Requires-Dist: onnxruntime>=1.11.0; extra == "dev"
 Requires-Dist: requests>=2.20.0; extra == "dev"
 Requires-Dist: psutil>=5.9.5; extra == "dev"
-Requires-Dist: ruff>=0.0.260; extra == "dev"
-Requires-Dist: isort>=5.7.0; extra == "dev"
-Requires-Dist: black>=22.1; extra == "dev"
+Requires-Dist: ruff>=0.1.5; extra == "dev"
 Requires-Dist: mypy>=0.812; extra == "dev"
-Requires-Dist: pydocstyle[toml]>=6.1.1; extra == "dev"
 Requires-Dist: pre-commit>=2.17.0; extra == "dev"
 Requires-Dist: sphinx!=3.5.0,>=3.0.0; extra == "dev"
 Requires-Dist: sphinxemoji>=0.1.8; extra == "dev"
@@ -302,10 +296,11 @@ Requires-Dist: sphinx-tabs>=3.3.0; extra == "dev"
 Requires-Dist: furo>=2022.3.4; extra == "dev"
 
 <p align="center">
-  <img src="https://github.com/mindee/doctr/releases/download/v0.3.1/Logo_doctr.gif?raw=True" width="40%">
+  <img src="https://github.com/mindee/doctr/raw/main/docs/images/Logo_doctr.gif" width="40%">
 </p>
 
-[![Slack Icon](https://img.shields.io/badge/Slack-Community-4A154B?style=flat-square&logo=slack&logoColor=white)](https://slack.mindee.com) [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) ![Build Status](https://github.com/mindee/doctr/workflows/builds/badge.svg) [![codecov](https://codecov.io/gh/mindee/doctr/branch/main/graph/badge.svg?token=577MO567NM)](https://codecov.io/gh/mindee/doctr) [![CodeFactor](https://www.codefactor.io/repository/github/mindee/doctr/badge?s=bae07db86bb079ce9d6542315b8c6e70fa708a7e)](https://www.codefactor.io/repository/github/mindee/doctr) [![Codacy Badge](https://api.codacy.com/project/badge/Grade/340a76749b634586a498e1c0ab998f08)](https://app.codacy.com/gh/mindee/doctr?utm_source=github.com&utm_medium=referral&utm_content=mindee/doctr&utm_campaign=Badge_Grade) [![Doc Status](https://github.com/mindee/doctr/workflows/doc-status/badge.svg)](https://mindee.github.io/doctr) [![Pypi](https://img.shields.io/badge/pypi-v0.6.0-blue.svg)](https://pypi.org/project/python-doctr/) [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/mindee/doctr) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mindee/notebooks/blob/main/doctr/quicktour.ipynb)
+[![Slack Icon](https://img.shields.io/badge/Slack-Community-4A154B?style=flat-square&logo=slack&logoColor=white)](https://slack.mindee.com) [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) ![Build Status](https://github.com/mindee/doctr/workflows/builds/badge.svg) [![Docker Images](https://img.shields.io/badge/Docker-4287f5?style=flat&logo=docker&logoColor=white)](https://github.com/mindee/doctr/pkgs/container/doctr) [![codecov](https://codecov.io/gh/mindee/doctr/branch/main/graph/badge.svg?token=577MO567NM)](https://codecov.io/gh/mindee/doctr) [![CodeFactor](https://www.codefactor.io/repository/github/mindee/doctr/badge?s=bae07db86bb079ce9d6542315b8c6e70fa708a7e)](https://www.codefactor.io/repository/github/mindee/doctr) [![Codacy Badge](https://api.codacy.com/project/badge/Grade/340a76749b634586a498e1c0ab998f08)](https://app.codacy.com/gh/mindee/doctr?utm_source=github.com&utm_medium=referral&utm_content=mindee/doctr&utm_campaign=Badge_Grade) [![Doc Status](https://github.com/mindee/doctr/workflows/doc-status/badge.svg)](https://mindee.github.io/doctr) [![Pypi](https://img.shields.io/badge/pypi-v0.8.0-blue.svg)](https://pypi.org/project/python-doctr/) [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/mindee/doctr) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mindee/notebooks/blob/main/doctr/quicktour.ipynb)
+
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch**
 
@@ -314,7 +309,7 @@ What you can expect from this repository:
 - efficient ways to parse textual information (localize and identify each word) from your documents
 - guidance on how to integrate this in your current architecture
 
-![OCR_example](https://github.com/mindee/doctr/releases/download/v0.2.0/ocr.png?raw=True)
+![OCR_example](https://github.com/mindee/doctr/raw/main/docs/images/ocr.png)
 
 ## Quick Tour
 
@@ -377,10 +372,10 @@ If both options are set to False, the predictor will always fit and return rotat
 To interpret your model's predictions, you can visualize them interactively as follows:
 
 ```python
-result.show(doc)
+result.show()
 ```
 
-![Visualization sample](https://github.com/mindee/doctr/releases/download/v0.1.1/doctr_example_script.gif?raw=True)
+![Visualization sample](https://github.com/mindee/doctr/raw/main/docs/images/doctr_example_script.gif)
 
 Or even rebuild the original document from its predictions:
 
@@ -391,7 +386,7 @@ synthetic_pages = result.synthesize()
 plt.imshow(synthetic_pages[0]); plt.axis('off'); plt.show()
 ```
 
-![Synthesis sample](https://github.com/mindee/doctr/releases/download/v0.3.1/synthesized_sample.png?raw=True)
+![Synthesis sample](https://github.com/mindee/doctr/raw/main/docs/images/synthesized_sample.png)
 
 The `ocr_predictor` returns a `Document` object with a nested structure (with `Page`, `Block`, `Line`, `Word`, `Artefact`).
 To get a better understanding of our document model, check our [documentation](https://mindee.github.io/doctr/modules/io.html#document-structure):
@@ -404,7 +399,7 @@ json_output = result.export()
 
 ### Use the KIE predictor
 
-The KIE predictor is a more flexible predictor compared to OCR as your detection model can detect multiple classes in a document. For example, you can have a detection model to detect just dates and adresses in a document.
+The KIE predictor is a more flexible predictor compared to OCR as your detection model can detect multiple classes in a document. For example, you can have a detection model to detect just dates and addresses in a document.
 
 The KIE predictor makes it possible to use detector with multiple classes with a recognition model and to have the whole pipeline already setup for you.
 
@@ -430,7 +425,7 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 ### If you are looking for support from the Mindee team
 
-[![Bad OCR test detection image asking the developer if they need help](https://github.com/mindee/doctr/releases/download/v0.5.1/doctr-need-help.png?raw=True)](https://mindee.com/product/doctr)
+[![Bad OCR test detection image asking the developer if they need help](https://github.com/mindee/doctr/raw/main/docs/images/doctr-need-help.png)](https://mindee.com/product/doctr)
 
 ## Installation
 
@@ -438,7 +433,7 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 Python 3.8 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to install docTR.
 
-Since we use [weasyprint](https://weasyprint.readthedocs.io/), you will need extra dependencies if you are not running Linux.
+Since we use [weasyprint](https://weasyprint.org/), you will need extra dependencies if you are not running Linux.
 
 For MacOS users, you can install them as follows:
 
@@ -499,6 +494,7 @@ Credits where it's due: this repository is implementing, among others, architect
 
 - DBNet: [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/pdf/1911.08947.pdf).
 - LinkNet: [LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation](https://arxiv.org/pdf/1707.03718.pdf)
+- FAST: [FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation](https://arxiv.org/pdf/2111.02394.pdf)
 
 ### Text Recognition
 
@@ -518,7 +514,7 @@ The full package documentation is available [here](https://mindee.github.io/doct
 
 A minimal demo app is provided for you to play with our end-to-end OCR models!
 
-![Demo app](https://github.com/mindee/doctr/releases/download/v0.3.0/demo_update.png?raw=True)
+![Demo app](https://github.com/mindee/doctr/raw/main/docs/images/demo_update.png)
 
 #### Live demo
 
@@ -558,14 +554,54 @@ USE_TORCH=1 streamlit run demo/app.py
 Instead of having your demo actually running Python, you would prefer to run everything in your web browser?
 Check out our [TensorFlow.js demo](https://github.com/mindee/doctr-tfjs-demo) to get started!
 
-![TFJS demo](https://github.com/mindee/doctr-tfjs-demo/releases/download/v0.1-models/demo_illustration_mini.png?raw=True)
+![TFJS demo](https://github.com/mindee/doctr/raw/main/docs/images/demo_illustration_mini.png)
 
 ### Docker container
 
-If you wish to deploy containerized environments, you can use the provided Dockerfile to build a docker image:
+[We offer Docker container support for easy testing and deployment](https://github.com/mindee/doctr/pkgs/container/doctr).
+
+#### Using GPU with docTR Docker Images
+
+The docTR Docker images are GPU-ready and based on CUDA `11.8`.
+However, to use GPU support with these Docker images, please ensure that Docker is configured to use your GPU.
+
+To verify and configure GPU support for Docker, please follow the instructions provided in the [NVIDIA Container Toolkit Installation Guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
+
+Once Docker is configured to use GPUs, you can run docTR Docker containers with GPU support:
+
+```shell
+docker run -it --gpus all ghcr.io/mindee/doctr:tf-py3.8.18-gpu-2023-09 bash
+```
+
+#### Available Tags
+
+The Docker images for docTR follow a specific tag nomenclature: `<framework>-py<python_version>-<system>-<doctr_version|YYYY-MM>`. Here's a breakdown of the tag structure:
+
+- `<framework>`: `tf` (TensorFlow) or `torch` (PyTorch).
+- `<python_version>`: `3.8.18`, `3.9.18`, or `3.10.13`.
+- `<system>`: `cpu` or `gpu`
+- `<doctr_version>`: a tag >= `v0.7.1`
+- `<YYYY-MM>`: e.g. `2023-09`
+
+Here are examples of different image tags:
+
+| Tag                        | Description                                       |
+|----------------------------|---------------------------------------------------|
+| `tf-py3.8.18-cpu-v0.7.1`       | TensorFlow version `3.8.18` with docTR `v0.7.1`. |
+| `torch-py3.9.18-gpu-2023-09`| PyTorch version `3.9.18` with GPU support and a monthly build from `2023-09`. |
+
+#### Building Docker Images Locally
+
+You can also build docTR Docker images locally on your computer.
+
+```shell
+docker build -t doctr .
+```
+
+You can specify custom Python versions and docTR versions using build arguments. For example, to build a docTR image with TensorFlow, Python version `3.9.10`, and docTR version `v0.7.0`, run the following command:
 
 ```shell
-docker build . -t <YOUR_IMAGE_TAG>
+docker build -t doctr --build-arg FRAMEWORK=tf --build-arg PYTHON_VERSION=3.9.10 --build-arg DOCTR_VERSION=v0.7.0 .
 ```
 
 ### Example script
@@ -638,8 +674,8 @@ If you wish to cite this project, feel free to use this [BibTeX](http://www.bibt
 
 If you scrolled down to this section, you most likely appreciate open source. Do you feel like extending the range of our supported characters? Or perhaps submitting a paper implementation? Or contributing in any other way?
 
-You're in luck, we compiled a short guide (cf. [`CONTRIBUTING`](CONTRIBUTING.md)) for you to easily do so!
+You're in luck, we compiled a short guide (cf. [`CONTRIBUTING`](https://mindee.github.io/doctr/contributing/contributing.html)) for you to easily do so!
 
 ## License
 
-Distributed under the Apache 2.0 License. See [`LICENSE`](LICENSE) for more information.
+Distributed under the Apache 2.0 License. See [`LICENSE`](https://github.com/mindee/doctr?tab=Apache-2.0-1-ov-file#readme) for more information.

{python-doctr-0.7.0 → python-doctr-0.8.1}/README.md

@@ -1,8 +1,9 @@
 <p align="center">
-  <img src="https://github.com/mindee/doctr/releases/download/v0.3.1/Logo_doctr.gif?raw=True" width="40%">
+  <img src="https://github.com/mindee/doctr/raw/main/docs/images/Logo_doctr.gif" width="40%">
 </p>
 
-[![Slack Icon](https://img.shields.io/badge/Slack-Community-4A154B?style=flat-square&logo=slack&logoColor=white)](https://slack.mindee.com) [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) ![Build Status](https://github.com/mindee/doctr/workflows/builds/badge.svg) [![codecov](https://codecov.io/gh/mindee/doctr/branch/main/graph/badge.svg?token=577MO567NM)](https://codecov.io/gh/mindee/doctr) [![CodeFactor](https://www.codefactor.io/repository/github/mindee/doctr/badge?s=bae07db86bb079ce9d6542315b8c6e70fa708a7e)](https://www.codefactor.io/repository/github/mindee/doctr) [![Codacy Badge](https://api.codacy.com/project/badge/Grade/340a76749b634586a498e1c0ab998f08)](https://app.codacy.com/gh/mindee/doctr?utm_source=github.com&utm_medium=referral&utm_content=mindee/doctr&utm_campaign=Badge_Grade) [![Doc Status](https://github.com/mindee/doctr/workflows/doc-status/badge.svg)](https://mindee.github.io/doctr) [![Pypi](https://img.shields.io/badge/pypi-v0.6.0-blue.svg)](https://pypi.org/project/python-doctr/) [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/mindee/doctr) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mindee/notebooks/blob/main/doctr/quicktour.ipynb)
+[![Slack Icon](https://img.shields.io/badge/Slack-Community-4A154B?style=flat-square&logo=slack&logoColor=white)](https://slack.mindee.com) [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) ![Build Status](https://github.com/mindee/doctr/workflows/builds/badge.svg) [![Docker Images](https://img.shields.io/badge/Docker-4287f5?style=flat&logo=docker&logoColor=white)](https://github.com/mindee/doctr/pkgs/container/doctr) [![codecov](https://codecov.io/gh/mindee/doctr/branch/main/graph/badge.svg?token=577MO567NM)](https://codecov.io/gh/mindee/doctr) [![CodeFactor](https://www.codefactor.io/repository/github/mindee/doctr/badge?s=bae07db86bb079ce9d6542315b8c6e70fa708a7e)](https://www.codefactor.io/repository/github/mindee/doctr) [![Codacy Badge](https://api.codacy.com/project/badge/Grade/340a76749b634586a498e1c0ab998f08)](https://app.codacy.com/gh/mindee/doctr?utm_source=github.com&utm_medium=referral&utm_content=mindee/doctr&utm_campaign=Badge_Grade) [![Doc Status](https://github.com/mindee/doctr/workflows/doc-status/badge.svg)](https://mindee.github.io/doctr) [![Pypi](https://img.shields.io/badge/pypi-v0.8.0-blue.svg)](https://pypi.org/project/python-doctr/) [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/mindee/doctr) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mindee/notebooks/blob/main/doctr/quicktour.ipynb)
+
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch**
 
@@ -11,7 +12,7 @@ What you can expect from this repository:
 - efficient ways to parse textual information (localize and identify each word) from your documents
 - guidance on how to integrate this in your current architecture
 
-![OCR_example](https://github.com/mindee/doctr/releases/download/v0.2.0/ocr.png?raw=True)
+![OCR_example](https://github.com/mindee/doctr/raw/main/docs/images/ocr.png)
 
 ## Quick Tour
 
@@ -74,10 +75,10 @@ If both options are set to False, the predictor will always fit and return rotat
 To interpret your model's predictions, you can visualize them interactively as follows:
 
 ```python
-result.show(doc)
+result.show()
 ```
 
-![Visualization sample](https://github.com/mindee/doctr/releases/download/v0.1.1/doctr_example_script.gif?raw=True)
+![Visualization sample](https://github.com/mindee/doctr/raw/main/docs/images/doctr_example_script.gif)
 
 Or even rebuild the original document from its predictions:
 
@@ -88,7 +89,7 @@ synthetic_pages = result.synthesize()
 plt.imshow(synthetic_pages[0]); plt.axis('off'); plt.show()
 ```
 
-![Synthesis sample](https://github.com/mindee/doctr/releases/download/v0.3.1/synthesized_sample.png?raw=True)
+![Synthesis sample](https://github.com/mindee/doctr/raw/main/docs/images/synthesized_sample.png)
 
 The `ocr_predictor` returns a `Document` object with a nested structure (with `Page`, `Block`, `Line`, `Word`, `Artefact`).
 To get a better understanding of our document model, check our [documentation](https://mindee.github.io/doctr/modules/io.html#document-structure):
@@ -101,7 +102,7 @@ json_output = result.export()
 
 ### Use the KIE predictor
 
-The KIE predictor is a more flexible predictor compared to OCR as your detection model can detect multiple classes in a document. For example, you can have a detection model to detect just dates and adresses in a document.
+The KIE predictor is a more flexible predictor compared to OCR as your detection model can detect multiple classes in a document. For example, you can have a detection model to detect just dates and addresses in a document.
 
 The KIE predictor makes it possible to use detector with multiple classes with a recognition model and to have the whole pipeline already setup for you.
 
@@ -127,7 +128,7 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 ### If you are looking for support from the Mindee team
 
-[![Bad OCR test detection image asking the developer if they need help](https://github.com/mindee/doctr/releases/download/v0.5.1/doctr-need-help.png?raw=True)](https://mindee.com/product/doctr)
+[![Bad OCR test detection image asking the developer if they need help](https://github.com/mindee/doctr/raw/main/docs/images/doctr-need-help.png)](https://mindee.com/product/doctr)
 
 ## Installation
 
@@ -135,7 +136,7 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 Python 3.8 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to install docTR.
 
-Since we use [weasyprint](https://weasyprint.readthedocs.io/), you will need extra dependencies if you are not running Linux.
+Since we use [weasyprint](https://weasyprint.org/), you will need extra dependencies if you are not running Linux.
 
 For MacOS users, you can install them as follows:
 
@@ -196,6 +197,7 @@ Credits where it's due: this repository is implementing, among others, architect
 
 - DBNet: [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/pdf/1911.08947.pdf).
 - LinkNet: [LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation](https://arxiv.org/pdf/1707.03718.pdf)
+- FAST: [FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation](https://arxiv.org/pdf/2111.02394.pdf)
 
 ### Text Recognition
 
@@ -215,7 +217,7 @@ The full package documentation is available [here](https://mindee.github.io/doct
 
 A minimal demo app is provided for you to play with our end-to-end OCR models!
 
-![Demo app](https://github.com/mindee/doctr/releases/download/v0.3.0/demo_update.png?raw=True)
+![Demo app](https://github.com/mindee/doctr/raw/main/docs/images/demo_update.png)
 
 #### Live demo
 
@@ -255,14 +257,54 @@ USE_TORCH=1 streamlit run demo/app.py
 Instead of having your demo actually running Python, you would prefer to run everything in your web browser?
 Check out our [TensorFlow.js demo](https://github.com/mindee/doctr-tfjs-demo) to get started!
 
-![TFJS demo](https://github.com/mindee/doctr-tfjs-demo/releases/download/v0.1-models/demo_illustration_mini.png?raw=True)
+![TFJS demo](https://github.com/mindee/doctr/raw/main/docs/images/demo_illustration_mini.png)
 
 ### Docker container
 
-If you wish to deploy containerized environments, you can use the provided Dockerfile to build a docker image:
+[We offer Docker container support for easy testing and deployment](https://github.com/mindee/doctr/pkgs/container/doctr).
+
+#### Using GPU with docTR Docker Images
+
+The docTR Docker images are GPU-ready and based on CUDA `11.8`.
+However, to use GPU support with these Docker images, please ensure that Docker is configured to use your GPU.
+
+To verify and configure GPU support for Docker, please follow the instructions provided in the [NVIDIA Container Toolkit Installation Guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
+
+Once Docker is configured to use GPUs, you can run docTR Docker containers with GPU support:
+
+```shell
+docker run -it --gpus all ghcr.io/mindee/doctr:tf-py3.8.18-gpu-2023-09 bash
+```
+
+#### Available Tags
+
+The Docker images for docTR follow a specific tag nomenclature: `<framework>-py<python_version>-<system>-<doctr_version|YYYY-MM>`. Here's a breakdown of the tag structure:
+
+- `<framework>`: `tf` (TensorFlow) or `torch` (PyTorch).
+- `<python_version>`: `3.8.18`, `3.9.18`, or `3.10.13`.
+- `<system>`: `cpu` or `gpu`
+- `<doctr_version>`: a tag >= `v0.7.1`
+- `<YYYY-MM>`: e.g. `2023-09`
+
+Here are examples of different image tags:
+
+| Tag                        | Description                                       |
+|----------------------------|---------------------------------------------------|
+| `tf-py3.8.18-cpu-v0.7.1`       | TensorFlow version `3.8.18` with docTR `v0.7.1`. |
+| `torch-py3.9.18-gpu-2023-09`| PyTorch version `3.9.18` with GPU support and a monthly build from `2023-09`. |
+
+#### Building Docker Images Locally
+
+You can also build docTR Docker images locally on your computer.
+
+```shell
+docker build -t doctr .
+```
+
+You can specify custom Python versions and docTR versions using build arguments. For example, to build a docTR image with TensorFlow, Python version `3.9.10`, and docTR version `v0.7.0`, run the following command:
 
 ```shell
-docker build . -t <YOUR_IMAGE_TAG>
+docker build -t doctr --build-arg FRAMEWORK=tf --build-arg PYTHON_VERSION=3.9.10 --build-arg DOCTR_VERSION=v0.7.0 .
 ```
 
 ### Example script
@@ -335,8 +377,8 @@ If you wish to cite this project, feel free to use this [BibTeX](http://www.bibt
 
 If you scrolled down to this section, you most likely appreciate open source. Do you feel like extending the range of our supported characters? Or perhaps submitting a paper implementation? Or contributing in any other way?
 
-You're in luck, we compiled a short guide (cf. [`CONTRIBUTING`](CONTRIBUTING.md)) for you to easily do so!
+You're in luck, we compiled a short guide (cf. [`CONTRIBUTING`](https://mindee.github.io/doctr/contributing/contributing.html)) for you to easily do so!
 
 ## License
 
-Distributed under the Apache 2.0 License. See [`LICENSE`](LICENSE) for more information.
+Distributed under the Apache 2.0 License. See [`LICENSE`](https://github.com/mindee/doctr?tab=Apache-2.0-1-ov-file#readme) for more information.

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/__init__.py

@@ -13,12 +13,14 @@ from .imgur5k import *
 from .mjsynth import *
 from .ocr import *
 from .recognition import *
+from .orientation import *
 from .sroie import *
 from .svhn import *
 from .svt import *
 from .synthtext import *
 from .utils import *
 from .vocabs import *
+from .wildreceipt import *
 
 if is_tf_available():
     from .loader import *

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/cord.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -29,6 +29,7 @@ class CORD(VisionDataset):
     >>> img, target = train_set[0]
 
     Args:
+    ----
         train: whether the subset should be the training one
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
         recognition_task: whether the dataset should be used for recognition task
@@ -109,9 +110,10 @@ class CORD(VisionDataset):
                 for crop, label in zip(crops, list(text_targets)):
                     self.data.append((crop, label))
             else:
-                self.data.append(
-                    (img_path, dict(boxes=np.asarray(box_targets, dtype=int).clip(min=0), labels=list(text_targets)))
-                )
+                self.data.append((
+                    img_path,
+                    dict(boxes=np.asarray(box_targets, dtype=int).clip(min=0), labels=list(text_targets)),
+                ))
 
         self.root = tmp_root
 

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/datasets/base.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -59,7 +59,7 @@ class _AbstractDataset:
             # Conditions to assess it is detection model with multiple classes and avoid confusion with other tasks.
             if (
                 isinstance(target, dict)
-                and all([isinstance(item, np.ndarray) for item in target.values()])
+                and all(isinstance(item, np.ndarray) for item in target.values())
                 and set(target.keys()) != {"boxes", "labels"}  # avoid confusion with obj detection target
             ):
                 img_transformed = _copy_tensor(img)
@@ -82,6 +82,7 @@ class _VisionDataset(_AbstractDataset):
     """Implements an abstract dataset
 
     Args:
+    ----
         url: URL of the dataset
         file_name: name of the file once downloaded
         file_hash: expected SHA256 of the file

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/datasets/pytorch.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -18,6 +18,8 @@ __all__ = ["AbstractDataset", "VisionDataset"]
 
 
 class AbstractDataset(_AbstractDataset):
+    """Abstract class for all datasets"""
+
     def _read_sample(self, index: int) -> Tuple[torch.Tensor, Any]:
         img_name, target = self.data[index]
 
@@ -53,5 +55,5 @@ class AbstractDataset(_AbstractDataset):
         return images, list(targets)
 
 
-class VisionDataset(AbstractDataset, _VisionDataset):
+class VisionDataset(AbstractDataset, _VisionDataset):  # noqa: D101
     pass

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/datasets/tensorflow.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -18,6 +18,8 @@ __all__ = ["AbstractDataset", "VisionDataset"]
 
 
 class AbstractDataset(_AbstractDataset):
+    """Abstract class for all datasets"""
+
     def _read_sample(self, index: int) -> Tuple[tf.Tensor, Any]:
         img_name, target = self.data[index]
 
@@ -53,5 +55,5 @@ class AbstractDataset(_AbstractDataset):
         return images, list(targets)
 
 
-class VisionDataset(AbstractDataset, _VisionDataset):
+class VisionDataset(AbstractDataset, _VisionDataset):  # noqa: D101
     pass

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/detection.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -26,6 +26,7 @@ class DetectionDataset(AbstractDataset):
     >>> img, target = train_set[0]
 
     Args:
+    ----
         img_folder: folder with all the images of the dataset
         label_path: path to the annotations of each image
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
@@ -66,14 +67,16 @@ class DetectionDataset(AbstractDataset):
     def format_polygons(
         self, polygons: Union[List, Dict], use_polygons: bool, np_dtype: Type
     ) -> Tuple[np.ndarray, List[str]]:
-        """format polygons into an array
+        """Format polygons into an array
 
         Args:
+        ----
             polygons: the bounding boxes
             use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
             np_dtype: dtype of array
 
         Returns:
+        -------
             geoms: bounding boxes as np array
             polygons_classes: list of classes for each bounding box
         """
@@ -92,4 +95,4 @@ class DetectionDataset(AbstractDataset):
 
     @property
     def class_names(self):
-        return sorted(list(set(self._class_names)))
+        return sorted(set(self._class_names))

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/doc_artefacts.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -26,6 +26,7 @@ class DocArtefacts(VisionDataset):
     >>> img, target = train_set[0]
 
     Args:
+    ----
         train: whether the subset should be the training one
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
         **kwargs: keyword arguments from `VisionDataset`.

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/funsd.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -29,6 +29,7 @@ class FUNSD(VisionDataset):
     >>> img, target = train_set[0]
 
     Args:
+    ----
         train: whether the subset should be the training one
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
         recognition_task: whether the dataset should be used for recognition task
@@ -81,7 +82,7 @@ class FUNSD(VisionDataset):
             text_targets, box_targets = zip(*_targets)
             if use_polygons:
                 # xmin, ymin, xmax, ymax -> (x, y) coordinates of top left, top right, bottom right, bottom left corners
-                box_targets = [
+                box_targets = [  # type: ignore[assignment]
                     [
                         [box[0], box[1]],
                         [box[2], box[1]],
@@ -100,12 +101,10 @@ class FUNSD(VisionDataset):
                     if not any(char in label for char in ["☑", "☐", "\uf703", "\uf702"]):
                         self.data.append((crop, label))
             else:
-                self.data.append(
-                    (
-                        img_path,
-                        dict(boxes=np.asarray(box_targets, dtype=np_dtype), labels=list(text_targets)),
-                    )
-                )
+                self.data.append((
+                    img_path,
+                    dict(boxes=np.asarray(box_targets, dtype=np_dtype), labels=list(text_targets)),
+                ))
 
         self.root = tmp_root
 

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/generator/base.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -24,6 +24,7 @@ def synthesize_text_img(
     """Generate a synthetic text image
 
     Args:
+    ----
         text: the text to render as an image
         font_size: the size of the font
         font_family: the font family (has to be installed on your system)
@@ -31,9 +32,9 @@ def synthesize_text_img(
         text_color: text color on the final image
 
     Returns:
+    -------
         PIL image of the text
     """
-
     background_color = (0, 0, 0) if background_color is None else background_color
     text_color = (255, 255, 255) if text_color is None else text_color
 

{python-doctr-0.7.0 → python-doctr-0.8.1}/doctr/datasets/generator/pytorch.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -18,6 +18,7 @@ class CharacterGenerator(_CharacterGenerator):
     >>> img, target = ds[0]
 
     Args:
+    ----
         vocab: vocabulary to take the character from
         num_samples: number of samples that will be generated iterating over the dataset
         cache_samples: whether generated images should be cached firsthand
@@ -39,6 +40,7 @@ class WordGenerator(_WordGenerator):
     >>> img, target = ds[0]
 
     Args:
+    ----
         vocab: vocabulary to take the character from
         min_chars: minimum number of characters in a word
         max_chars: maximum number of characters in a word