python-doctr 0.10.0__tar.gz → 0.12.0__tar.gz

{python_doctr-0.10.0 → python_doctr-0.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: python-doctr
-Version: 0.10.0
+Version: 0.12.0
 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
@@ -219,11 +219,11 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Natural Language :: English
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: <4,>=3.9.0
+Requires-Python: <4,>=3.10.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy<3.0.0,>=1.16.0
@@ -239,9 +239,11 @@ Requires-Dist: huggingface-hub<1.0.0,>=0.20.0
 Requires-Dist: Pillow>=9.2.0
 Requires-Dist: defusedxml>=0.7.0
 Requires-Dist: anyascii>=0.3.2
+Requires-Dist: validators>=0.18.0
 Requires-Dist: tqdm>=4.30.0
 Provides-Extra: tf
-Requires-Dist: tensorflow<3.0.0,>=2.15.0; extra == "tf"
+Requires-Dist: tensorflow[and-cuda]<3.0.0,>=2.15.0; sys_platform == "linux" and extra == "tf"
+Requires-Dist: tensorflow<3.0.0,>=2.15.0; sys_platform != "linux" and extra == "tf"
 Requires-Dist: tf-keras<3.0.0,>=2.15.0; extra == "tf"
 Requires-Dist: tf2onnx<2.0.0,>=1.16.0; extra == "tf"
 Provides-Extra: torch
@@ -275,7 +277,8 @@ 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,>=2.15.0; extra == "dev"
+Requires-Dist: tensorflow[and-cuda]<3.0.0,>=2.15.0; sys_platform == "linux" and extra == "dev"
+Requires-Dist: tensorflow<3.0.0,>=2.15.0; sys_platform != "linux" and extra == "dev"
 Requires-Dist: tf-keras<3.0.0,>=2.15.0; extra == "dev"
 Requires-Dist: tf2onnx<2.0.0,>=1.16.0; extra == "dev"
 Requires-Dist: torch<3.0.0,>=2.0.0; extra == "dev"
@@ -300,12 +303,13 @@ Requires-Dist: recommonmark>=0.7.1; extra == "dev"
 Requires-Dist: sphinx-markdown-tables>=0.0.15; extra == "dev"
 Requires-Dist: sphinx-tabs>=3.3.0; extra == "dev"
 Requires-Dist: furo>=2022.3.4; extra == "dev"
+Dynamic: license-file
 
 <p align="center">
   <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) [![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-v0.9.0-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-v0.12.0-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) [![Gurubase](https://img.shields.io/badge/Gurubase-Ask%20docTR%20Guru-006BFF)](https://gurubase.io/g/doctr)
 
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch**
@@ -436,9 +440,22 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 ## Installation
 
+> [!WARNING]
+> **TensorFlow Backend Deprecation Notice**
+>
+> Using docTR with TensorFlow as a backend is deprecated and will be removed in the next major release (v1.0.0).
+> We **recommend switching to the PyTorch backend**, which is more actively maintained and supports the latest features and models.
+> Alternatively, you can use [OnnxTR](https://github.com/felixdittrich92/OnnxTR), which does **not** require TensorFlow or PyTorch.
+>
+> This decision was made based on several considerations:
+>
+> - Allows better focus on improving the core library
+> - Frees up resources to develop new features faster
+> - Enables more targeted optimizations with PyTorch
+
 ### Prerequisites
 
-Python 3.9 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to install docTR.
+Python 3.10 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to install docTR.
 
 ### Latest release
 
@@ -502,6 +519,7 @@ Credits where it's due: this repository is implementing, among others, architect
 - MASTER: [MASTER: Multi-Aspect Non-local Network for Scene Text Recognition](https://arxiv.org/pdf/1910.02562.pdf).
 - ViTSTR: [Vision Transformer for Fast and Efficient Scene Text Recognition](https://arxiv.org/pdf/2105.08582.pdf).
 - PARSeq: [Scene Text Recognition with Permuted Autoregressive Sequence Models](https://arxiv.org/pdf/2207.06966).
+- VIPTR: [A Vision Permutable Extractor for Fast and Efficient Scene Text Recognition](https://arxiv.org/abs/2401.10110).
 
 ## More goodies
 
@@ -557,37 +575,37 @@ Check out our [TensorFlow.js demo](https://github.com/mindee/doctr-tfjs-demo) to
 
 ### Docker container
 
-[We offer Docker container support for easy testing and deployment](https://github.com/mindee/doctr/pkgs/container/doctr).
+We offer Docker container support for easy testing and deployment. [Here are the available docker tags.](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.
+The docTR Docker images are GPU-ready and based on CUDA `12.2`. Make sure your host is **at least `12.2`**, otherwise Torch or TensorFlow won't be able to initialize the GPU.
+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
+docker run -it --gpus all ghcr.io/mindee/doctr:torch-py3.9.18-2024-10 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:
+The Docker images for docTR follow a specific tag nomenclature: `<deps>-py<python_version>-<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`
+- `<deps>`: `tf`, `torch`, `tf-viz-html-contrib` or `torch-viz-html-contrib`.
+- `<python_version>`: `3.9.18`, `3.10.13` or `3.11.8`.
+- `<doctr_version>`: a tag >= `v0.11.0`
+- `<YYYY-MM>`: e.g. `2014-10`
 
 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`. |
+| `tf-py3.10.13-v0.11.0`       | TensorFlow version `3.10.13` with docTR `v0.11.0`. |
+| `torch-viz-html-contrib-py3.11.8-2024-10`       | Torch with extra dependencies version `3.11.8` from latest commit on `main` in `2024-10`. |
+| `torch-py3.11.8-2024-10`| PyTorch version `3.11.8` from latest commit on `main` in `2024-10`. |
 
 #### Building Docker Images Locally
 

{python_doctr-0.10.0 → python_doctr-0.12.0}/README.md

@@ -2,7 +2,7 @@
   <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) [![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-v0.9.0-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-v0.12.0-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) [![Gurubase](https://img.shields.io/badge/Gurubase-Ask%20docTR%20Guru-006BFF)](https://gurubase.io/g/doctr)
 
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch**
@@ -133,9 +133,22 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 ## Installation
 
+> [!WARNING]
+> **TensorFlow Backend Deprecation Notice**
+>
+> Using docTR with TensorFlow as a backend is deprecated and will be removed in the next major release (v1.0.0).
+> We **recommend switching to the PyTorch backend**, which is more actively maintained and supports the latest features and models.
+> Alternatively, you can use [OnnxTR](https://github.com/felixdittrich92/OnnxTR), which does **not** require TensorFlow or PyTorch.
+>
+> This decision was made based on several considerations:
+>
+> - Allows better focus on improving the core library
+> - Frees up resources to develop new features faster
+> - Enables more targeted optimizations with PyTorch
+
 ### Prerequisites
 
-Python 3.9 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to install docTR.
+Python 3.10 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to install docTR.
 
 ### Latest release
 
@@ -199,6 +212,7 @@ Credits where it's due: this repository is implementing, among others, architect
 - MASTER: [MASTER: Multi-Aspect Non-local Network for Scene Text Recognition](https://arxiv.org/pdf/1910.02562.pdf).
 - ViTSTR: [Vision Transformer for Fast and Efficient Scene Text Recognition](https://arxiv.org/pdf/2105.08582.pdf).
 - PARSeq: [Scene Text Recognition with Permuted Autoregressive Sequence Models](https://arxiv.org/pdf/2207.06966).
+- VIPTR: [A Vision Permutable Extractor for Fast and Efficient Scene Text Recognition](https://arxiv.org/abs/2401.10110).
 
 ## More goodies
 
@@ -254,37 +268,37 @@ Check out our [TensorFlow.js demo](https://github.com/mindee/doctr-tfjs-demo) to
 
 ### Docker container
 
-[We offer Docker container support for easy testing and deployment](https://github.com/mindee/doctr/pkgs/container/doctr).
+We offer Docker container support for easy testing and deployment. [Here are the available docker tags.](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.
+The docTR Docker images are GPU-ready and based on CUDA `12.2`. Make sure your host is **at least `12.2`**, otherwise Torch or TensorFlow won't be able to initialize the GPU.
+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
+docker run -it --gpus all ghcr.io/mindee/doctr:torch-py3.9.18-2024-10 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:
+The Docker images for docTR follow a specific tag nomenclature: `<deps>-py<python_version>-<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`
+- `<deps>`: `tf`, `torch`, `tf-viz-html-contrib` or `torch-viz-html-contrib`.
+- `<python_version>`: `3.9.18`, `3.10.13` or `3.11.8`.
+- `<doctr_version>`: a tag >= `v0.11.0`
+- `<YYYY-MM>`: e.g. `2014-10`
 
 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`. |
+| `tf-py3.10.13-v0.11.0`       | TensorFlow version `3.10.13` with docTR `v0.11.0`. |
+| `torch-viz-html-contrib-py3.11.8-2024-10`       | Torch with extra dependencies version `3.11.8` from latest commit on `main` in `2024-10`. |
+| `torch-py3.11.8-2024-10`| PyTorch version `3.11.8` from latest commit on `main` in `2024-10`. |
 
 #### Building Docker Images Locally
 

python_doctr-0.12.0/doctr/contrib/__init__.py

@@ -0,0 +1 @@
+from .artefacts import ArtefactDetector

{python_doctr-0.10.0 → python_doctr-0.12.0}/doctr/contrib/artefacts.py

@@ -1,9 +1,9 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, 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.
 
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any
 
 import cv2
 import numpy as np
@@ -14,7 +14,7 @@ from .base import _BasePredictor
 
 __all__ = ["ArtefactDetector"]
 
-default_cfgs: Dict[str, Dict[str, Any]] = {
+default_cfgs: dict[str, dict[str, Any]] = {
     "yolov8_artefact": {
         "input_shape": (3, 1024, 1024),
         "labels": ["bar_code", "qr_code", "logo", "photo"],
@@ -34,7 +34,6 @@ class ArtefactDetector(_BasePredictor):
     >>> results = detector(doc)
 
     Args:
-    ----
         arch: the architecture to use
         batch_size: the batch size to use
         model_path: the path to the model to use
@@ -50,9 +49,9 @@ class ArtefactDetector(_BasePredictor):
         self,
         arch: str = "yolov8_artefact",
         batch_size: int = 2,
-        model_path: Optional[str] = None,
-        labels: Optional[List[str]] = None,
-        input_shape: Optional[Tuple[int, int, int]] = None,
+        model_path: str | None = None,
+        labels: list[str] | None = None,
+        input_shape: tuple[int, int, int] | None = None,
         conf_threshold: float = 0.5,
         iou_threshold: float = 0.5,
         **kwargs: Any,
@@ -66,7 +65,7 @@ class ArtefactDetector(_BasePredictor):
     def preprocess(self, img: np.ndarray) -> np.ndarray:
         return np.transpose(cv2.resize(img, (self.input_shape[2], self.input_shape[1])), (2, 0, 1)) / np.array(255.0)
 
-    def postprocess(self, output: List[np.ndarray], input_images: List[List[np.ndarray]]) -> List[List[Dict[str, Any]]]:
+    def postprocess(self, output: list[np.ndarray], input_images: list[list[np.ndarray]]) -> list[list[dict[str, Any]]]:
         results = []
 
         for batch in zip(output, input_images):
@@ -109,7 +108,6 @@ class ArtefactDetector(_BasePredictor):
         Display the results
 
         Args:
-        ----
             **kwargs: additional keyword arguments to be passed to `plt.show`
         """
         requires_package("matplotlib", "`.show()` requires matplotlib installed")

{python_doctr-0.10.0 → python_doctr-0.12.0}/doctr/contrib/base.py

@@ -1,9 +1,9 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, 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.
 
-from typing import Any, List, Optional
+from typing import Any
 
 import numpy as np
 
@@ -16,32 +16,29 @@ class _BasePredictor:
     Base class for all predictors
 
     Args:
-    ----
         batch_size: the batch size to use
         url: the url to use to download a model if needed
         model_path: the path to the model to use
         **kwargs: additional arguments to be passed to `download_from_url`
     """
 
-    def __init__(self, batch_size: int, url: Optional[str] = None, model_path: Optional[str] = None, **kwargs) -> None:
+    def __init__(self, batch_size: int, url: str | None = None, model_path: str | None = None, **kwargs) -> None:
         self.batch_size = batch_size
         self.session = self._init_model(url, model_path, **kwargs)
 
-        self._inputs: List[np.ndarray] = []
-        self._results: List[Any] = []
+        self._inputs: list[np.ndarray] = []
+        self._results: list[Any] = []
 
-    def _init_model(self, url: Optional[str] = None, model_path: Optional[str] = None, **kwargs: Any) -> Any:
+    def _init_model(self, url: str | None = None, model_path: str | None = None, **kwargs: Any) -> Any:
         """
         Download the model from the given url if needed
 
         Args:
-        ----
             url: the url to use
             model_path: the path to the model to use
             **kwargs: additional arguments to be passed to `download_from_url`
 
         Returns:
-        -------
             Any: the ONNX loaded model
         """
         requires_package("onnxruntime", "`.contrib` module requires `onnxruntime` to be installed.")
@@ -57,40 +54,34 @@ class _BasePredictor:
         Preprocess the input image
 
         Args:
-        ----
             img: the input image to preprocess
 
         Returns:
-        -------
             np.ndarray: the preprocessed image
         """
         raise NotImplementedError
 
-    def postprocess(self, output: List[np.ndarray], input_images: List[List[np.ndarray]]) -> Any:
+    def postprocess(self, output: list[np.ndarray], input_images: list[list[np.ndarray]]) -> Any:
         """
         Postprocess the model output
 
         Args:
-        ----
             output: the model output to postprocess
             input_images: the input images used to generate the output
 
         Returns:
-        -------
             Any: the postprocessed output
         """
         raise NotImplementedError
 
-    def __call__(self, inputs: List[np.ndarray]) -> Any:
+    def __call__(self, inputs: list[np.ndarray]) -> Any:
         """
         Call the model on the given inputs
 
         Args:
-        ----
             inputs: the inputs to use
 
         Returns:
-        -------
             Any: the postprocessed output
         """
         self._inputs = inputs

{python_doctr-0.10.0 → python_doctr-0.12.0}/doctr/datasets/__init__.py

@@ -1,6 +1,7 @@
 from doctr.file_utils import is_tf_available
 
 from .generator import *
+from .coco_text import *
 from .cord import *
 from .detection import *
 from .doc_artefacts import *

python_doctr-0.12.0/doctr/datasets/coco_text.py

@@ -0,0 +1,139 @@
+# Copyright (C) 2021-2025, 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.
+
+import json
+import os
+from pathlib import Path
+from typing import Any
+
+import numpy as np
+from tqdm import tqdm
+
+from .datasets import AbstractDataset
+from .utils import convert_target_to_relative, crop_bboxes_from_image
+
+__all__ = ["COCOTEXT"]
+
+
+class COCOTEXT(AbstractDataset):
+    """
+    COCO-Text dataset from `"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images"
+    <https://arxiv.org/pdf/1601.07140v2>`_ |
+    `"homepage" <https://bgshih.github.io/cocotext/>`_.
+
+    >>> # NOTE: You need to download the dataset first.
+    >>> from doctr.datasets import COCOTEXT
+    >>> train_set = COCOTEXT(train=True, img_folder="/path/to/coco_text/train2014/",
+    >>>                     label_path="/path/to/coco_text/cocotext.v2.json")
+    >>> img, target = train_set[0]
+    >>> test_set = COCOTEXT(train=False, img_folder="/path/to/coco_text/train2014/",
+    >>> label_path = "/path/to/coco_text/cocotext.v2.json")
+    >>> img, target = test_set[0]
+
+    Args:
+        img_folder: folder with all the images of the dataset
+        label_path: path to the annotations file of the dataset
+        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
+        detection_task: whether the dataset should be used for detection task
+        **kwargs: keyword arguments from `AbstractDataset`.
+    """
+
+    def __init__(
+        self,
+        img_folder: str,
+        label_path: str,
+        train: bool = True,
+        use_polygons: bool = False,
+        recognition_task: bool = False,
+        detection_task: bool = False,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            img_folder, pre_transforms=convert_target_to_relative if not recognition_task else None, **kwargs
+        )
+        # Task check
+        if recognition_task and detection_task:
+            raise ValueError(
+                " 'recognition' and 'detection task' cannot be set to True simultaneously. "
+                + " To get the whole dataset with boxes and labels leave both parameters to False "
+            )
+
+        # File existence check
+        if not os.path.exists(label_path) or not os.path.exists(img_folder):
+            raise FileNotFoundError(f"unable to find {label_path if not os.path.exists(label_path) else img_folder}")
+
+        tmp_root = img_folder
+        self.train = train
+        np_dtype = np.float32
+        self.data: list[tuple[str | Path | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
+
+        with open(label_path, "r") as file:
+            data = json.load(file)
+
+        # Filter images based on the set
+        img_items = [img for img in data["imgs"].items() if (img[1]["set"] == "train") == train]
+        box: list[float] | np.ndarray
+
+        for img_id, img_info in tqdm(img_items, desc="Preparing and Loading COCOTEXT", total=len(img_items)):
+            img_path = os.path.join(img_folder, img_info["file_name"])
+
+            # File existence check
+            if not os.path.exists(img_path):  # pragma: no cover
+                raise FileNotFoundError(f"Unable to locate {img_path}")
+
+            # Get annotations for the current image (only legible text)
+            annotations = [
+                ann
+                for ann in data["anns"].values()
+                if ann["image_id"] == int(img_id) and ann["legibility"] == "legible"
+            ]
+
+            # Some images have no annotations with readable text
+            if not annotations:  # pragma: no cover
+                continue
+
+            _targets = []
+
+            for annotation in annotations:
+                x, y, w, h = annotation["bbox"]
+                if use_polygons:
+                    # (x, y) coordinates of top left, top right, bottom right, bottom left corners
+                    box = np.array(
+                        [
+                            [x, y],
+                            [x + w, y],
+                            [x + w, y + h],
+                            [x, y + h],
+                        ],
+                        dtype=np_dtype,
+                    )
+                else:
+                    # (xmin, ymin, xmax, ymax) coordinates
+                    box = [x, y, x + w, y + h]
+                _targets.append((annotation["utf8_string"], box))
+            text_targets, box_targets = zip(*_targets)
+
+            if recognition_task:
+                crops = crop_bboxes_from_image(
+                    img_path=os.path.join(tmp_root, img_path), geoms=np.asarray(box_targets, dtype=int).clip(min=0)
+                )
+                for crop, label in zip(crops, list(text_targets)):
+                    if label and " " not in label:
+                        self.data.append((crop, label))
+
+            elif detection_task:
+                self.data.append((img_path, np.asarray(box_targets, dtype=int).clip(min=0)))
+            else:
+                self.data.append((
+                    img_path,
+                    dict(boxes=np.asarray(box_targets, dtype=int).clip(min=0), labels=list(text_targets)),
+                ))
+
+        self.root = tmp_root
+
+    def extra_repr(self) -> str:
+        return f"train={self.train}"

{python_doctr-0.10.0 → python_doctr-0.12.0}/doctr/datasets/cord.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, 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.
@@ -6,7 +6,7 @@
 import json
 import os
 from pathlib import Path
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import numpy as np
 from tqdm import tqdm
@@ -29,7 +29,6 @@ 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
@@ -72,12 +71,14 @@ class CORD(VisionDataset):
                 + "To get the whole dataset with boxes and labels leave both parameters to False."
             )
 
-        # List images
+        # list images
         tmp_root = os.path.join(self.root, "image")
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         self.train = train
         np_dtype = np.float32
-        for img_path in tqdm(iterable=os.listdir(tmp_root), desc="Unpacking CORD", total=len(os.listdir(tmp_root))):
+        for img_path in tqdm(
+            iterable=os.listdir(tmp_root), desc="Preparing and Loading CORD", total=len(os.listdir(tmp_root))
+        ):
             # File existence check
             if not os.path.exists(os.path.join(tmp_root, img_path)):
                 raise FileNotFoundError(f"unable to locate {os.path.join(tmp_root, img_path)}")
@@ -91,7 +92,7 @@ class CORD(VisionDataset):
                         if len(word["text"]) > 0:
                             x = word["quad"]["x1"], word["quad"]["x2"], word["quad"]["x3"], word["quad"]["x4"]
                             y = word["quad"]["y1"], word["quad"]["y2"], word["quad"]["y3"], word["quad"]["y4"]
-                            box: Union[List[float], np.ndarray]
+                            box: list[float] | np.ndarray
                             if use_polygons:
                                 # (x, y) coordinates of top left, top right, bottom right, bottom left corners
                                 box = np.array(
@@ -115,7 +116,8 @@ class CORD(VisionDataset):
                     img_path=os.path.join(tmp_root, img_path), geoms=np.asarray(box_targets, dtype=int).clip(min=0)
                 )
                 for crop, label in zip(crops, list(text_targets)):
-                    self.data.append((crop, label))
+                    if " " not in label:
+                        self.data.append((crop, label))
             elif detection_task:
                 self.data.append((img_path, np.asarray(box_targets, dtype=int).clip(min=0)))
             else:

python_doctr-0.12.0/doctr/datasets/datasets/__init__.py

@@ -0,0 +1,6 @@
+from doctr.file_utils import is_tf_available, is_torch_available
+
+if is_torch_available():
+    from .pytorch import *
+elif is_tf_available():
+    from .tensorflow import *  # type: ignore[assignment]