python-doctr 0.9.0__tar.gz → 0.11.0__tar.gz

{python_doctr-0.9.0 → python_doctr-0.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: python-doctr
-Version: 0.9.0
+Version: 0.11.0
 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
@@ -219,14 +219,14 @@ 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<2.0.0,>=1.16.0
+Requires-Dist: numpy<3.0.0,>=1.16.0
 Requires-Dist: scipy<2.0.0,>=1.4.0
 Requires-Dist: h5py<4.0.0,>=3.1.0
 Requires-Dist: opencv-python<5.0.0,>=4.5.0
@@ -241,11 +241,13 @@ Requires-Dist: defusedxml>=0.7.0
 Requires-Dist: anyascii>=0.3.2
 Requires-Dist: tqdm>=4.30.0
 Provides-Extra: tf
-Requires-Dist: tensorflow<2.16.0,>=2.11.0; 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
-Requires-Dist: torch<3.0.0,>=1.12.0; extra == "torch"
-Requires-Dist: torchvision>=0.13.0; extra == "torch"
+Requires-Dist: torch<3.0.0,>=2.0.0; extra == "torch"
+Requires-Dist: torchvision>=0.15.0; extra == "torch"
 Requires-Dist: onnx<3.0.0,>=1.12.0; extra == "torch"
 Provides-Extra: html
 Requires-Dist: weasyprint>=55.0; extra == "html"
@@ -257,7 +259,6 @@ Requires-Dist: onnxruntime>=1.11.0; extra == "contrib"
 Provides-Extra: testing
 Requires-Dist: pytest>=5.3.2; extra == "testing"
 Requires-Dist: coverage[toml]>=4.5.4; extra == "testing"
-Requires-Dist: hdf5storage>=0.1.18; extra == "testing"
 Requires-Dist: onnxruntime>=1.11.0; extra == "testing"
 Requires-Dist: requests>=2.20.0; extra == "testing"
 Requires-Dist: psutil>=5.9.5; extra == "testing"
@@ -275,17 +276,18 @@ 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<2.16.0,>=2.11.0; 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,>=1.12.0; extra == "dev"
-Requires-Dist: torchvision>=0.13.0; extra == "dev"
+Requires-Dist: torch<3.0.0,>=2.0.0; extra == "dev"
+Requires-Dist: torchvision>=0.15.0; extra == "dev"
 Requires-Dist: onnx<3.0.0,>=1.12.0; extra == "dev"
 Requires-Dist: weasyprint>=55.0; extra == "dev"
 Requires-Dist: matplotlib>=3.1.0; extra == "dev"
 Requires-Dist: mplcursors>=0.3; extra == "dev"
 Requires-Dist: pytest>=5.3.2; extra == "dev"
 Requires-Dist: coverage[toml]>=4.5.4; extra == "dev"
-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"
@@ -305,7 +307,7 @@ Requires-Dist: furo>=2022.3.4; extra == "dev"
   <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-v0.11.0-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**
@@ -438,7 +440,7 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 ### 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
 
@@ -464,7 +466,7 @@ pip install "python-doctr[torch,viz,html,contib]"
 For MacBooks with M1 chip, you will need some additional packages or specific versions:
 
 - TensorFlow 2: [metal plugin](https://developer.apple.com/metal/tensorflow-plugin/)
-- PyTorch: [version >= 1.12.0](https://pytorch.org/get-started/locally/#start-locally)
+- PyTorch: [version >= 2.0.0](https://pytorch.org/get-started/locally/#start-locally)
 
 ### Developer mode
 
@@ -557,37 +559,37 @@ 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-0.9.0 → python_doctr-0.11.0}/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-v0.11.0-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**
@@ -135,7 +135,7 @@ The KIE predictor results per page are in a dictionary format with each key repr
 
 ### 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
 
@@ -161,7 +161,7 @@ pip install "python-doctr[torch,viz,html,contib]"
 For MacBooks with M1 chip, you will need some additional packages or specific versions:
 
 - TensorFlow 2: [metal plugin](https://developer.apple.com/metal/tensorflow-plugin/)
-- PyTorch: [version >= 1.12.0](https://pytorch.org/get-started/locally/#start-locally)
+- PyTorch: [version >= 2.0.0](https://pytorch.org/get-started/locally/#start-locally)
 
 ### Developer mode
 
@@ -254,37 +254,37 @@ 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-0.11.0/doctr/contrib/__init__.py

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

{python_doctr-0.9.0 → python_doctr-0.11.0}/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-0.9.0 → python_doctr-0.11.0}/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-0.9.0 → python_doctr-0.11.0}/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
@@ -29,10 +29,10 @@ 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
+        detection_task: whether the dataset should be used for detection task
         **kwargs: keyword arguments from `VisionDataset`.
     """
 
@@ -53,6 +53,7 @@ class CORD(VisionDataset):
         train: bool = True,
         use_polygons: bool = False,
         recognition_task: bool = False,
+        detection_task: bool = False,
         **kwargs: Any,
     ) -> None:
         url, sha256, name = self.TRAIN if train else self.TEST
@@ -64,13 +65,20 @@ class CORD(VisionDataset):
             pre_transforms=convert_target_to_relative if not recognition_task else None,
             **kwargs,
         )
+        if recognition_task and detection_task:
+            raise ValueError(
+                "`recognition_task` and `detection_task` cannot be set to True simultaneously. "
+                + "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]]]] = []
+        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)}")
@@ -84,7 +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(
@@ -109,6 +117,8 @@ class CORD(VisionDataset):
                 )
                 for crop, label in zip(crops, list(text_targets)):
                     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,

python_doctr-0.11.0/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]

{python_doctr-0.9.0 → python_doctr-0.11.0}/doctr/datasets/datasets/base.py

@@ -1,12 +1,13 @@
-# 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.
 
 import os
 import shutil
+from collections.abc import Callable
 from pathlib import Path
-from typing import Any, Callable, List, Optional, Tuple, Union
+from typing import Any
 
 import numpy as np
 
@@ -19,15 +20,15 @@ __all__ = ["_AbstractDataset", "_VisionDataset"]
 
 
 class _AbstractDataset:
-    data: List[Any] = []
-    _pre_transforms: Optional[Callable[[Any, Any], Tuple[Any, Any]]] = None
+    data: list[Any] = []
+    _pre_transforms: Callable[[Any, Any], tuple[Any, Any]] | None = None
 
     def __init__(
         self,
-        root: Union[str, Path],
-        img_transforms: Optional[Callable[[Any], Any]] = None,
-        sample_transforms: Optional[Callable[[Any, Any], Tuple[Any, Any]]] = None,
-        pre_transforms: Optional[Callable[[Any, Any], Tuple[Any, Any]]] = None,
+        root: str | Path,
+        img_transforms: Callable[[Any], Any] | None = None,
+        sample_transforms: Callable[[Any, Any], tuple[Any, Any]] | None = None,
+        pre_transforms: Callable[[Any, Any], tuple[Any, Any]] | None = None,
     ) -> None:
         if not Path(root).is_dir():
             raise ValueError(f"expected a path to a reachable folder: {root}")
@@ -41,10 +42,10 @@ class _AbstractDataset:
     def __len__(self) -> int:
         return len(self.data)
 
-    def _read_sample(self, index: int) -> Tuple[Any, Any]:
+    def _read_sample(self, index: int) -> tuple[Any, Any]:
         raise NotImplementedError
 
-    def __getitem__(self, index: int) -> Tuple[Any, Any]:
+    def __getitem__(self, index: int) -> tuple[Any, Any]:
         # Read image
         img, target = self._read_sample(index)
         # Pre-transforms (format conversion at run-time etc.)
@@ -82,7 +83,6 @@ 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
@@ -96,13 +96,13 @@ class _VisionDataset(_AbstractDataset):
     def __init__(
         self,
         url: str,
-        file_name: Optional[str] = None,
-        file_hash: Optional[str] = None,
+        file_name: str | None = None,
+        file_hash: str | None = None,
         extract_archive: bool = False,
         download: bool = False,
         overwrite: bool = False,
-        cache_dir: Optional[str] = None,
-        cache_subdir: Optional[str] = None,
+        cache_dir: str | None = None,
+        cache_subdir: str | None = None,
         **kwargs: Any,
     ) -> None:
         cache_dir = (
@@ -115,7 +115,7 @@ class _VisionDataset(_AbstractDataset):
 
         file_name = file_name if isinstance(file_name, str) else os.path.basename(url)
         # Download the file if not present
-        archive_path: Union[str, Path] = os.path.join(cache_dir, cache_subdir, file_name)
+        archive_path: str | Path = os.path.join(cache_dir, cache_subdir, file_name)
 
         if not os.path.exists(archive_path) and not download:
             raise ValueError("the dataset needs to be downloaded first with download=True")

{python_doctr-0.9.0 → python_doctr-0.11.0}/doctr/datasets/datasets/pytorch.py

@@ -1,11 +1,11 @@
-# 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.
 
 import os
 from copy import deepcopy
-from typing import Any, List, Tuple
+from typing import Any
 
 import numpy as np
 import torch
@@ -20,7 +20,7 @@ __all__ = ["AbstractDataset", "VisionDataset"]
 class AbstractDataset(_AbstractDataset):
     """Abstract class for all datasets"""
 
-    def _read_sample(self, index: int) -> Tuple[torch.Tensor, Any]:
+    def _read_sample(self, index: int) -> tuple[torch.Tensor, Any]:
         img_name, target = self.data[index]
 
         # Check target
@@ -29,14 +29,14 @@ class AbstractDataset(_AbstractDataset):
             assert "labels" in target, "Target should contain 'labels' key"
         elif isinstance(target, tuple):
             assert len(target) == 2
-            assert isinstance(target[0], str) or isinstance(
-                target[0], np.ndarray
-            ), "first element of the tuple should be a string or a numpy array"
+            assert isinstance(target[0], str) or isinstance(target[0], np.ndarray), (
+                "first element of the tuple should be a string or a numpy array"
+            )
             assert isinstance(target[1], list), "second element of the tuple should be a list"
         else:
-            assert isinstance(target, str) or isinstance(
-                target, np.ndarray
-            ), "Target should be a string or a numpy array"
+            assert isinstance(target, str) or isinstance(target, np.ndarray), (
+                "Target should be a string or a numpy array"
+            )
 
         # Read image
         img = (
@@ -48,11 +48,11 @@ class AbstractDataset(_AbstractDataset):
         return img, deepcopy(target)
 
     @staticmethod
-    def collate_fn(samples: List[Tuple[torch.Tensor, Any]]) -> Tuple[torch.Tensor, List[Any]]:
+    def collate_fn(samples: list[tuple[torch.Tensor, Any]]) -> tuple[torch.Tensor, list[Any]]:
         images, targets = zip(*samples)
-        images = torch.stack(images, dim=0)  # type: ignore[assignment]
+        images = torch.stack(images, dim=0)
 
-        return images, list(targets)  # type: ignore[return-value]
+        return images, list(targets)
 
 
 class VisionDataset(AbstractDataset, _VisionDataset):  # noqa: D101