python-doctr 0.12.0__py3-none-any.whl → 1.0.0__py3-none-any.whl

doctr/utils/geometry.py

@@ -390,14 +390,13 @@ def convert_to_relative_coords(geoms: np.ndarray, img_shape: tuple[int, int]) ->
     raise ValueError(f"invalid format for arg `geoms`: {geoms.shape}")
 
 
-def extract_crops(img: np.ndarray, boxes: np.ndarray, channels_last: bool = True) -> list[np.ndarray]:
+def extract_crops(img: np.ndarray, boxes: np.ndarray) -> list[np.ndarray]:
     """Created cropped images from list of bounding boxes
 
     Args:
         img: input image
         boxes: bounding boxes of shape (N, 4) where N is the number of boxes, and the relative
             coordinates (xmin, ymin, xmax, ymax)
-        channels_last: whether the channel dimensions is the last one instead of the last one
 
     Returns:
         list of cropped images
@@ -409,21 +408,19 @@ def extract_crops(img: np.ndarray, boxes: np.ndarray, channels_last: bool = True
 
     # Project relative coordinates
     _boxes = boxes.copy()
-    h, w = img.shape[:2] if channels_last else img.shape[-2:]
+    h, w = img.shape[:2]
     if not np.issubdtype(_boxes.dtype, np.integer):
         _boxes[:, [0, 2]] *= w
         _boxes[:, [1, 3]] *= h
         _boxes = _boxes.round().astype(int)
         # Add last index
         _boxes[2:] += 1
-    if channels_last:
-        return deepcopy([img[box[1] : box[3], box[0] : box[2]] for box in _boxes])
 
-    return deepcopy([img[:, box[1] : box[3], box[0] : box[2]] for box in _boxes])
+    return deepcopy([img[box[1] : box[3], box[0] : box[2]] for box in _boxes])
 
 
 def extract_rcrops(
-    img: np.ndarray, polys: np.ndarray, dtype=np.float32, channels_last: bool = True, assume_horizontal: bool = False
+    img: np.ndarray, polys: np.ndarray, dtype=np.float32, assume_horizontal: bool = False
 ) -> list[np.ndarray]:
     """Created cropped images from list of rotated bounding boxes
 
@@ -431,7 +428,6 @@ def extract_rcrops(
         img: input image
         polys: bounding boxes of shape (N, 4, 2)
         dtype: target data type of bounding boxes
-        channels_last: whether the channel dimensions is the last one instead of the last one
         assume_horizontal: whether the boxes are assumed to be only horizontally oriented
 
     Returns:
@@ -444,12 +440,12 @@ def extract_rcrops(
 
     # Project relative coordinates
     _boxes = polys.copy()
-    height, width = img.shape[:2] if channels_last else img.shape[-2:]
+    height, width = img.shape[:2]
     if not np.issubdtype(_boxes.dtype, np.integer):
         _boxes[:, :, 0] *= width
         _boxes[:, :, 1] *= height
 
-    src_img = img if channels_last else img.transpose(1, 2, 0)
+    src_img = img
 
     # Handle only horizontal oriented boxes
     if assume_horizontal:

doctr/utils/visualization.py

@@ -148,7 +148,7 @@ def get_colors(num_colors: int) -> list[tuple[float, float, float]]:
         hue = i / 360.0
         lightness = (50 + np.random.rand() * 10) / 100.0
         saturation = (90 + np.random.rand() * 10) / 100.0
-        colors.append(colorsys.hls_to_rgb(hue, lightness, saturation))
+        colors.append(colorsys.hls_to_rgb(hue, lightness, saturation))  # type: ignore[arg-type]
     return colors
 
 

doctr/version.py

@@ -1 +1 @@
-__version__ = 'v0.12.0'
+__version__ = 'v1.0.0'

{python_doctr-0.12.0.dist-info → python_doctr-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-doctr
-Version: 0.12.0
+Version: 1.0.0
 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
@@ -210,7 +210,7 @@ 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://mindee.github.io/doctr/changelog.html
-Keywords: OCR,deep learning,computer vision,tensorflow,pytorch,text detection,text recognition
+Keywords: OCR,deep learning,computer vision,pytorch,text detection,text recognition
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Education
@@ -226,6 +226,9 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: <4,>=3.10.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: torch<3.0.0,>=2.0.0
+Requires-Dist: torchvision>=0.15.0
+Requires-Dist: onnx<3.0.0,>=1.12.0
 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
@@ -241,15 +244,6 @@ 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[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,>=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"
 Provides-Extra: viz
@@ -277,10 +271,6 @@ 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[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"
 Requires-Dist: torchvision>=0.15.0; extra == "dev"
 Requires-Dist: onnx<3.0.0,>=1.12.0; extra == "dev"
@@ -309,10 +299,10 @@ Dynamic: license-file
   <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-v0.12.0-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)
+[![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-v1.0.0-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**
+**Optical Character Recognition made seamless & accessible to anyone, powered by PyTorch**
 
 What you can expect from this repository:
 
@@ -440,19 +430,6 @@ 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 3.10 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to install docTR.
@@ -465,24 +442,15 @@ You can then install the latest release of the package using [pypi](https://pypi
 pip install python-doctr
 ```
 
-> :warning: Please note that the basic installation is not standalone, as it does not provide a deep learning framework, which is required for the package to run.
-
-We try to keep framework-specific dependencies to a minimum. You can install framework-specific builds as follows:
+We try to keep extra dependencies to a minimum. You can install specific builds as follows:
 
 ```shell
-# for TensorFlow
-pip install "python-doctr[tf]"
-# for PyTorch
-pip install "python-doctr[torch]"
+# standard build
+pip install python-doctr
 # optional dependencies for visualization, html, and contrib modules can be installed as follows:
-pip install "python-doctr[torch,viz,html,contib]"
+pip install "python-doctr[viz,html,contrib]"
 ```
 
-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 >= 2.0.0](https://pytorch.org/get-started/locally/#start-locally)
-
 ### Developer mode
 
 Alternatively, you can install it from source, which will require you to install [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git).
@@ -493,13 +461,10 @@ git clone https://github.com/mindee/doctr.git
 pip install -e doctr/.
 ```
 
-Again, if you prefer to avoid the risk of missing dependencies, you can install the TensorFlow or the PyTorch build:
+Again, if you prefer to avoid the risk of missing dependencies, you can install the build:
 
 ```shell
-# for TensorFlow
-pip install -e doctr/.[tf]
-# for PyTorch
-pip install -e doctr/.[torch]
+pip install -e doctr/.
 ```
 
 ## Models architectures
@@ -542,20 +507,6 @@ Check it out [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%2
 
 If you prefer to use it locally, there is an extra dependency ([Streamlit](https://streamlit.io/)) that is required.
 
-##### Tensorflow version
-
-```shell
-pip install -r demo/tf-requirements.txt
-```
-
-Then run your app in your default browser with:
-
-```shell
-USE_TF=1 streamlit run demo/app.py
-```
-
-##### PyTorch version
-
 ```shell
 pip install -r demo/pt-requirements.txt
 ```
@@ -563,23 +514,16 @@ pip install -r demo/pt-requirements.txt
 Then run your app in your default browser with:
 
 ```shell
-USE_TORCH=1 streamlit run demo/app.py
+streamlit run demo/app.py
 ```
 
-#### TensorFlow.js
-
-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/raw/main/docs/images/demo_illustration_mini.png)
-
 ### Docker container
 
 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 `12.2`. Make sure your host is **at least `12.2`**, otherwise Torch or TensorFlow won't be able to initialize the 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 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).
@@ -594,7 +538,7 @@ docker run -it --gpus all ghcr.io/mindee/doctr:torch-py3.9.18-2024-10 bash
 
 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:
 
-- `<deps>`: `tf`, `torch`, `tf-viz-html-contrib` or `torch-viz-html-contrib`.
+- `<deps>`: `torch`, `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`
@@ -603,7 +547,6 @@ Here are examples of different image tags:
 
 | Tag                        | Description                                       |
 |----------------------------|---------------------------------------------------|
-| `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`. |
 
@@ -615,10 +558,10 @@ You can also build docTR Docker images locally on your computer.
 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:
+You can specify custom Python versions and docTR versions using build arguments. For example, to build a docTR image with PyTorch, Python version `3.9.10`, and docTR version `v0.7.0`, run the following command:
 
 ```shell
-docker build -t doctr --build-arg FRAMEWORK=tf --build-arg PYTHON_VERSION=3.9.10 --build-arg DOCTR_VERSION=v0.7.0 .
+docker build -t doctr --build-arg FRAMEWORK=torch --build-arg PYTHON_VERSION=3.9.10 --build-arg DOCTR_VERSION=v0.7.0 .
 ```
 
 ### Example script

python_doctr-1.0.0.dist-info/RECORD

@@ -0,0 +1,149 @@
+doctr/__init__.py,sha256=sdqGeYFfPLRsRH54PsedllScz5FD8yWwyekcsOq3JNc,110
+doctr/file_utils.py,sha256=z2R4VoyDW2Y-P5VvrNJQhV8eOQkN9rCbm5khI8iqmHc,999
+doctr/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+doctr/version.py,sha256=kgXjUv1-JWgHAxO9DO1HCqJL8uFnPENHVFy5p7lbOc8,23
+doctr/contrib/__init__.py,sha256=EKeAGa3TOuJVWR4H_HJvuKO5VPEnJWXW305JMw3ufic,40
+doctr/contrib/artefacts.py,sha256=sIVEx21GIXKCaYG4RVRvXRmjyGkAdTI9O8GB8vIw8kc,5291
+doctr/contrib/base.py,sha256=g0VAg51NZNB5etQe3gZy-7kSm_NLzg26j7Jb4v8lLBk,3273
+doctr/datasets/__init__.py,sha256=QzWe91FU1d3Vi5h4ayPtJUE-Y_SSs_4Xp6MAkZ8XKTc,504
+doctr/datasets/coco_text.py,sha256=VXTnzgUpj3akmVuaUwzRTKc6wvtJGcUVkJeSlj5M3-M,5496
+doctr/datasets/cord.py,sha256=8xPawKP4rgTbxNJRwQT1MychXQWNY2vcZ9awbzgsRsM,5315
+doctr/datasets/detection.py,sha256=CXz_qzMw5SjjhEGtgl83YZIpN1sLXUqDKXm1rAfQNBU,3531
+doctr/datasets/doc_artefacts.py,sha256=h8NtwwZmC_xIlpJyJRi83dVuOFZPF_FhtK1v7f7aXlY,3230
+doctr/datasets/funsd.py,sha256=cbUrLa7fI2AFUzx4HRzHxIio6XOJuiV2RjwK6CQGkgM,4733
+doctr/datasets/ic03.py,sha256=7wtXRQaV_lG_I2sBrP17yCVZ3HegQUQrRaaAUUKlyxM,5564
+doctr/datasets/ic13.py,sha256=LEbSiGDBVywqBM_qJjzz6g9Qmd1hnpi2x_stHMSLz-Q,4528
+doctr/datasets/iiit5k.py,sha256=MeqqoJMlXNDabS04GvQvsdg77g_PmdR2zdzG97acBcQ,4583
+doctr/datasets/iiithws.py,sha256=cgitit-ePAtZFTO6tRZFNua7MuCJuXYzgkgHybqjnzk,2768
+doctr/datasets/imgur5k.py,sha256=o9epJAeZkrNNxs1BXIYlx4_dzrVrxMJgFGEaM_GwNvo,7525
+doctr/datasets/mjsynth.py,sha256=RuVtTjLtIe0tEOF5AibwmMx8Z_hdu3gE04jxQ1iMCz0,4075
+doctr/datasets/ocr.py,sha256=ON447DE1kvXLYwVgTtJ1vNnYo_Rf2drBxShPfhnJ7EY,2523
+doctr/datasets/orientation.py,sha256=HaF2dKyK7kDUFluY5B2mBtxw8nyO9UNOsbP1dDrD8Lk,1091
+doctr/datasets/recognition.py,sha256=RdGw1W_NOlzaVqQlOgGrAB01Z-x9UCJ7dQJdPUp0two,1858
+doctr/datasets/sroie.py,sha256=bKrsvw98zcEfOw5Re0F7-06MzJRv-E73t7BYwmSokoA,4430
+doctr/datasets/svhn.py,sha256=3c7jnAm9JVY3osO-crgQZDNNp1ArTtPHqigBulcQk48,5784
+doctr/datasets/svt.py,sha256=hOzr4QcKGSLj3qn3uG_6PYC3RdTWv9ouUX0JbmlW0qM,5046
+doctr/datasets/synthtext.py,sha256=G-xaVVuv445Kaus0OSA5cvjo0BTPsjB8QxZhFX3wfLA,6301
+doctr/datasets/utils.py,sha256=PDY9kwfqXzVUhy7QCtBF31bGs5boMrxSY-HWAoNSSrY,8106
+doctr/datasets/vocabs.py,sha256=dPhTl7E98cVdcRzA7LGqYcn5bOUN5wrnQMF-wfItfaI,99032
+doctr/datasets/wildreceipt.py,sha256=ipnLArx_CGDmmkegm6rQUxVGHzFF0EzJREcezY0ap7s,5213
+doctr/datasets/datasets/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/datasets/datasets/base.py,sha256=wxpVVYPLnuPBYFGIR-5vG_FDEzT8wx57xPaUipiM-6c,4826
+doctr/datasets/datasets/pytorch.py,sha256=wS7BkexqpFjIKJXIPMaSsSI8g-XxOexKOazofmIxJoI,2030
+doctr/datasets/generator/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/datasets/generator/base.py,sha256=xMymMfWhzQwsfpWGG6a7KxPP8T262ilUWrE0OelT90k,5706
+doctr/datasets/generator/pytorch.py,sha256=-6WD696LOS09Caq0ohHlivK22RTK2Ke3YwqAx8n8qQ8,2116
+doctr/io/__init__.py,sha256=kS7tKGFvzxOCWBOun-Y8n9CsziwRKNynjwpZEUUI03M,106
+doctr/io/elements.py,sha256=tdBiILkTeKci7nbbIYxHikf1-GQy5uBHHgc6ZbZbOP4,26474
+doctr/io/html.py,sha256=3wSKH5qD03f2RqxA7D_d8oEBRVdTs4lLVvFZCkR2jrc,698
+doctr/io/pdf.py,sha256=1fbmMKU4XAk4sY-wVES48_5EwMdGz4SiilAFcaPq94M,1308
+doctr/io/reader.py,sha256=yES-J4KVIMqG2X-LHriqLm1R6kyQWcNlOAnfkW9Vjsw,2732
+doctr/io/image/__init__.py,sha256=bJLj2I8OOTYLuTDjdinao0nkOIWQOLbzIuww23EX3gw,43
+doctr/io/image/base.py,sha256=fD6hfJ6myvxo_5LSUVbzOqExK-aSE0qi_l0MY3Pm0fQ,1681
+doctr/io/image/pytorch.py,sha256=ai8KMIzuPd9blcEZrOCzzEExXQ6DPk_DqgU49ihDWLY,3201
+doctr/models/__init__.py,sha256=yn_mXUL8B5L27Uaat1rLGRQHgLR8VLVxzBuPfNuN1YE,124
+doctr/models/_utils.py,sha256=c9gc3zQOADBFXHjWKtE9wqmp6Dh9bhiZqH3O_YPCQ8I,7353
+doctr/models/builder.py,sha256=UKZBuKutxA0iVM7i8owFdKiwQp9KwyC5Hb4Aio0l0hg,20370
+doctr/models/core.py,sha256=CAgymBtEsVAJ70SHdtaBroM67nbNf6osXN6dWC6qAF4,482
+doctr/models/zoo.py,sha256=89E60O61USlQ9a1bTP5SRY2_Gjk4pTvk3TNoCQC4AiI,9276
+doctr/models/classification/__init__.py,sha256=piTKyOGbTiKBzZSAHQLXf622mqjxaAJPicNtH3b-A0k,173
+doctr/models/classification/zoo.py,sha256=5g6zERM7Y-EYPr5GPgkELnIFHATyPVgJKhaZvHCBEbs,4265
+doctr/models/classification/magc_resnet/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/magc_resnet/pytorch.py,sha256=gl1rHozKCWhWyW5KY0RAjrTilbGkg_uHCiHvU-RlQSI,5480
+doctr/models/classification/mobilenet/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/mobilenet/pytorch.py,sha256=H1NwgxV8vni2vYsw2A9xSTnaXdToy4Xy_G-ZcRzC1mg,9826
+doctr/models/classification/predictor/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/predictor/pytorch.py,sha256=-9x4UaRY16lwrFMSpo808IHjXMQTYDryPY-uYnrEZA4,2523
+doctr/models/classification/resnet/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/resnet/pytorch.py,sha256=gmuJ0IfWTZSHgWij2rW81kfO5WjsvKxJ94SLSWjxmyA,13250
+doctr/models/classification/textnet/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/textnet/pytorch.py,sha256=oPt3oBN3HEID-WFlAtgcW7v--1Gov1x1RcktSzrLe40,10424
+doctr/models/classification/vgg/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/vgg/pytorch.py,sha256=LB3T1SALv6RG2P8v5p2R5lrpaGN7xtKCULqudIT5WCc,3679
+doctr/models/classification/vip/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/vip/pytorch.py,sha256=dKexvWprSWdE_y2iViqw-4GXFUnRRm4y0J1Lgme9kuo,16134
+doctr/models/classification/vip/layers/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/vip/layers/pytorch.py,sha256=FmVzFnDMVl1JlgKrJtxSTLmr3Qp3BqKo3eqJNvRMI1Q,21019
+doctr/models/classification/vit/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/classification/vit/pytorch.py,sha256=Cni9o9hw9OZMdi-XfMRA0P7mWQtik9Oaf6DXfh50CEk,6371
+doctr/models/detection/__init__.py,sha256=RqSz5beehLiqhW0PwFLFmCfTyMjofO-0umcQJLDMHjY,105
+doctr/models/detection/core.py,sha256=-fHsDHgCBMi0FenckvJD1-Vwc1N1mdLXtxLIN9IXB50,3444
+doctr/models/detection/zoo.py,sha256=95fHBUJure77kstR-b6gDXfep-kKpXqsgy6bV63diPc,3671
+doctr/models/detection/_utils/__init__.py,sha256=bJLj2I8OOTYLuTDjdinao0nkOIWQOLbzIuww23EX3gw,43
+doctr/models/detection/_utils/base.py,sha256=fi8XLUVcWG4J-dhxHeTuB6gYL_brt02T0HIP0TVR8jQ,2475
+doctr/models/detection/_utils/pytorch.py,sha256=81AlwGUZGmqCF18Svh_Mwm96-MPXYg-iR6xHXCEE3u0,1021
+doctr/models/detection/differentiable_binarization/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/detection/differentiable_binarization/base.py,sha256=1NNEPt8rlTZrmYNYUhZj56ex9BQVTW6eQbSYDLh2oUM,15788
+doctr/models/detection/differentiable_binarization/pytorch.py,sha256=MBa3nLufNQywn7GMQl0RHQd-ZMZzKNYjZXzzKA9QmSc,16453
+doctr/models/detection/fast/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/detection/fast/base.py,sha256=714-NSdvjjGz3YsdURRHPzSV-K6DJO0F0UygyAUjKBM,10225
+doctr/models/detection/fast/pytorch.py,sha256=i0UQMOn1g_YtF3WVWWyYAANQqiOBl1r837rUaNaA0ws,16702
+doctr/models/detection/linknet/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/detection/linknet/base.py,sha256=avY0YeCv8-IL0TiDmxaI04UdUZY5dTmDn3TbM0uEVLM,10007
+doctr/models/detection/linknet/pytorch.py,sha256=nEV06dEFzSlFw517EUpFZ_bF8oU6xKxjyWdgbzU9c74,14333
+doctr/models/detection/predictor/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/detection/predictor/pytorch.py,sha256=UyxTh3SPXGohU7oMu11xnwiOg-xD3HOkMlIz48cgA5M,2627
+doctr/models/factory/__init__.py,sha256=cKPoH2V2157lLMTR2zsljG3_IQHziodqR-XK_LG0D_I,19
+doctr/models/factory/hub.py,sha256=XYCdnwD2zThM2ZHmz0EexCEL5Ag4IdvbXxFhaQyptLM,6893
+doctr/models/kie_predictor/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/kie_predictor/base.py,sha256=c8mmLJMLlpnVb5GNDP3hm-oefZ42fbk2dkmKMYVf8Gc,2291
+doctr/models/kie_predictor/pytorch.py,sha256=2-iF5a0VUGg-PKifyhxX8F3BruL68ZW2GpQ5OpzagXU,7704
+doctr/models/modules/__init__.py,sha256=pouP7obVTu4p6aHkyaqa1yHKbynpvT0Hgo-LO_1U2R4,83
+doctr/models/modules/layers/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/modules/layers/pytorch.py,sha256=uH-plEGsdm4BzQ6iuIiWZhJnnYovwUO6fnu7FzX8SaI,8667
+doctr/models/modules/transformer/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/modules/transformer/pytorch.py,sha256=MiJMXMbotK9pAl1ITtitGjho86dxqnQBH9SfEjwJqHs,7657
+doctr/models/modules/vision_transformer/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/modules/vision_transformer/pytorch.py,sha256=Tpl-zdePOXj_uHJvnfsg-IAZ5cb3klE2rvJKugppjaI,3943
+doctr/models/predictor/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/predictor/base.py,sha256=73-otJgr4FVEONv2aijMxv1hcp2qd0lAUMgRlqmdkKQ,8541
+doctr/models/predictor/pytorch.py,sha256=_fL3sZTMh_MWzdgzJOf6y2Rv31GKzw0s2Av-H2bDICY,6241
+doctr/models/preprocessor/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/preprocessor/pytorch.py,sha256=m5UHLKXh6n0gp1NAIWe05IYZbhYXOK9-yjU7jRMLVvw,4395
+doctr/models/recognition/__init__.py,sha256=bgAvbwjO14Z2RQFD2XKZcSYJNsyxPa96SGHmX_nqbAQ,145
+doctr/models/recognition/core.py,sha256=VLfNOFc9lx6YOLCOK3f7lRuIS9lMXDSvs6je3FmfaZ0,1524
+doctr/models/recognition/utils.py,sha256=W5zwcv7bIjg_Mr-cH_x6JBe9brCBQvUB1IZNFiN6T-Y,3739
+doctr/models/recognition/zoo.py,sha256=j4lRRFlBtSqQl5C0-jrZPJWFspuAPo81GKhQ06tfEWc,2991
+doctr/models/recognition/crnn/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/recognition/crnn/pytorch.py,sha256=mZsoRVvCRL6pZaXkyjtPTMemXVHpEwEqPkjXDRa6wb4,12234
+doctr/models/recognition/master/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/recognition/master/base.py,sha256=SFo8AyoSC8sCkelPiVXB6dBVcdAmZVObCzzel0_RXM4,1471
+doctr/models/recognition/master/pytorch.py,sha256=taUk6_LJd4FHpXLhe3uO1eEIYzra4OyoGynWPwQ8Ohg,12756
+doctr/models/recognition/parseq/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/recognition/parseq/base.py,sha256=C-J0mm1kWmiVH3X_A1GZizmtqzVYzkFb8Z2bb9e5uww,1465
+doctr/models/recognition/parseq/pytorch.py,sha256=FlYL89YCKEgWjDbOeZSzH03ufCRX3EqY6k6exNUmNrM,20801
+doctr/models/recognition/predictor/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/recognition/predictor/_utils.py,sha256=qRuVsPECmuokPWbbM4JjKR1L8VHBbk0w8LSyYMGdYfA,4695
+doctr/models/recognition/predictor/pytorch.py,sha256=96FIIQl1ZSQMvx6a1Q6HQnvPNNC9T7rusP2SegO3hQo,2753
+doctr/models/recognition/sar/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/recognition/sar/pytorch.py,sha256=cYqNvOIE0tESKrZ-J1mStbf7YxKUpht0GHQgYnhrbJQ,15639
+doctr/models/recognition/viptr/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/recognition/viptr/pytorch.py,sha256=dQP3s76kmSx8M7EQ0A5hoDYB8MMsaaAw2m5cNTRDqvo,9355
+doctr/models/recognition/vitstr/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/recognition/vitstr/base.py,sha256=5ZjYF0WPgH5sSSaoHeoiw4Os2IZey-souszvkYKgzV8,1419
+doctr/models/recognition/vitstr/pytorch.py,sha256=N_7YShzNGNjSS64Uj8b9rbOIwBvVkbqMRitMR5kiwAI,10080
+doctr/models/utils/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/models/utils/pytorch.py,sha256=8ENZmoOmyTi4X1fOgcEo7_RnfWIvSrh8TkELYB7zv04,5782
+doctr/transforms/__init__.py,sha256=0VHbvUZ7llFd1e_7_JdWTaxYMCvaR6KbUJaYJequmQI,23
+doctr/transforms/functional/__init__.py,sha256=hxLu7FmRYn01ysoOQalrMa5K_qg4rLNf8OAuoemzd6I,23
+doctr/transforms/functional/base.py,sha256=K3taCHB1WGIWJ1FE47VPONZFPr2iAU1wgy6S8fRuODA,6842
+doctr/transforms/functional/pytorch.py,sha256=_imUaMkfk4-9L7ipZ1FpNweWApD9Q0Hup10_Ixm8V5A,5102
+doctr/transforms/modules/__init__.py,sha256=bJLj2I8OOTYLuTDjdinao0nkOIWQOLbzIuww23EX3gw,43
+doctr/transforms/modules/base.py,sha256=M8K-g4Q1KKZYJA52QKloE8vR-DE2wK4RP8rhKjFnfm0,7678
+doctr/transforms/modules/pytorch.py,sha256=IiK4AKvKGIhMKe1G3dJzGuINbLnSA3AX0dcN2Q8VId4,11802
+doctr/utils/__init__.py,sha256=uQY9ibZ24V896fmihIsK23QOIZdKtk0HyKoCVJ_lLuM,95
+doctr/utils/common_types.py,sha256=ebBlz_61A2gUp_CD2R_8o1pJ5CpCSJimJWzAyGas1uQ,534
+doctr/utils/data.py,sha256=2yv95B2t9b5Hd-SGgEWGqe8ooBrrl-k-kxBd8Ig0SuM,4188
+doctr/utils/fonts.py,sha256=1vEakG5wfOe-XmsXC63Pi_nox6XZaoHcDsJPjafGo-Q,1265
+doctr/utils/geometry.py,sha256=-oKDdCYq7MRYms8kp1ui_rx7HrmhYZhmglwgtCE_DG0,18678
+doctr/utils/metrics.py,sha256=u2d9nz5NY3gHKpmj5DlcK9OjMlB6zwoZrr-vxVntvp4,20249
+doctr/utils/multithreading.py,sha256=FinxQSGRpMs6WL8paixeOGd5CNAkG2VYqC-5d1izYBE,1972
+doctr/utils/reconstitution.py,sha256=mWEGVPhtxnVDKbUDr8E1tad4HaGISGC3DenJvm8I0uM,7256
+doctr/utils/repr.py,sha256=zw4vLHFIqpTGqsEFosGLkM7aLAjy6RLu_yUz5SyI_YA,2087
+doctr/utils/visualization.py,sha256=fUnmwjIUsh8rfqUWf-eDAycK5RAVO28r0krc0gq96Z0,13118
+python_doctr-1.0.0.dist-info/licenses/LICENSE,sha256=75RTSsXOsAYhGpxsHc9U41ep6GS7vrUPufeekgoeOXM,11336
+python_doctr-1.0.0.dist-info/METADATA,sha256=JlKh78_1zbnvhgyLvlwDd6-U_c1fGu59JG-2qleSugI,32161
+python_doctr-1.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+python_doctr-1.0.0.dist-info/top_level.txt,sha256=lCgp4pmjPI3HYph62XhfzA3jRwM715kGtJPmqIUJ9t8,6
+python_doctr-1.0.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+python_doctr-1.0.0.dist-info/RECORD,,

doctr/datasets/datasets/tensorflow.py

@@ -1,59 +0,0 @@
-# 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
-
-import numpy as np
-import tensorflow as tf
-
-from doctr.io import read_img_as_tensor, tensor_from_numpy
-
-from .base import _AbstractDataset, _VisionDataset
-
-__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]
-
-        # Check target
-        if isinstance(target, dict):
-            assert "boxes" in target, "Target should contain 'boxes' key"
-            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[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"
-            )
-
-        # Read image
-        img = (
-            tensor_from_numpy(img_name, dtype=tf.float32)
-            if isinstance(img_name, np.ndarray)
-            else read_img_as_tensor(os.path.join(self.root, img_name), dtype=tf.float32)
-        )
-
-        return img, deepcopy(target)
-
-    @staticmethod
-    def collate_fn(samples: list[tuple[tf.Tensor, Any]]) -> tuple[tf.Tensor, list[Any]]:
-        images, targets = zip(*samples)
-        images = tf.stack(images, axis=0)
-
-        return images, list(targets)
-
-
-class VisionDataset(AbstractDataset, _VisionDataset):  # noqa: D101
-    pass

doctr/datasets/generator/tensorflow.py

@@ -1,58 +0,0 @@
-# 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 tensorflow as tf
-
-from .base import _CharacterGenerator, _WordGenerator
-
-__all__ = ["CharacterGenerator", "WordGenerator"]
-
-
-class CharacterGenerator(_CharacterGenerator):
-    """Implements a character image generation dataset
-
-    >>> from doctr.datasets import CharacterGenerator
-    >>> ds = CharacterGenerator(vocab='abdef', num_samples=100)
-    >>> 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
-        font_family: font to use to generate the text images
-        img_transforms: composable transformations that will be applied to each image
-        sample_transforms: composable transformations that will be applied to both the image and the target
-    """
-
-    def __init__(self, *args, **kwargs) -> None:
-        super().__init__(*args, **kwargs)
-
-    @staticmethod
-    def collate_fn(samples):
-        images, targets = zip(*samples)
-        images = tf.stack(images, axis=0)
-
-        return images, tf.convert_to_tensor(targets)
-
-
-class WordGenerator(_WordGenerator):
-    """Implements a character image generation dataset
-
-    >>> from doctr.datasets import WordGenerator
-    >>> ds = WordGenerator(vocab='abdef', min_chars=1, max_chars=32, num_samples=100)
-    >>> 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
-        num_samples: number of samples that will be generated iterating over the dataset
-        cache_samples: whether generated images should be cached firsthand
-        font_family: font to use to generate the text images
-        img_transforms: composable transformations that will be applied to each image
-        sample_transforms: composable transformations that will be applied to both the image and the target
-    """
-
-    pass

doctr/datasets/loader.py

@@ -1,94 +0,0 @@
-# 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 math
-from collections.abc import Callable
-
-import numpy as np
-import tensorflow as tf
-
-__all__ = ["DataLoader"]
-
-
-def default_collate(samples):
-    """Collate multiple elements into batches
-
-    Args:
-        samples: list of N tuples containing M elements
-
-    Returns:
-        tuple of M sequences containing N elements each
-    """
-    batch_data = zip(*samples)
-
-    tf_data = tuple(tf.stack(elt, axis=0) for elt in batch_data)
-
-    return tf_data
-
-
-class DataLoader:
-    """Implements a dataset wrapper for fast data loading
-
-    >>> from doctr.datasets import CORD, DataLoader
-    >>> train_set = CORD(train=True, download=True)
-    >>> train_loader = DataLoader(train_set, batch_size=32)
-    >>> train_iter = iter(train_loader)
-    >>> images, targets = next(train_iter)
-
-    Args:
-        dataset: the dataset
-        shuffle: whether the samples should be shuffled before passing it to the iterator
-        batch_size: number of elements in each batch
-        drop_last: if `True`, drops the last batch if it isn't full
-        collate_fn: function to merge samples into a batch
-    """
-
-    def __init__(
-        self,
-        dataset,
-        shuffle: bool = True,
-        batch_size: int = 1,
-        drop_last: bool = False,
-        collate_fn: Callable | None = None,
-    ) -> None:
-        self.dataset = dataset
-        self.shuffle = shuffle
-        self.batch_size = batch_size
-        nb = len(self.dataset) / batch_size
-        self.num_batches = math.floor(nb) if drop_last else math.ceil(nb)
-        if collate_fn is None:
-            self.collate_fn = self.dataset.collate_fn if hasattr(self.dataset, "collate_fn") else default_collate
-        else:
-            self.collate_fn = collate_fn
-        self.reset()
-
-    def __len__(self) -> int:
-        return self.num_batches
-
-    def reset(self) -> None:
-        # Updates indices after each epoch
-        self._num_yielded = 0
-        self.indices = np.arange(len(self.dataset))
-        if self.shuffle is True:
-            np.random.shuffle(self.indices)
-
-    def __iter__(self):
-        self.reset()
-        return self
-
-    def __next__(self):
-        if self._num_yielded < self.num_batches:
-            # Get next indices
-            idx = self._num_yielded * self.batch_size
-            indices = self.indices[idx : min(len(self.dataset), idx + self.batch_size)]
-
-            samples = list(map(self.dataset.__getitem__, indices))
-
-            batch_data = self.collate_fn(samples)
-
-            self._num_yielded += 1
-            return batch_data
-        else:
-            raise StopIteration