python-doctr 0.11.0__tar.gz → 1.0.0__tar.gz

{python_doctr-0.11.0/python_doctr.egg-info → python_doctr-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: python-doctr
-Version: 0.11.0
+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
@@ -239,16 +242,8 @@ 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[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
@@ -276,10 +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"
@@ -302,15 +293,16 @@ 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-v0.11.0-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)
+[![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:
 
@@ -450,24 +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).
@@ -478,13 +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
@@ -504,6 +484,7 @@ 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
 
@@ -526,20 +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
 ```
@@ -547,23 +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).
@@ -578,7 +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`
@@ -587,7 +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`. |
 
@@ -599,10 +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-0.11.0 → python_doctr-1.0.0}/README.md

@@ -2,10 +2,10 @@
   <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-v0.11.0-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)
+[![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:
 
@@ -145,24 +145,15 @@ 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).
@@ -173,13 +164,10 @@ 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
@@ -199,6 +187,7 @@ 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
 
@@ -221,20 +210,6 @@ 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
 ```
@@ -242,23 +217,16 @@ 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).
@@ -273,7 +241,7 @@ 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`
@@ -282,7 +250,6 @@ 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`. |
 
@@ -294,10 +261,10 @@ 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-0.11.0 → python_doctr-1.0.0}/doctr/__init__.py

@@ -1,3 +1,2 @@
 from . import io, models, datasets, contrib, transforms, utils
-from .file_utils import is_tf_available, is_torch_available
 from .version import __version__  # noqa: F401

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/__init__.py

@@ -1,6 +1,5 @@
-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 *
@@ -21,6 +20,3 @@ from .synthtext import *
 from .utils import *
 from .vocabs import *
 from .wildreceipt import *
-
-if is_tf_available():
-    from .loader import *

python_doctr-1.0.0/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-0.11.0 → python_doctr-1.0.0}/doctr/datasets/cord.py

@@ -116,7 +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-1.0.0/doctr/datasets/datasets/__init__.py

@@ -0,0 +1 @@
+from .pytorch import *

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/datasets/pytorch.py

@@ -50,9 +50,9 @@ class AbstractDataset(_AbstractDataset):
     @staticmethod
     def collate_fn(samples: list[tuple[torch.Tensor, Any]]) -> tuple[torch.Tensor, list[Any]]:
         images, targets = zip(*samples)
-        images = torch.stack(images, dim=0)
+        images = torch.stack(images, dim=0)  # type: ignore[assignment]
 
-        return images, list(targets)
+        return images, list(targets)  # type: ignore[return-value]
 
 
 class VisionDataset(AbstractDataset, _VisionDataset):  # noqa: D101

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/funsd.py

@@ -107,8 +107,8 @@ class FUNSD(VisionDataset):
                 )
                 for crop, label in zip(crops, list(text_targets)):
                     # filter labels with unknown characters
-                    if not any(char in label for char in ["☑", "☐", "\uf703", "\uf702"]):
-                        self.data.append((crop, label))
+                    if not any(char in label for char in ["☑", "☐", "\u03bf", "\uf703", "\uf702", " "]):
+                        self.data.append((crop, label.replace("–", "-")))
             elif detection_task:
                 self.data.append((img_path, np.asarray(box_targets, dtype=np_dtype)))
             else:

python_doctr-1.0.0/doctr/datasets/generator/__init__.py

@@ -0,0 +1 @@
+from .pytorch import *

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/ic03.py

@@ -122,7 +122,7 @@ class IC03(VisionDataset):
                 if recognition_task:
                     crops = crop_bboxes_from_image(img_path=os.path.join(tmp_root, name.text), geoms=boxes)
                     for crop, label in zip(crops, labels):
-                        if crop.shape[0] > 0 and crop.shape[1] > 0 and len(label) > 0:
+                        if crop.shape[0] > 0 and crop.shape[1] > 0 and len(label) > 0 and " " not in label:
                             self.data.append((crop, label))
                 elif detection_task:
                     self.data.append((name.text, boxes))

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/ic13.py

@@ -100,7 +100,8 @@ class IC13(AbstractDataset):
             if recognition_task:
                 crops = crop_bboxes_from_image(img_path=img_path, geoms=box_targets)
                 for crop, label in zip(crops, labels):
-                    self.data.append((crop, label))
+                    if " " not in label:
+                        self.data.append((crop, label))
             elif detection_task:
                 self.data.append((img_path, box_targets))
             else:

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/iiit5k.py

@@ -8,6 +8,7 @@ from typing import Any
 
 import numpy as np
 import scipy.io as sio
+from PIL import Image
 from tqdm import tqdm
 
 from .datasets import VisionDataset
@@ -98,7 +99,9 @@ class IIIT5K(VisionDataset):
                 box_targets = [[box[0], box[1], box[0] + box[2], box[1] + box[3]] for box in box_targets]
 
             if recognition_task:
-                self.data.append((_raw_path, _raw_label))
+                if " " not in _raw_label:
+                    with Image.open(os.path.join(tmp_root, _raw_path)) as pil_img:
+                        self.data.append((np.array(pil_img.convert("RGB")), _raw_label))
             elif detection_task:
                 self.data.append((_raw_path, np.asarray(box_targets, dtype=np_dtype)))
             else:

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/imgur5k.py

@@ -133,7 +133,13 @@ class IMGUR5K(AbstractDataset):
                         img_path=os.path.join(self.root, img_name), geoms=np.asarray(box_targets, dtype=np_dtype)
                     )
                     for crop, label in zip(crops, labels):
-                        if crop.shape[0] > 0 and crop.shape[1] > 0 and len(label) > 0:
+                        if (
+                            crop.shape[0] > 0
+                            and crop.shape[1] > 0
+                            and len(label) > 0
+                            and len(label) < 30
+                            and " " not in label
+                        ):
                             # write data to disk
                             with open(os.path.join(reco_folder_path, f"{reco_images_counter}.txt"), "w") as f:
                                 f.write(label)
@@ -152,6 +158,7 @@ class IMGUR5K(AbstractDataset):
         return f"train={self.train}"
 
     def _read_from_folder(self, path: str) -> None:
-        for img_path in glob.glob(os.path.join(path, "*.png")):
+        img_paths = glob.glob(os.path.join(path, "*.png"))
+        for img_path in tqdm(iterable=img_paths, desc="Preparing and Loading IMGUR5K", total=len(img_paths)):
             with open(os.path.join(path, f"{os.path.basename(img_path)[:-4]}.txt"), "r") as f:
                 self.data.append((img_path, f.read()))

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/ocr.py

@@ -40,7 +40,7 @@ class OCRDataset(AbstractDataset):
         super().__init__(img_folder, **kwargs)
 
         # List images
-        self.data: list[tuple[str, dict[str, Any]]] = []
+        self.data: list[tuple[Path, dict[str, Any]]] = []
         np_dtype = np.float32
         with open(label_file, "rb") as f:
             data = json.load(f)

{python_doctr-0.11.0 → python_doctr-1.0.0}/doctr/datasets/recognition.py

@@ -23,7 +23,7 @@ class RecognitionDataset(AbstractDataset):
 
     Args:
         img_folder: path to the images folder
-        labels_path: pathe to the json file containing all labels (character sequences)
+        labels_path: path to the json file containing all labels (character sequences)
         **kwargs: keyword arguments from `AbstractDataset`.
     """