feat: ✨ Official docker images for docTR

.github/workflows/docker.yml

@@ -14,7 +14,7 @@ jobs:
       - name: Build docker image
         run: docker build . -t doctr-tf-py3.8-slim
       - name: Run docker container
-        run: docker run doctr-tf-py3.8-slim python -c 'import doctr'
+        run: docker run doctr-tf-py3.8-slim python3 -c 'import doctr'
 
   pytest-api:
     runs-on: ${{ matrix.os }}

.github/workflows/public_docker_images.yml

@@ -0,0 +1,89 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+#
+name: Docker image on ghcr.io
+
+on:
+  push:
+    tags:
+      - 'v*'
+  pull_request:
+    branches: main
+  schedule:
+    - cron: '0 2 29 * *'  # At 02:00 on day-of-month 29
+
+env:
+  REGISTRY: ghcr.io
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        # Must match version at https://www.python.org/ftp/python/
+        python: ["3.8.18", "3.9.18", "3.10.13"]
+        framework: ["tf", "torch"]
+        system: ["cpu", "gpu"]
+
+    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
+        with:
+          images: ${{ env.REGISTRY }}/${{ github.repository }}
+          tags: |
+            # used only on schedule event
+            type=schedule,pattern={{date 'YYYY-MM'}},prefix=${{ matrix.framework }}-py${{ matrix.python }}-${{ matrix.system }}-
+            # set latest tag only if `enable` is True
+            # see https://github.com/docker/metadata-action#latest-tag
+            type=raw,value=latest,enable=${{ matrix.framework == 'tf' && matrix.python == '3.8.18' && matrix.system == 'gpu' && github.ref == format('refs/heads/{0}', 'main') }}
+            # used only if a tag following semver is published
+            type=semver,pattern={{raw}},prefix=${{ matrix.framework }}-py${{ matrix.python }}-${{ matrix.system }}-
+
+      - name: Build Docker image
+        id: build
+        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
+        with:
+          context: .
+          build-args: |
+            FRAMEWORK=${{ matrix.framework }}
+            PYTHON_VERSION=${{ matrix.python }}
+            SYSTEM=${{ matrix.system }}
+            DOCTR_REPO=${{ github.repository }}
+            DOCTR_VERSION=${{ github.sha }}
+          push: false  # push only if `import doctr` works
+          tags: ${{ steps.meta.outputs.tags }}
+
+      - name: Check if `import doctr` works
+        run: docker run ${{ steps.build.outputs.imageid }} python3 -c 'import doctr'
+
+      - name: Push Docker image
+        # Push only if the CI is not triggered by "PR on main"
+        if: github.ref == 'refs/heads/main' && github.event_name != 'pull_request'
+        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
+        with:
+          context: .
+          build-args: |
+            FRAMEWORK=${{ matrix.framework }}
+            PYTHON_VERSION=${{ matrix.python }}
+            SYSTEM=${{ matrix.system }}
+            DOCTR_REPO=${{ github.repository }}
+            DOCTR_VERSION=${{ github.sha }}
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}

Dockerfile

@@ -1,21 +1,72 @@
-# Use the TensorFlow GPU image as the base image. This image also works with CPU-only setups
-FROM tensorflow/tensorflow@sha256:b4676741c491bff3d0f29c38c369281792c7d5c5bfa2b1aa93e5231a8d236323
+FROM ubuntu:22.04
 
-ENV PYTHONUNBUFFERED=1 
-ENV PYTHONDONTWRITEBYTECODE=1 
-ENV DOCTR_CACHE_DIR=/app/.cache 
+ENV DEBIAN_FRONTEND=noninteractive
+ENV LANG=C.UTF-8
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
 
-WORKDIR /app
+ARG SYSTEM=gpu
 
-COPY . .
+# Enroll NVIDIA GPG public key and install CUDA
+RUN if [ "$SYSTEM" = "gpu" ]; then \
+    apt-get update && \
+    apt-get install -y gnupg ca-certificates wget && \
+    # - Install Nvidia repo keys
+    # - See: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#network-repo-installation-for-ubuntu
+    wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb && \
+    dpkg -i cuda-keyring_1.1-1_all.deb && \
+    apt-get update && apt-get install -y --no-install-recommends \
+    cuda-command-line-tools-11-8 \
+    cuda-cudart-dev-11-8 \
+    cuda-nvcc-11-8 \
+    cuda-cupti-11-8 \
+    cuda-nvprune-11-8 \
+    cuda-libraries-11-8 \
+    cuda-nvrtc-11-8 \
+    libcufft-11-8 \
+    libcurand-11-8 \
+    libcusolver-11-8 \
+    libcusparse-11-8 \
+    libcublas-11-8 \
+    # - CuDNN: https://docs.nvidia.com/deeplearning/sdk/cudnn-install/index.html#ubuntu-network-installation
+    libcudnn8=8.6.0.163-1+cuda11.8 \
+    libnvinfer-plugin8=8.6.1.6-1+cuda11.8 \
+    libnvinfer8=8.6.1.6-1+cuda11.8; \
+fi
 
-# Install necessary dependencies for video processing and GUI operations
-RUN apt-get update \
-    && apt-get install --no-install-recommends ffmpeg libsm6 libxext6 -y \
-    && apt-get autoremove -y \
-    && rm -rf /var/lib/apt/lists/* 
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    # - Other packages
+    build-essential \
+    pkg-config \
+    curl \
+    wget \
+    software-properties-common \
+    unzip \
+    git \
+    # - Packages to build Python
+    tar make gcc zlib1g-dev libffi-dev libssl-dev liblzma-dev libbz2-dev \
+    # - Packages for docTR
+    libgl1-mesa-dev libsm6 libxext6 libxrender-dev libpangocairo-1.0-0 \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* \
+fi
 
-# Install the current application with TensorFlow extras and modify permissions
-RUN pip install --upgrade pip setuptools wheel \
-    && pip install -e .[tf] \
-    && chmod -R a+w /app
+# Install Python
+ARG PYTHON_VERSION=3.10.13
+
+RUN wget http://www.python.org/ftp/python/$PYTHON_VERSION/Python-$PYTHON_VERSION.tgz && \
+    tar -zxf Python-$PYTHON_VERSION.tgz && \
+    cd Python-$PYTHON_VERSION && \
+    mkdir /opt/python/ && \
+    ./configure --prefix=/opt/python && \
+    make && \
+    make install
+
+ENV PATH=/opt/python/bin:$PATH
+
+# Install docTR
+ARG FRAMEWORK=tf
+ARG DOCTR_REPO='mindee/doctr'
+ARG DOCTR_VERSION=main
+RUN pip3 install -U pip setuptools wheel && \
+    pip3 install "python-doctr[$FRAMEWORK]@git+https://github.com/$DOCTR_REPO.git@$DOCTR_VERSION"

README.md

@@ -2,7 +2,7 @@
   <img src="docs/images/Logo_doctr.gif" width="40%">
 </p>
 
-[![Slack Icon](https://img.shields.io/badge/Slack-Community-4A154B?style=flat-square&logo=slack&logoColor=white)](https://slack.mindee.com) [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) ![Build Status](https://github.com/mindee/doctr/workflows/builds/badge.svg) [![codecov](https://codecov.io/gh/mindee/doctr/branch/main/graph/badge.svg?token=577MO567NM)](https://codecov.io/gh/mindee/doctr) [![CodeFactor](https://www.codefactor.io/repository/github/mindee/doctr/badge?s=bae07db86bb079ce9d6542315b8c6e70fa708a7e)](https://www.codefactor.io/repository/github/mindee/doctr) [![Codacy Badge](https://api.codacy.com/project/badge/Grade/340a76749b634586a498e1c0ab998f08)](https://app.codacy.com/gh/mindee/doctr?utm_source=github.com&utm_medium=referral&utm_content=mindee/doctr&utm_campaign=Badge_Grade) [![Doc Status](https://github.com/mindee/doctr/workflows/doc-status/badge.svg)](https://mindee.github.io/doctr) [![Pypi](https://img.shields.io/badge/pypi-v0.7.0-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/packages) [![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-v0.7.0-blue.svg)](https://pypi.org/project/python-doctr/) [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/mindee/doctr) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mindee/notebooks/blob/main/doctr/quicktour.ipynb)
 
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch**
@@ -260,10 +260,49 @@ Check out our [TensorFlow.js demo](https://github.com/mindee/doctr-tfjs-demo) to
 
 ### Docker container
 
-If you wish to deploy containerized environments, you can use the provided Dockerfile to build a docker image:
+[We offers Docker container support for easy testing and deployment](https://github.com/mindee/doctr/packages).
+
+#### Using GPU with docTR Docker Images
+
+The docTR Docker images are GPU-ready and based on CUDA `11.8`.
+However, to use GPU support with these Docker images, please ensure that Docker is configured to use your GPU.
+
+To verify and configure GPU support for Docker, please follow the instructions provided in the [NVIDIA Container Toolkit Installation Guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
+
+Once Docker is configured to use GPUs, you can run docTR Docker containers with GPU support:
+
+```shell
+docker run --it --gpus all ghcr.io/mindee/doctr:tf-py3.8.18-v0.7.1 bash
+```
+
+#### Available Tags
+
+The Docker images for docTR follow a specific tag nomenclature: `<framework>-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`.
+- `<doctr_version>`: a tag >= `v0.7.1`
+- `<YYYY-MM>`: e.g. `2023-10`
+
+Here are examples of different image tags:
+
+| Tag                        | Description                                       |
+|----------------------------|---------------------------------------------------|
+| `tf-py3.8.18-v0.7.1`       | TensorFlow version `3.8.18` with docTR `v0.7.1`. |
+| `torch-py3.9.18-2023-10`| PyTorch version `3.9.18` with a monthly build from `2023-10`. |
+
+#### Building Docker Images Locally
+
+You can also build docTR Docker images locally on your computer.
+
+```shell
+docker build -t doctr .
+```
+
+You can specify custom Python versions and docTR versions using build arguments. For example, to build a docTR image with TensorFlow, Python version `3.9.10`, and docTR version `v0.7.0`, run the following command:
 
 ```shell
-docker build . -t <YOUR_IMAGE_TAG>
+docker build -t doctr --build-arg FRAMEWORK=tf --build-arg PYTHON_VERSION=3.9.10 --build-arg DOCTR_VERSION=v0.7.0 .
 ```
 
 ### Example script