an1018 · an1018 · Aug 17, 2021 · Aug 20, 2021 · Aug 21, 2021 · Aug 27, 2021
diff --git a/.github/layout-parser.png b/.github/layout-parser.png
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -1,17 +1,70 @@
 name: CI
 
-on: [push]
+on: [push, pull_request]
 
 jobs:
-  build:
+
+  test_only_effdet_backend:
+
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.7'
+
+    - name: Test Dependency Support 
+      run: |
+        pip install pytest
+        pip install -e . # The bare layoutparser module 
+        pytest tests_deps/test_file_utils.py
+
+    - name: Install only effdet deps 
+      run: |
+        pip install pytest
+        pip install -e ".[effdet]"
+        pytest tests_deps/test_only_effdet.py
+
+  test_only_detectron2_backend:
 
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.7'
+
+    - name: Install only Detectron2 deps 
+      run: |
+        pip install pytest
+        pip install -e .
+        pip install torchvision && pip install "git+https://github.com/facebookresearch/detectron2.git@v0.5#egg=detectron2"
+        pytest tests_deps/test_only_detectron2.py
+
+  test_only_paddledetection_backend:
+
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.7'
+
+    - name: Install only PaddleDetection deps 
+      run: |
+        pip install pytest
+        pip install -e ".[paddledetection]"
+        pytest tests_deps/test_only_paddledetection.py
+
+  test_all_methods_all_backends:
+    needs: [test_only_effdet_backend, test_only_detectron2_backend, test_only_paddledetection_backend]
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: [3.7, 3.8]
-
     steps:
     - uses: actions/checkout@v2
+
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2
       with:
@@ -21,7 +74,6 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install .
-        pip install 'git+https://github.com/facebookresearch/detectron2.git@v0.1.3#egg=detectron2' 
 
     - name: Lint with flake8
       run: |
@@ -30,9 +82,10 @@ jobs:
         flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics --ignore F821
         # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-        
+
     - name: Test with pytest
       run: |
         # Install additional requirements when running tests
+        pip install ".[effdet]"
         pip install -r dev-requirements.txt
-        pytest
+        pytest tests
diff --git a/.gitignore b/.gitignore
@@ -1,3 +1,6 @@
+# Examples files 
+examples/Customizing Layout Models with Label Studio Annotation/downloaded-annotations
+
 *.bak
 .gitattributes
 .last_checked

diff --git a/.readthedocs.yml b/.readthedocs.yml
@@ -18,4 +18,6 @@ python:
   install:
     - method: pip
       path: .
+      extra_requirements:
+        - effdet
     - requirements: dev-requirements.txt
diff --git a/README.md b/README.md
@@ -1,68 +1,120 @@
 <p align="center">
   <img src="https://github.com/Layout-Parser/layout-parser/raw/master/.github/layout-parser.png" alt="Layout Parser Logo" width="35%">
-  <p align="center">
+  <h3 align="center">
   A unified toolkit for Deep Learning Based Document Image Analysis
-  </p>
+  </h3>
 </p>
 
 <p align=center>
-<a href="https://arxiv.org/abs/2103.15348"><img src="https://img.shields.io/badge/arXiv-2103.15348-b31b1b.svg" title="Layout Parser Paper"></a>
-<a href="https://layout-parser.github.io"><img src="https://img.shields.io/badge/website-layout--parser.github.io-informational.svg" title="Layout Parser Paper"></a>
-<a href="https://layout-parser.readthedocs.io/en/latest/"><img src="https://img.shields.io/badge/doc-layout--parser.readthedocs.io-light.svg" title="Layout Parser Documentation"></a>
+<a href="https://pypi.org/project/layoutparser/"><img src="https://img.shields.io/pypi/v/layoutparser?color=%23099cec&label=PyPI%20package&logo=pypi&logoColor=white" title="The current version of Layout Parser"></a>
+<a href="https://github.com/Layout-Parser/layout-parser/blob/master/LICENSE"><img src="https://img.shields.io/pypi/l/layoutparser" title="Layout Parser uses Apache 2 License"></a>
+<img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dm/layoutparser">
 </p>
 
 <p align=center>
-<a href="https://pypi.org/project/layoutparser/"><img src="https://img.shields.io/pypi/v/layoutparser?color=%23099cec&label=PyPI%20package&logo=pypi&logoColor=white" title="The current version of Layout Parser"></a>
-<a href="https://pypi.org/project/layoutparser/"><img src="https://img.shields.io/pypi/pyversions/layoutparser?color=%23099cec&" alt="Python 3.6 3.7 3.8" title="Layout Parser supports Python 3.6 and above"></a>
-<img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dm/layoutparser">
-<a href="https://github.com/Layout-Parser/layout-parser/blob/master/LICENSE"><img src="https://img.shields.io/pypi/l/layoutparser" title="Layout Parser uses Apache 2 License"></a>
+<a href="https://arxiv.org/abs/2103.15348"><img src="https://img.shields.io/badge/paper-2103.15348-b31b1b.svg" title="Layout Parser Paper"></a>
+<a href="https://layout-parser.github.io"><img src="https://img.shields.io/badge/website-layout--parser.github.io-informational.svg" title="Layout Parser Paper"></a>
+<a href="https://layout-parser.readthedocs.io/en/latest/"><img src="https://img.shields.io/badge/doc-layout--parser.readthedocs.io-light.svg" title="Layout Parser Documentation"></a>
 </p>
 
 ---
 
-## Installation 
+## What is LayoutParser
+
+![Example Usage](.github/example.png)
 
-You can find detailed installation instructions in [installation.md](installation.md). But generally, it's just `pip install` 
-some libraries: 
+LayoutParser aims to provide a wide range of tools that aims to streamline Document Image Analysis (DIA) tasks. Please check the LayoutParser [demo video](https://youtu.be/8yA5xB4Dg8c) (1 min) or [full talk](https://www.youtube.com/watch?v=YG0qepPgyGY) (15 min) for details. And here are some key features:
+
+- LayoutParser provides a rich repository of deep learning models for layout detection as well as a set of unified APIs for using them. For example, 
+
+  <details>
+  <summary>Perform DL layout detection in 4 lines of code</summary>
+
+  ```python
+  import layoutparser as lp
+  model = lp.AutoLayoutModel('lp://EfficientDete/PubLayNet')
+  # image = Image.open("path/to/image")
+  layout = model.detect(image) 
+  ```
+
+  </details>
+
+- LayoutParser comes with a set of layout data structures with carefully designed APIs that are optimized for document image analysis tasks. For example, 
+
+  <details>
+  <summary>Selecting layout/textual elements in the left column of a page</summary>
+
+  ```python
+  image_width = image.size[0]
+  left_column = lp.Interval(0, image_width/2, axis='x')
+  layout.filter_by(left_column, center=True) # select objects in the left column 
+  ```
+
+  </details>
+
+  <details>
+  <summary>Performing OCR for each detected Layout Region</summary>
+
+  ```python
+  ocr_agent = lp.TesseractAgent()
+  for layout_region in layout: 
+      image_segment = layout_region.crop(image)
+      text = ocr_agent.detect(image_segment)
+  ```
+
+  </details>  
+
+  <details>
+  <summary>Flexible APIs for visualizing the detected layouts</summary>
+
+  ```python
+  lp.draw_box(image, layout, box_width=1, show_element_id=True, box_alpha=0.25)
+  ```
+
+  </details>  
+
+  </details>  
+
+  <details>
+  <summary>Loading layout data stored in json, csv, and even PDFs</summary>
+
+  ```python 
+  layout = lp.load_json("path/to/json")
+  layout = lp.load_csv("path/to/csv")
+  pdf_layout = lp.load_pdf("path/to/pdf")
+  ```
+
+  </details>
+
+- LayoutParser is also a open platform that enables the sharing of layout detection models and DIA pipelines among the community. 
+  <details>
+  <summary><a href="https://layout-parser.github.io/platform/">Check</a> the LayoutParser open platform</summary>
+  </details>
+
+  <details>
+  <summary><a href="https://github.com/Layout-Parser/platform">Submit</a> your models/pipelines to LayoutParser</summary>
+  </details>
 
-```bash
-pip install -U layoutparser
+## Installation 
 
-# Install Detectron2 for using DL Layout Detection Model
-# Please make sure the PyTorch version is compatible with
-# the installed Detectron2 version. 
-pip install 'git+https://github.com/facebookresearch/detectron2.git@v0.4#egg=detectron2' 
+After several major updates, layoutparser provides various functionalities and deep learning models from different backends. But it still easy to install layoutparser, and we designed the installation method in a way such that you can choose to install only the needed dependencies for your project:
 
-# Install the ocr components when necessary 
-pip install layoutparser[ocr]      
+```bash
+pip install layoutparser # Install the base layoutparser library with  
+pip install "layoutparser[layoutmodels]" # Install DL layout model toolkit 
+pip install "layoutparser[ocr]" # Install OCR toolkit
 ```
 
-**For Windows Users:** Please read [installation.md](installation.md) for details about installing Detectron2.
+Extra steps are needed if you want to use Detectron2-based models. Please check [installation.md](installation.md) for additional details on layoutparser installation. 
 
-## Quick Start
+## Examples 
 
 We provide a series of examples for to help you start using the layout parser library: 
 
 1. [Table OCR and Results Parsing](https://github.com/Layout-Parser/layout-parser/blob/master/examples/OCR%20Tables%20and%20Parse%20the%20Output.ipynb): `layoutparser` can be used for conveniently OCR documents and convert the output in to structured data. 
 
 2. [Deep Layout Parsing Example](https://github.com/Layout-Parser/layout-parser/blob/master/examples/Deep%20Layout%20Parsing.ipynb): With the help of Deep Learning, `layoutparser` supports the analysis very complex documents and processing of the hierarchical structure in the layouts. 
 
-
-## DL Assisted Layout Prediction Example 
-
-![Example Usage](.github/example.png)
-
-*The images shown in the figure above are: a screenshot of [this paper](https://arxiv.org/abs/2004.08686), an image from the [PRIMA Layout Analysis Dataset](https://www.primaresearch.org/dataset/), a screenshot of the [WSJ website](http://wsj.com), and an image from the [HJDataset](https://dell-research-harvard.github.io/HJDataset/).*
-
-With only 4 lines of code in `layoutparse`, you can unlock the information from complex documents that existing tools could not provide. You can either choose a deep learning model from the [ModelZoo](https://github.com/Layout-Parser/layout-parser/blob/master/docs/notes/modelzoo.md), or load the model that you trained on your own. And use the following code to predict the layout as well as visualize it: 
-
-```python
->>> import layoutparser as lp
->>> model = lp.Detectron2LayoutModel('lp://PrimaLayout/mask_rcnn_R_50_FPN_3x/config')
->>> layout = model.detect(image) # You need to load the image somewhere else, e.g., image = cv2.imread(...)
->>> lp.draw_box(image, layout,) # With extra configurations
-```
-
 ## Contributing
 
 We encourage you to contribute to Layout Parser! Please check out the [Contributing guidelines](.github/CONTRIBUTING.md) for guidelines about how to proceed. Join us!

diff --git a/dev-requirements.txt b/dev-requirements.txt
@@ -1,4 +1,5 @@
 pytest
+torch
 numpy
 opencv-python
 pandas
@@ -10,4 +11,6 @@ sphinx_rtd_theme
 google-cloud-vision==1
 pytesseract
 pycocotools
-git+https://github.com/facebookresearch/detectron2.git@v0.4#egg=detectron2
+git+https://github.com/facebookresearch/detectron2.git@v0.4#egg=detectron2
+paddlepaddle
+effdet
diff --git a/docs/api_doc/io.rst b/docs/api_doc/io.rst
@@ -2,22 +2,28 @@ Load and Export Layout Data
 ================================
 
 
-DataFrame and CSV
+`Dataframe` and CSV
 --------------------------------
 
 .. autofunction:: layoutparser.io.load_dataframe
 
 .. autofunction:: layoutparser.io.load_csv
 
 
-Dictionary and JSON 
+`Dict` and JSON 
 --------------------------------
 
 .. autofunction:: layoutparser.io.load_dict
 
 .. autofunction:: layoutparser.io.load_json
 
 
+PDF
+--------------------------------
+
+.. autofunction:: layoutparser.io.load_pdf
+
+
 Other Formats
 --------------------------------
 Stay tuned! We are working on to support more formats. 
diff --git a/docs/conf.py b/docs/conf.py
@@ -1,3 +1,17 @@
+# Copyright 2021 The Layout Parser team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 # Configuration file for the Sphinx documentation builder.
 #
 # This file only contains a selection of the most common options. For a full

diff --git a/docs/example/deep_layout_parsing/index.rst b/docs/example/deep_layout_parsing/index.rst
@@ -118,10 +118,10 @@ Finally sort the text regions and assign ids:
     left_interval = lp.Interval(0, w/2*1.05, axis='x').put_on_canvas(image)
 
     left_blocks = text_blocks.filter_by(left_interval, center=True)
-    left_blocks.sort(key = lambda b:b.coordinates[1])
+    left_blocks.sort(key = lambda b:b.coordinates[1], inplace=True)
 
     right_blocks = [b for b in text_blocks if b not in left_blocks]
-    right_blocks.sort(key = lambda b:b.coordinates[1])
+    right_blocks.sort(key = lambda b:b.coordinates[1], inplace=True)
 
     # And finally combine the two list and add the index
     # according to the order

diff --git a/docs/notes/modelzoo.md b/docs/notes/modelzoo.md
@@ -28,6 +28,8 @@ model.detect(image)
 | [NewspaperNavigator](https://news-navigator.labs.loc.gov/)            | [faster_rcnn_R_50_FPN_3x](https://www.dropbox.com/s/wnido8pk4oubyzr/config.yml?dl=1)       | lp://NewspaperNavigator/faster_rcnn_R_50_FPN_3x/config |                                                                           |
 | [TableBank](https://doc-analysis.github.io/tablebank-page/index.html) | [faster_rcnn_R_50_FPN_3x](https://www.dropbox.com/s/7cqle02do7ah7k4/config.yaml?dl=1)      | lp://TableBank/faster_rcnn_R_50_FPN_3x/config          | 89.78 [eval.csv](https://www.dropbox.com/s/1uwnz58hxf96iw2/eval.csv?dl=0) |
 | [TableBank](https://doc-analysis.github.io/tablebank-page/index.html) | [faster_rcnn_R_101_FPN_3x](https://www.dropbox.com/s/h63n6nv51kfl923/config.yaml?dl=1)     | lp://TableBank/faster_rcnn_R_101_FPN_3x/config         | 91.26 [eval.csv](https://www.dropbox.com/s/e1kq8thkj2id1li/eval.csv?dl=0) |
+| [Math Formula Detection(MFD)](http://transcriptorium.eu/~htrcontest/MathsICDAR2021/) | [faster_rcnn_R_50_FPN_3x](https://www.dropbox.com/s/ld9izb95f19369w/config.yaml?dl=1)     | lp://MFD/faster_rcnn_R_50_FPN_3x/config         | 79.68 [eval.csv](https://www.dropbox.com/s/1yvrs29jjybrlpw/eval.csv?dl=0) |
+
 
 * For PubLayNet models, we suggest using `mask_rcnn_X_101_32x8d_FPN_3x` model as it's trained on the whole training set, while others are only trained on the validation set (the size is only around 1/50). You could expect a 15% AP improvement using the `mask_rcnn_X_101_32x8d_FPN_3x` model.
 
@@ -39,4 +41,5 @@ model.detect(image)
 | [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet)        | `{0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"}`     |
 | [PrimaLayout](https://www.primaresearch.org/dataset/)        | `{1:"TextRegion", 2:"ImageRegion", 3:"TableRegion", 4:"MathsRegion", 5:"SeparatorRegion", 6:"OtherRegion"}` |
 | [NewspaperNavigator](https://news-navigator.labs.loc.gov/)        | `{0: "Photograph", 1: "Illustration", 2: "Map", 3: "Comics/Cartoon", 4: "Editorial Cartoon", 5: "Headline", 6: "Advertisement"}` |
-| [TableBank](https://doc-analysis.github.io/tablebank-page/index.html)         | `{0: "Table"}` |
+| [TableBank](https://doc-analysis.github.io/tablebank-page/index.html)         | `{0: "Table"}` |
+| [MFD](http://transcriptorium.eu/~htrcontest/MathsICDAR2021/)         | `{1: "Equation"}` |