rapid-orientation 0.0.1

Tools for classifying the direction of images containing text based ONNXRuntime.

rapid-layout Package

1. Install package by pypi.

$ pip install rapid-layout

2. Run by script.

• RapidLayout has the default model_path value, you can set the different value of model_path to use different models, e.g. layout_engine = RapidLayout(model_path='layout_publaynet.onnx')
• See details, for README_Layout .
• 📌 layout.png source: link

import cv2
from rapid_layout import RapidLayout

layout_engine = RapidLayout()

img = cv2.imread('layout.png')

layout_res, elapse = layout_engine(img)
print(layout_res)

3. Run by command line.

• Usage:

  $ rapid_layout -h
  usage: rapid_layout [-h] [-v] -img IMG_PATH [-m MODEL_PATH]
  
  optional arguments:
  -h, --help            show this help message and exit
  -v, --vis             Wheter to visualize the layout results.
  -img IMG_PATH, --img_path IMG_PATH
                          Path to image for layout.
  -m MODEL_PATH, --model_path MODEL_PATH
                          The model path used for inference.
  

• Example:

  $ rapid_layout -v -img layout.png
  

4. Result.

• Return value.

  [
      {'bbox': array([321.4160495, 91.53214898, 562.06141263, 199.85522603]), 'label': 'text'},
      {'bbox': array([58.67292211, 107.29000663, 300.25448676, 199.68142]), 'label': 'table_caption'}
  ]
  

• Visualize result.