All necessary instructions to use the DocVisor tool.

Step 1 : Download or Clone DocVisor tool

Clone Using Git

If you have git installed on your local machine, run the following command to clone the docvisor repository.

git clone

Download Zip

If you do not have git or you want to download the zip file, download the zip file from here and unzip the tool to any location on your divice.

Step 2: Data Preperation

There three main layouts of the DocVisor tool:

  1. Fully Automatic
  2. Box Supervised
  3. OCR

You can load one or more of these tools to the DocVisor tool at any given point in time.

  • To load the Fully Automatic tool, prepare your datafiles as described here
  • To load the Box Supervised tool, prepare your datafiles as described here
  • To load the OCR tool, prepare your datafiles as described here

Step 3: Setting up your environment

  1. Create a conda environment using the following command:

     conda create --name docvisor
  2. Ensure that the pip points to the docvisor environment by running which pip. If it does not, then run the following command:

     conda install pip
  3. Install the requirements necessary:

    pip install -r requirements.txt

Step 4: Modify Config File

  1. Place all the metaData files in one directory

The metaData directory will look like:

    - ocr_handwritten.json
    - ocr_printed.json
    - fullyAutomatic.json
    - boxSupervised.json
  1. Change the path of the metaData file in the tool/ file.

Step 5: Launch the tool

Launch the tool by running ./ script.

Load Example Data

We have provided an example folder in the repository for all the layouts. To load the example layouts, follow the steps below:

  1. Ensure that the metaDataDir field in tool/ is set to example/metaData
  2. Run ./ script to load the app