Universal Data Tool
  • Universal Data Tool Docs
  • Installation
  • Running On-Premise
  • Collaborative Labeling
  • Building and Labeling Datasets
    • Image Segmentation
    • Image Classification
    • Text Classification
    • Named Entity Recognition
    • Entity Relations / Part of Speech Tagging
    • Audio Transcription
    • Data Entry
    • Video Segmentation
    • Composite Interfaces
    • Landmark / Pose Annotation
  • Importing Data
    • Upload or Open Directories
    • Import File URLs
    • Import COCO Images
    • Import from Google Drive
    • Import from AWS S3 Bucket
    • Import from CSV or JSON
    • Import using AWS Cognito
    • Import Text Snippets
  • The Format .udt.json
    • What is the .udt.json format?
    • What is the .udt.csv format?
  • Machine Learning
    • Jupyter Notebook Integration
    • Import Datasets into Pandas
    • Fast.ai
      • Fast.ai Image Classification
      • Fast.ai Image Segmentation
  • Integrate with Any Web Page
    • Integrate with the Javascript Library
    • Getting Started with React
  • Train your Workforce
    • Getting Started with UDT Courses
  • Frequently Asked Questions
Powered by GitBook
On this page

Was this helpful?

  1. The Format .udt.json

What is the .udt.json format?

PreviousImport Text SnippetsNextWhat is the .udt.csv format?

Last updated 4 years ago

Was this helpful?

The UDT JSON format is an for specifying human annotation tasks. For example, you might use the .udt.json format to store the labels and specification for transcribing audio or labeling images.

The UDT JSON format can be easily.

The basic structure of a UDT JSON file is this:

{
    "interface": {
        "type": "<some_interface>"
        // ... more interface details
    },
    "samples": [
        { /* sample json object */ },
        // ...
    ]
}

Here's an example for an dataset...

{
  "interface": {
    "type": "image_segmentation",
    "labels": [
      {
        "id": "cat",
        "description": "Feline Mammal"
      },
      {
        "id": "dog",
        "description": "Canine Mammal"
      }
    ],
    "regionTypesAllowed": ["bounding-box"],
    "multipleRegions": true
  },
  "samples": [
    {
      "imageUrl": "https://media.gettyimages.com/photos/dog-and-cat-picture-id151350785"
    },
    {
      "imageUrl": "https://media.gettyimages.com/photos/guess-who-rules-the-roost-in-that-house-picture-id500927195"
    },
    {
      "imageUrl": "https://media.gettyimages.com/photos/she-simply-loves-animals-picture-id499806311"
    }
  ]
}

Principles

The principles that drive the UDT format are...

  • Complete Specificity such that no additional documents or conversations are required to perform the task.

  • Simplicity and Human Readability so that datasets can be easily examined in the JSON format and understood

  • Specificity such that no additional documents or conversations are required to start labeling

open-source format
converted to and from an equivalent CSV format
image segmentation