pbaa 1.0.0

Prompt based automatic annotation

pbaa

Easy inference implementation of Grounded-Sam for Prompt-based automatic annotation

---

Table of Contents

• Installation
• Usage
• License

Grounded-SAM

Most of code based on Grounded-Sam

Installation

pip install pbaa

Usage

Option

• --source, -s : Path to source image or directory. (processing)
  • --source <Source image>
  • --source source_image.jpg
• --prompt, -p : Space-separated a pair of prompt and target classe. (Multi)
  • --prompt "<Prompt>" <Class>
  • --prompt "black dog" dog

CLI

# pbaa -s <Source> -p <prompt> <class> -p <prompt> <class> ...

pbaa -s source_image.jpg -p "black dog" dog
pbaa -s source_image.jpg -p "black dog" dog -p "white cat" cat

Python

from pbaa import inference

inference("path/to/source_image.jpg", {"black dog": "dog", "white cat": "cat"})

License

pbaa is distributed under the terms of the Apache-2.0 license.

Acknowledgements

Grounded-Segment-Anything :https://github.com/IDEA-Research/Grounded-Segment-Anything