pbaa 1.0.2

Prompt based automatic annotation

pbaa : Prompt-Based Automatic Annotation

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

---

Table of Contents

• Installation
• Usage
• Demo
• License

Installation

pip install pbaa

Usage

Options

Usage: pbaa [OPTIONS]

Options:
  --version                    Show the version and exit.
  -s, --src TEXT               Source image or directory path  [required]
  -p, --prompt <TEXT TEXT>...  Space-separated a pair of prompt and target
                               classe. (Multi)  [required]
  -b, --box_threshold FLOAT    Threshold for Object Detection (default: 0.25)
  -n, --nms_threshold FLOAT    Threshold for NMS (default: 0.8)
  -o, --output_dir TEXT        Path to result data (default: '.')
  -h, --help                   Show this message and exit.

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 model_init, inference

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

Demo

## Source : assets/demo9.jpg
## prompts : {"plant" : "plant", "picture" : "picture", "dog": "dog", "lamp" : "lamp", "carpet" : "carpet", "sofa" : "sofa"}

pbaa -s assets/demo9.jpg -p plant plant -p picture picture -p dog dog -p lamp lamp -p carpet carpet -p sofa sofa

Origin	Detection	Segmentation

Result data

demo9.json

json structure

index
  ├ cls : class name
  ├ conf : confidence score
  ├ box : bounding box coordinates
  └ poly : polygon coordinates

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
Grounding DINO : https://github.com/IDEA-Research/GroundingDINO
Segment-anything : https://github.com/facebookresearch/segment-anything