moein-shariatnia/Pix2Seq

Simple Implementation of Pix2Seq model for object detection in PyTorch

40
/ 100
Emerging

This project helps anyone working with images to automatically identify and locate objects within them. You provide images (like photos from a camera or scanned documents), and it outputs a sequence of text that describes the detected objects and their precise bounding box coordinates. This is useful for computer vision practitioners who need to extract structured information from visual data.

130 stars. No commits in the last 6 months.

Use this if you need a straightforward way to train a model for object detection that outputs object labels and their locations as a descriptive text sequence.

Not ideal if you need to perform image classification or image segmentation rather than detecting specific objects and their boundaries.

object-detection computer-vision image-analysis visual-data-extraction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

130

Forks

16

Language

Python

License

MIT

Last pushed

Sep 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/moein-shariatnia/Pix2Seq"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.