keras/parseq

Model Overview

Permuted autoregressive sequence (PARSeq) model for Scene Text Recognition (STR)

This model is designed for Scene Text Recognition (STR), which involves reading text from images. You can load and use the pre-trained PARSeq model with the following Python code snippet. The model takes an image as input and outputs the recognized text.

Links

• PARSeq Quickstart Notebook
• PARSeq API Documentation
• PARSeq Model Card
• KerasHub Beginner Guide
• KerasHub Model Publishing Guide

Installation

Keras and KerasHub can be installed with:

pip install -U -q keras-hub
pip install -U -q keras>=3

Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instructions on installing them in another environment see the Keras Getting Started page.

Presets

The following model checkpoints are provided by the Keras team. Full code examples for each are available below.

Preset name	Parameters	Description
parseq	23.8M	23 million parameter base model.