Skip to content

Uses Visual Transformers to encode images of handwritten sentences and/or equations into a latent vector, then decodes the latent vector into Markdown / LaTeX format.

Notifications You must be signed in to change notification settings

KitPi/handwriting2Markdown

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

42 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Handwriting to Markdown

Small project to turn handwritten math notes into Markdown format notes with LaTeX math notation.

This project uses a visual encoder-decoder transformer model. It encodes images of handwritten math using a Visual Transformer into a latent vector, which it then decodes using Natural Language decoder into LaTeX notation.

Setup

Assuming target system has CUDA capable graphics card with CUDA toolkit, python3-pip, python3-venv, installed

Start venv, install requirements

  • python3 -m venv .venv
  • source .venv/bin/activate
  • pip install -r requirements.txt

Datasets

https://www.kaggle.com/datasets/shahrukhkhan/im2latex100k

Evaluation

Evauluation

About

Uses Visual Transformers to encode images of handwritten sentences and/or equations into a latent vector, then decodes the latent vector into Markdown / LaTeX format.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published