Awesome Open Source
Awesome Open Source


Seq2Seq model with Attention + Beam Search for Image to LaTeX, similar to Show, Attend and Tell and Harvard's paper and dataset.

Check the blog post.


Install pdflatex (latex to pdf) and ghostsript + magick (pdf to png) on Linux

make install-linux

(takes a while ~ 10 min, installs from source)

On Mac, assuming you already have a LaTeX distribution installed, you should have pdflatex and ghostscript installed, so you just need to install magick. You can try

make install-mac

Getting Started

We provide a small dataset just to check the pipeline. To build the images, train the model and evaluate

make small

You should observe that the model starts to produce reasonable patterns of LaTeX after a few minutes.


We provide the pre-processed formulas from Harvard but you'll need to produce the images from those formulas (a few hours on a laptop).

make build

Alternatively, you can download the prebuilt dataset from Harvard and use their preprocessing scripts found here

Training on the full dataset

If you already did make build you can just train and evaluate the model with the following commands

make train
make eval

Or, to build the images from the formulas, train the model and evaluate, run

make full


  1. Build the images from the formulas, write the matching file and extract the vocabulary. Run only once for a dataset
python --data=configs/data.json --vocab=configs/vocab.json
  1. Train
python --data=configs/data.json --vocab=configs/vocab.json --training=configs/training.json --model=configs/model.json --output=results/full/
  1. Evaluate the text metrics
python --results=results/full/
  1. Evaluate the image metrics
python --results=results/full/

(To get more information on the arguments, run)

python --help

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (51,962
tensorflow (2,131
seq2seq (102
beam-search (20

Find Open Source By Browsing 7,000 Topics Across 59 Categories