guillaumegenthial/im2latex
A TensorFlow Seq2Seq model with attention and beam search that converts images of mathematical formulas into LaTeX code.
Not currently ranked — collecting fresh signals.
star history
The model follows an encoder-decoder architecture where a convolutional neural network encodes an image of a mathematical formula and a recurrent decoder with attention generates the corresponding LaTeX sequence. It includes beam search for improved decoding and was inspired by the Show, Attend and Tell paper and Harvard’s im2markup dataset.
Frequently asked
- What is guillaumegenthial/im2latex?
- A TensorFlow Seq2Seq model with attention and beam search that converts images of mathematical formulas into LaTeX code.
- Is im2latex open source?
- Yes — guillaumegenthial/im2latex is open source, released under the Apache-2.0 license.
- What language is im2latex written in?
- guillaumegenthial/im2latex is primarily written in Python.
- How popular is im2latex?
- guillaumegenthial/im2latex has 462 stars on GitHub.
- Where can I find im2latex?
- guillaumegenthial/im2latex is on GitHub at https://github.com/guillaumegenthial/im2latex.