Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
pix2tex: Using a ViT to convert images of equations into LaTeX code.
| Date | Stars |
|---|---|
| 2026-07-30 | 16508 |
| 2026-08-07 | 16530 |
| 2026-08-15 | 16539 |
| 2026-08-18 | 16539 |
| 2026-08-19 | 16540 |
| 2026-08-20 | 16543 |
| 2026-08-21 | 16543 |
| 2026-08-22 | 16544 |
| 2026-08-23 | 16546 |
| 2026-08-24 | 16545 |
| 2026-08-25 | 16545 |
| 2026-08-26 | 16546 |
| 2026-08-27 | 16547 |
| 2026-08-28 | 16548 |
| 2026-08-29 | 16549 |
| 2026-08-30 | 16550 |
| 2026-08-31 | 16551 |
| 2026-09-01 | 16550 |
| 2026-09-02 | 16549 |
| 2026-09-03 | 16551 |
| 2026-09-04 | 16555 |
| 2026-09-05 | 16554 |
| 2026-09-06 | 16558 |
| 2026-09-08 | 16560 |
| 2026-09-09 | 16561 |
| 2026-09-10 | 16559 |
| 2026-09-11 | 16557 |
| 2026-09-12 | 16558 |
| 2026-09-13 | 16561 |
| 2026-09-14 | 16564 |
| 2026-09-15 | 16566 |
| 2026-09-16 | 16569 |
| 2026-09-17 | 16570 |
| 2026-09-18 | 16569 |
| 2026-09-19 | 16568 |
| 2026-09-20 | 16567 |
| 2026-09-21 | 16569 |
| 2026-09-22 | 16573 |
| 2026-09-23 | 16575 |
| 2026-09-25 | 16576 |
| 2026-09-26 | 16577 |
| 2026-09-27 | 16572 |
| 2026-09-28 | 16574 |
| 2026-09-29 | 16575 |
| 2026-09-30 | 16577 |
| 2026-10-01 | 16578 |
| 2026-10-02 | 16582 |
| 2026-10-03 | 16579 |
| 2026-10-04 | 16580 |
| 2026-10-05 | 16579 |
| 2026-10-06 | 16583 |
| 2026-10-07 | 16587 |
| 2026-10-08 | 16589 |
| 2026-10-09 | 16588 |
| 2026-10-10 | 16587 |
| 2026-10-11 | 16588 |
| 2026-10-12 | 16587 |
| 2026-10-14 | 16590 |
| 2026-10-15 | 16592 |
| 2026-10-17 | 16592 |
| 2026-10-18 | 16591 |
| 2026-10-19 | 16595 |
| 2026-10-20 | 16596 |
| 2026-10-21 | 16596 |
| 2026-10-22 | 16598 |
| 2026-10-23 | 16600 |
| 2026-10-24 | 16601 |
| 2026-10-25 | 16603 |
| 2026-10-26 | 16605 |
| 2026-10-27 | 16602 |
| 2026-10-28 | 16600 |
| 2026-10-29 | 16601 |
| 2026-10-30 | 16602 |
| 2026-10-31 | 16599 |
| 2026-11-01 | 16599 |
| 2026-11-02 | 16602 |
| 2026-11-03 | 16602 |
| 2026-11-04 | 16603 |
Today
+1 stars today
This week
+3 stars this week
This month
+24 stars this month
Momentum
0.0
growth rate 0.02%/day
# pix2tex - LaTeX OCR
[](https://github.com/lukas-blecher/LaTeX-OCR) [](https://pix2tex.readthedocs.io/en/latest/?badge=latest) [](https://pypi.org/project/pix2tex) [](https://pypi.org/project/pix2tex) [](https://github.com/lukas-blecher/LaTeX-OCR/releases) [](https://hub.docker.com/r/lukasblecher/pix2tex) [](https://colab.research.google.com/github/lukas-blecher/LaTeX-OCR/blob/main/notebooks/LaTeX_OCR_test.ipynb) [](https://huggingface.co/spaces/lukbl/LaTeX-OCR)
The goal of this project is to create a learning based system that takes an image of a math formula and returns corresponding LaTeX code.
## Using the model
To run the model you need Python 3.7+
If you don't have PyTorch installed. Follow their instructions [here](https://pytorch.org/get-started/locally/).
Install the package `pix2tex`:
```
pip install "pix2tex[gui]"
```
Model checkpoints will be downloaded automatically.
There are three ways to get a prediction from an image.
1. You can use the command line tool by calling `pix2tex`. Here you can parse already existing images from the disk and images in your clipboard.
2. Thanks to [@katie-lim](https://github.com/katie-lim), you can use a nice user interface as a quick way to get the model prediction. Just call the GUI with `latexocr`. From here you can take a screenshot and the predicted latex code is rendered using [MathJax](https://www.mathjax.org/) and copied to your clipboard.
Under linux, it is possible to use the GUI with `gnome-screenshot` (which comes with multiple monitor support). For other Wayland compositers, `grim` and `slurp` will be used for wlroots-based Wayland compositers and `spectacle` for KDE Plasma. Note that `gnome-screenshot` is not compatible with wlroots or Qt based compositers. Since `gnome-screenshot` will be preferred when available, you may have to set the environment variable `SCREENSHOT_TOOL` to `grim` or `spectacle` in these cases (other available values are `gnome-screenshot` and `pil`).
If the model is unsure about the what's in the image it might output a different prediction every time you click "Retry". With the `temperature` parameter you can control this behavior (low temperature will produce the same result).
3. You can use an API. This has additional dependencies. Install via `pip install -U "pix2tex[api]"` and run
```bash
python -m pix2tex.api.run
```
to start a [Streamlit](https://streamlit.io/) demo that connects to the API at port 8502. There is also a docker image available for the API: https://hub.docker.com/r/lukasblecher/pix2tex [](https://hub.docker.com/r/lukasblecher/pix2tex)
```
docker pull lukasblecher/pix2tex:api
docker run --rm -p 8502:8502 lukasblecher/pix2tex:api
```
To also run the streamlit demo run
```
docker run --rm -it -p 8501:8501 --entrypoint python lukasblecher/pix2tex:api pix2tex/api/run.py
```
and navigate to http://localhost:8501/
4. Use from within Python
```python
from PIL import Image
from Excerpt of 8,893 characters
Read on GitHub
Lukas Blecher · Germany
256
TITC
25
wzy · @ustc-ivclab
6
Francesco Mario D'Afiero
5
Levi Zim · Looking for FLOSS Job Opportunities
4
Joep
4
4
Awam M Wang
3
兰铃 · 二本混子
2
@LineageOS · Ireland
2
Oct0pu5 · China University of Petroleum, Beijing · China
1
Ha YongWook · Tanalysis · South Korea
1
wnma
1
rainy liu
1
1
James Yang · China
1
Zhi-Qiang Zhou · Tsinghua University
1
Opal Kim
1
Switzerland
1
R. Häcker
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ce25eb4c2272abb9, topic:deep-learning, topic:pytorch
matched fp:ce25eb4c2272abb9, topic:ocr, name:ocr, readme:ocr
matched fp:ce25eb4c2272abb9, topic:transformer
matched fp:ce25eb4c2272abb9, topic:dataset