onnx-models
nougat
onnx-models | nougat | |
---|---|---|
5 | 13 | |
106 | 8,103 | |
1.9% | 3.5% | |
5.5 | 7.5 | |
6 months ago | 26 days ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
onnx-models
-
Wonnx real-time webcam image classication using WebGPU
No, the inference accuracy of the image classifier is dependent on the model used and this is a demo of the code executing the model in a browser with GPU acceleration not the model itself. You can plug and play any model in the onnx format e.g. https://github.com/onnx/models. As a comparison, complaining about the "abysmal quality" of the dummy model on display here is like saying blender is bad 3d modeling software after opening it for the first time because all it models is a blank cube.
- FLaNK Stack for 04 December 2023
- GitHub repo containing gigabytes of example onxx models
- ONNX Model Zoo Hosted on GitHub
nougat
-
Show HN: Talk to any ArXiv paper just by changing the URL
https://github.com/facebookresearch/nougat/tree/main
- FLaNK Stack for 04 December 2023
- Detexify LaTeX Handwriting Symbol Recognition
-
Pix2tex: Using a ViT to convert images of equations into LaTeX code
If you're looking for more e2e math / latex aware OCR checkout https://github.com/facebookresearch/nougat
- Nougat: Open-source LaTeX aware OCR for math-heavy books
-
Did anyone manage to get nougat running?
git clone --recurse-submodules https://github.com/facebookresearch/nougat.git PyProject
- Nougat: Facebook Research PDF to .mdd Model
-
Linear Book Scanner – The open-source automatic book scanner
> For the scientific literature, we need a ChatGPT equivalent to reconstruct LaTeX source that can reproduce each page. (We really need a successor to LaTeX that isn't such an arcane language, and can author fixed and flowable text with equal ease.)
Check out Nougat: OCRing scientific papers with a deep net trained end to end. It was released by Meta a few days ago.
“PDF format leads to a loss of semantic information, particularly for mathematical expressions. We propose Nougat (Neural Optical Understanding for Academic Documents), a Visual Transformer model that performs an Optical Character Recognition (OCR) task for processing scientific documents into a markup language, and demonstrate the effectiveness of our model on a new dataset of scientific documents.”
https://facebookresearch.github.io/nougat/
-
Nougat: Neural Optical Understanding for Academic Documents
The paper (and examples) as HTML: https://facebookresearch.github.io/nougat/
Repo with code, including a CLI tool for converting a PDF to Mathpix Markdown: https://github.com/facebookresearch/nougat
What are some alternatives?
FLaNK-SaoPauloBrazil - FLaNK-SaoPauloBrazil
LIMoE-pytorch - PyTorch implementation of LIMoE
narrator - David Attenborough narrates your life
libcolorpicker - Color Picker Library For iOS
velox - A C++ vectorized database acceleration library aimed to optimizing query engines and data processing systems.
typst - A new markup-based typesetting system that is powerful and easy to learn.
voyager - 🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.
advanced-brightness-slider-tweak - iOS Tweak that manipulates the brightness slider in the control center so the display brightness and the white point intensity can be modified
meditron - Meditron is a suite of open-source medical Large Language Models (LLMs).
NotiBlock - An iOS jailbreak tweak to write custom filters to block notifications
FLiPStackWeekly - FLaNK AI Weekly covering Apache NiFi, Apache Flink, Apache Kafka, Apache Spark, Apache Iceberg, Apache Ozone, Apache Pulsar, and more...
LaTeX-OCR - pix2tex: Using a ViT to convert images of equations into LaTeX code.