От вет-ИИ для коров до имперского глянца: хардкорный MLOps на бесплатных GPU

В начале 2026 года ленты новостей принесли тревожные сообщения из Сибири: массовые вспышки опасных заболеваний у КРС (крупного рогатого скота) привели к необходимости вынужденного забоя тысяч голов. Для многих фермеров это означало потерю бизнеса и средств к существованию. Мы задались вопросом: может ли доступный Computer Vision стать первой линией обороны? Инструментом, который позволит фермеру в отдаленном районе провести первичный скрининг (триаж) животного с помощью обычного смартфона и вовремя вызвать ветеринара, не дожидаясь начала эпидемии. Так родился проект AI-Vet-Scanner ( наше пространство на Hugging Face ), определяющий признаки заболеваний по фотографии.

https://habr.com/ru/articles/1013214/

#MLOps #Kaggle #Computer_Vision #OpenCV #PyMuPDF #Hugging_Face #датасет #парсинг #оптимизация_памяти #SDXL_LoRA

Censor, a new document redaction tool, is there!

It allows to draw black rectangles on PDF documents and to permanently remove the text and images below. Find it on @Codeberg: https://codeberg.org/censor/Censor, get it from @flathub: https://flathub.org/apps/page.codeberg.censor.Censor, or translate it on Codeberg Translate: https://translate.codeberg.org/engage/censor!

It is a free and open-source graphical user interface (GUI) for #Linux and the #GNOME desktop, and uses the #MuPDF library with its #python bindings from the #PyMuPDF module.

#censorship #redaction #PDF #Codeberg #Flatpak #Flathub

After struggling to get #python #PyMuPDF to work and being close the deadline, I shifted to using a combination of other commands.

First using the #linux #pdftohtml command, which is so much faster than PyMuPDF and packages the result similar to saving a website.

Next with #NeoVim and #RegEx format the #HTML file to be able to be quickly processed with #NodeJs #cheerio and eventually through #json to be saved in #sqlite.

Is it elegant and automatic? No, though it works!

#JavaScript

Currently trying to extract and format data from PDFs using #python #PyMuPDF.

Initially used the `get_text(value)` method with the `"text"` value, only to learn that I could have potentially saved time directly using the `"html"` value, since I have been creating pattern matchers to format the text into #HTML.

After investigation, although the html option exists, the post processing is more strenuous than the initial approach.

My fascination with the `get_text(value)` method is that each value packages the data differently. Where as `"html"` puts the text in `<p><span>text</span></p>`, `"xhtml"` puts it instead in `<h1>text</h1>`.

I just updated my 2023 post on extracting text from #EPUB files in #Python, and added an evaluation of #PyMuPDF (which also supports EPUB!). Includes link to demo script.

https://www.bitsgalore.org/2023/03/09/extracting-text-from-epub-files-in-python

Ever felt the need to convert a #PDF into a fixed-layout #EPUB that preserves the table of contents, internal cross-references and hyperlinks? Finding no out-of-the-box solution, I've developed one myself using #Python and the #PyMuPDF library. Here it is, open source, and ready for use:

https://github.com/aourednik/pdf2epub3fixed

My script is particularly suitable for the conversion of complex layout PDFs generated with variants of #TeXLaTeX.
Enjoy!