Deploy LayoutLMv3 for Document Classification using Streamlit, Transformers and HuggingFace Spaces

preview_player
Показать описание


In this video, you'll learn how to deploy a pre-trained LayoutLMv3 model for document classification using Streamlit and HuggingFace Spaces. This is a powerful combination of tools that allows for easy and free deployment of pre-trained models. We will be going through the steps of loading the model, preparing the input data, and running the classification process. By the end of this video, you will have a solid understanding of how to deploy pre-trained models for document classification in your own projects and a demo app.

00:00 - Intro
00:36 - Demo app
01:46 - Streamlit
02:58 - Project setup
06:20 - VSCode setup
08:00 - Streamlit app
29:48 - Upload to HuggingFace Spaces
32:38 - Test the live app
33:24 - Conclusion

#pytorch #streamlit #python #deeplearning #machinelearning #tutorial #course
Рекомендации по теме
Комментарии
Автор

hi venelin, your tutorials are awesome... can you please make videos on data extraction from invoice using layoutLM ?

ospai-hn
Автор

Thank you Venelin, watched the whole playlist. You have demonstrated it very well. I wish you can create a video on how to extract ROI from the documents let say an ID card etc. Thanks again 🤗

syedasim
Автор

Have you attempted to run LayoutLMv3 on windows?

watafakmadafaka
Автор

Thank you so much for sharing this tutorial!
Have you uploaded the notebook? Where can we get it?

AndrewBelov-fe
Автор

is it possible to attach multiple images, and pdfs to the nlp and ask it a question that would require context from 1 or more documents?

cluberic