![visitors](https://visitor-badge.glitch.me/badge?page_id=wissamantoun.arabicnlpapp)
[![DeepSource](https://static.deepsource.io/deepsource-badge-light-mini.svg)](https://deepsource.io/gh/Erlemar/digit-draw-detect/?ref=repository-badge )

This is a repo of my "Handwritten digit detector" pet-project. It uses a YOLOv3 model trained from scratch and Streamlit for frontent. You can see the live version of the app [here](https://huggingface.co/spaces/Artgor/digit-draw-detect).

If you are interested in reading more about this project, here are some links:
* [Project page on my personal website](https://andlukyane.com/project/drawn-digits-prediction)
* [A dataset with the digits and bounding boxes on Kaggle](https://www.kaggle.com/datasets/artgor/handwritten-digits-and-bounding-boxes)
* [Training code](https://github.com/Erlemar/pytorch_tempest_pet_)
* [Blogpost on my personal website](https://andlukyane.com/blog/a-third-life-of-a-personal-project)
* [Blogpost on medium](https://towardsdatascience.com/the-third-life-of-a-personal-pet-project-for-handwritten-digit-recognition-fd908dc8e7a1)
* [Russian blogpost on habr](https://habr.com/ru/company/ods/blog/707046/)
* [W&B report](https://wandb.ai/al-3002-w/pet_project_object_detection/reports/Training-a-model-for-Handwritten-Object-Detection---VmlldzozMTgwMzA2?accessToken=yi6t4sz6iwr1yp78nfpvw71qao5wibak30np9tfft885tdj26g3tk91h1sie3h5m)