barzansaeedpour/object-localization-and-classification-with-one-network

This repository contains code and resources for performing object localization and classification using a single network on an Augmented MNIST dataset.

21
/ 100
Experimental

This project helps machine learning practitioners or researchers quickly experiment with a fundamental task in computer vision: identifying an object's type and its location within an image. You provide it with images containing a single, randomly positioned handwritten digit, and it outputs both the digit's classification (0-9) and a bounding box indicating its precise location. This is ideal for those exploring basic object detection concepts.

No commits in the last 6 months.

Use this if you are a machine learning student, researcher, or practitioner looking for a clear, hands-on example of a convolutional neural network that performs both image classification and object localization on a simple, augmented dataset.

Not ideal if you need a production-ready solution for complex multi-object detection in real-world images or if you're not familiar with fundamental machine learning and deep learning concepts.

computer-vision image-classification object-localization deep-learning-research machine-learning-education
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/barzansaeedpour/object-localization-and-classification-with-one-network"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.