gsurma/digit_recognizer

CNN digit recognizer implemented in Keras Notebook, Kaggle/MNIST (0.995).

42
/ 100
Emerging

This project helps machine learning practitioners or data scientists to automatically recognize handwritten digits from images. You provide it with images of handwritten numbers, and it tells you which digit (0-9) is in each image. This is ideal for those learning about or competing in image classification tasks.

No commits in the last 6 months.

Use this if you need a high-performing example of a Convolutional Neural Network for classifying handwritten digits.

Not ideal if you are looking for a general-purpose image classification tool beyond simple digit recognition or if you don't have programming experience.

handwriting-recognition image-classification machine-learning-education pattern-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

32

Forks

18

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gsurma/digit_recognizer"

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