Skip to content

A VGG neural network that classifies multiple handwritten digits from a single picture

Notifications You must be signed in to change notification settings

Louismousine/Multi-Digit-Neural-Network-Classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Multi Digit Neural Network Classifier

COMP 551: Applied machine learning project 3.

This project implements a VGG deep learning neural network to classify multiple modified MNIST digits. The model achieved 100% validation and training accuracy after about 40 epochs, and reached 99.785% accuracy on the Kaggle test set - which is good for 6th place / 98.

Project done with Sofia Dieguez and Diana Sera.

About

A VGG neural network that classifies multiple handwritten digits from a single picture

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published