Skip to content

Recognition of handwritten digits using neural networks (From scratch)

Notifications You must be signed in to change notification settings

Subhash3/Handwritten-digit-recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Handwritten Digit Recognition using Feed Forward Neural Networks.

  • This project utilises a neural network library, nicenet.
  • Check out its implementation from scratch here. For the pip3 package info, click here

Files in this repo

  • datasets/mnist.pkl.gz
    • gzipped serialized mnist dataset.
  • models/
    • Contains the exported trained models with different accuracy.
  • handwritten_digits.json - A pretrained model with an accuracy around 95%. - It is trained for 10 epochs with 50k samples of the MNIST training data
  • handwritten_digits.ipynb - Python3 notebook.
Feel free to contribute and open any issues!

About

Recognition of handwritten digits using neural networks (From scratch)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published