Skip to content

Trained a model on MNIST handwritten digit database using simple CNN in Keras, along with a GUI test application

Notifications You must be signed in to change notification settings

rssaini01/handwritten-digits-recognition

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Handwritten Digits Recognition Using CNN in Keras

Trained a model on MNIST handwritten digit database using CS231N in Keras.

Also implemented a GUI app to allow users to draw their own digit to test the model.

Training App

requirements

numpy
tensorflow
keras

run training

  1. Edit the config in training_app/config.py if necessary
  2. Run digitrecognition.py

result

0.9862 accuracy in 3 epochs

GUI Inference App

By utilizing trained model, we can predict given any images Here is an simple GUI application implemented in Django, which allows you draw a digit and run the prediction.

requirements

numpy
tensorflow
keras
pillow
django

run inference app

  1. cd to gui_inference_app
  2. make sure packages are installed correctly
  3. python manage.py runserver
  4. Open http://127.0.0.1:8000 in your browser

Demo

About

Trained a model on MNIST handwritten digit database using simple CNN in Keras, along with a GUI test application

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 66.4%
  • JavaScript 18.0%
  • HTML 15.0%
  • CSS 0.6%