Skip to content

Latest commit

 

History

History
11 lines (6 loc) · 583 Bytes

File metadata and controls

11 lines (6 loc) · 583 Bytes

Digit-Recognizer

This is a simple convoluation neural network using tensorflow to classify numbers from 0 to 9 with train and test accuracy of 98.98%. The dataset is taken from mnist dataset consisting of 70000 images out of which 60000 are train images and 10000 are test images.

After the model has been trained, 'mnist.h5' is generated to create a GUI to predict the digits using Tkinter.

Example:

Example 1

Example 2