MNIST Handwritten Digit Recognition Using CNN

The MNIST dataset is an acronym that stands for the Modified National Institute of Standards and Technology dataset.It is a dataset of 60,000 small square 28×28 pixel grayscale images of handwritten single digits between 0 and 9.The task is to classify a given image of a handwritten digit into one of 10 classes representing integer values from 0 to 9, inclusively. It can be simply imported from Keras Datasets using from keras.datasets import mnist

Steps to run the code

• Run the Jupyter Notebook named as MNIST_DigitRecognition_UsingCNN.ipynb
• Save the weight as mnist.h5
• Using graphical user interface test the model -> Run gui.py

Result

Test loss: 0.0241182143806917
Test accuracy: 0.9933000206947327