The MNIST database of handwritten digits, has a training set of 60,000 examples, and a test set of 10,000 examples.The digits have been size-normalized and centered in a fixed-size image of 28*28
The attached .ipynb file discloses the training and testing of the model on MNIST dataset, The architecture and design of convolutional neural network has been implemented from scratch using pytorch backend. Testing accuracy of 99.4% is achieved by the model.