Before we begin, let us understand the dataset. In this article, we will be solving the popular MNIST problem. It is a digit recognition task wherein we have to classify the images of handwritten digits into either of the 10 classes which are 0 to 9.
In the MNIST dataset, we have images of digits that were taken from a variety of scanned documents, normalized in size, and centered. Subsequently, each image is a 28 by 28-pixel square (784 pixels total). A standard split of the dataset is used to evaluate and compare models, where 60,000 images are used to train a model and a separate set of 10,000 images are used to test it.
This is beginner guide in CNN in PyTorch and TensorFlow
#tensorflow #pytorch