In today’s world, with the availability of enormous amounts of data and computation power, Machine Learning has gained a lot of momentum than before. Data is available in various forms and one of the most prominent forms of data is Images.
Classification is a kind of ML problem where we have a set of data points and we classify or label each point into a respective class. In this way, a particular data point can be differentiated from the neighboring points. Likewise in the case of Image classification, we classify a particular image into the respective class it belongs too.
In this blog, we will try to take a look at the implementation of an image classifier from scratch in Pytorch.
PyTorch is an open-source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook’s AI Research lab.
It is an established computer-vision dataset used for object recognition. It is a subset of the 80 million tiny images dataset and consists of 60,000 32x32 color images containing one of 10 object classes, with 6000 images per class. It was collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton.
#machine-learning #classification #pytorch #cifar-10 #deep learning