Overview
- Get an overview of PyTorch and TensorFlow
- Learn to build a Convolutional Neural Network (CNN) model in PyTorch to solve an Image Classification problem
- Learn to build a CNN model in TensorFlow to solve an Image Classification problem
Introduction
Image classification is one of the most important applications of computer vision. Its applications ranges from classifying objects in self driving cars to identifying blood cells in healthcare industry, from identifying defective items in manufacturing industry to build a system that can classify persons wearing masks or not. Image Classification is used in one way or the other in all these industries. How do they do it? Which framework do they use?
You must have read a lot about the differences between different deep learning frameworks including TensorFlow, PyTorch, Keras, and many more. TensorFlow and PyTorch are undoubtedly the most popular frameworks out of all in the industry. I am sure you will find endless resources to learn the similarities and differences between these deep learning frameworks.
- Here is one such resource for you: 5 Amazing Deep Learning Frameworks Every Data Scientist Must Know!
In this article, we will understand how to build a basic image classification model in PyTorch and TensorFlow. We will start with a brief overview of both PyTorch and TensorFlow. And then we will take the benchmark MNIST handwritten digit classification dataset and build an image classification model using CNN (Convolutional Neural Network) in PyTorch and TensorFlow.
This will act as a starting point for you and then you can pick any of the frameworks which you feel comfortable with and start building other computer vision models too.
Table of Contents
- Overview of PyTorch
- Overview of TensorFlow
- Understanding the Problem Statement: MNIST
- Implementing a CNN in PyTorch
- Implementing a CNN in TensorFlow
