Cats and Dogs Classification with Pre-trained Neural Network

Deep neural networks require a large amount of data and computing power to train them from scratch. Collecting and annotating the data is time-consuming and expensive. Even with the right computer, it may take days and weeks to train a deep-learning model with millions of data points. Big IT companies have trained and optimized deep neural networks on these large datasets, and have made these models available to everyone. You can use these pre-trained models as is or customize them to a specific task with transfer learning. In this project, you will learn how to use pre-trained models and transfer learning to circumvent the data and compute resource challenges in training deep-learning models from scratch.