Transfer learning is a very powerful deep learning technique which has more applications in different domains. The intuition is very simple and can be explained with an analogy. Suppose you want to learn a new language, say Spanish, then it could be useful to start from what you already know in a different language, say English.
Following this line of thinking, computer vision researchers now commonly use pre-trained CNNs to generate representations for new tasks, where the dataset may not be large enough to train an entire CNN from scratch. Another common tactic is to take the pre-trained ImageNet network and then fine-tune the entire network to the novel task.
InceptionV3 Net is a very deep ConvNet developed by Google. Keras implements the full network, shown in the following figure, and it comes pre-trained on ImageNet. The...