In this recipe, we will discuss transfer learning, a very powerful deep learning technique that has many 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 pretrained CNNs to generate representations for novel tasks, where the dataset may not be large enough to train an entire CNN from scratch. Another common tactic is to take the pretrained ImageNet network and then to fine-tune the entire network to the novel task. The example proposed here has been inspired by Francois Chollet in a famous blog posting for Keras. (https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html)