Book Image

Hands-On Transfer Learning with Python

By : Dipanjan Sarkar, Raghav Bali, Tamoghna Ghosh
Book Image

Hands-On Transfer Learning with Python

By: Dipanjan Sarkar, Raghav Bali, Tamoghna Ghosh

Overview of this book

Transfer learning is a machine learning (ML) technique where knowledge gained during training a set of problems can be used to solve other similar problems. The purpose of this book is two-fold; firstly, we focus on detailed coverage of deep learning (DL) and transfer learning, comparing and contrasting the two with easy-to-follow concepts and examples. The second area of focus is real-world examples and research problems using TensorFlow, Keras, and the Python ecosystem with hands-on examples. The book starts with the key essential concepts of ML and DL, followed by depiction and coverage of important DL architectures such as convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM), and capsule networks. Our focus then shifts to transfer learning concepts, such as model freezing, fine-tuning, pre-trained models including VGG, inception, ResNet, and how these systems perform better than DL models with practical examples. In the concluding chapters, we will focus on a multitude of real-world case studies and problems associated with areas such as computer vision, audio analysis and natural language processing (NLP). By the end of this book, you will be able to implement both DL and transfer learning principles in your own systems.
Table of Contents (14 chapters)

Understanding image captioning

By now, you should understand the significance and meaning of image captioning. This task can be simply defined as writing and recording a free-flowing and natural text description for any image. It is usually used to describe various scenes or events in images. This is also popularly termed scene recognition. Let's look at the following example:

Looking at this scene, what could be a suitable caption or description? The following are all valid descriptions of the scene:

  • A motocross rider is on a dirt hill
  • A guy on a bicycle midair above a hill
  • A dirt bike rider is moving fast down a dirt path
  • A biker riding a black motorbike in midair

You can see that all of these captions are valid and are similar yet use different words to convey the same meaning. This is why generating image captions automatically is not an easy task.

In fact, the...