Book Image

Hands-On Transfer Learning with Python

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

Hands-On Transfer Learning with Python

By: Dipanjan Sarkar, Nitin Panwar, 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)


Deep neural networks are extremely powerful models with hundreds and thousands of learnable parameters. The current scenario of training a coloring network presents a new set of challenges, some of which are discussed as follows:

  • The current network seems to have learned high-level features, such as grass and sports jerseys (to a certain extent), while it found learning color patterns for smaller objects a bit too difficult.
  • The training set was limited to a very specific subset of images and hence that is reflected in the test dataset. The model has poor performance on objects that are either not present in the training set or not many samples contain them.
  • Even though the training loss seems to have stabilized in under 50 epochs, we see that the model's performance on coloring is quite poor unless trained for a few hundred epochs.
  • The model has a high tendency...