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)

Constructing a custom optimizer

The objective is to iteratively minimize the overall loss with the help of an optimization algorithm. In the paper by Gatys et al., optimization was done using the L-BFGS algorithm, which is an optimization algorithm based on Quasi-Newton methods, which are popularly used for solving non-linear optimization problems and parameter estimation. This method usually converges faster than standard gradient descent.

SciPy has an implementation available in scipy.optimize.fmin_l_bfgs_b(); however, limitations include the function being applicable only to flat one-dimensional vectors, unlike three-dimensional image matrices that we are dealing with, and the fact that the value of loss function and gradients need to be passed as two separate functions. We build an Evaluator class based on patterns, followed by keras creator François Chollet, to compute...