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)

Exploratory analysis of audio events

We will follow a standard workflow of analyzing, visualizing, modeling, and evaluating our models on our audio data. Once all the data is downloaded, you will notice that there are a total of ten folders containing audio data samples in WAV format. We also have a metadata folder, which contains metadata information for each audio file in the UrbanSound8K.csv file. You can use this file to assign the class labels for each file or you can understand the file naming nomenclature to do the same.

Each audio file is named in a specific format. The name takes the [fsID]-[classID]-[occurrenceID]-[sliceID].wav format, which is populated as follows:

  • [fsID]: The freesound ID of the recording from which this excerpt (slice) is taken
  • [classID]: A numeric identifier of the sound class
  • [occurrenceID]: A numeric identifier to distinguish different occurrences...