Reader small image

You're reading from  Advanced Deep Learning with TensorFlow 2 and Keras - Second Edition

Product typeBook
Published inFeb 2020
Reading LevelIntermediate
PublisherPackt
ISBN-139781838821654
Edition2nd Edition
Languages
Right arrow
Author (1)
Rowel Atienza
Rowel Atienza
author image
Rowel Atienza

Rowel Atienza is an Associate Professor at the Electrical and Electronics Engineering Institute of the University of the Philippines, Diliman. He holds the Dado and Maria Banatao Institute Professorial Chair in Artificial Intelligence. Rowel has been fascinated with intelligent robots since he graduated from the University of the Philippines. He received his MEng from the National University of Singapore for his work on an AI-enhanced four-legged robot. He finished his Ph.D. at The Australian National University for his contribution on the field of active gaze tracking for human-robot interaction. Rowel's current research work focuses on AI and computer vision. He dreams on building useful machines that can perceive, understand, and reason. To help make his dreams become real, Rowel has been supported by grants from the Department of Science and Technology (DOST), Samsung Research Philippines, and Commission on Higher Education-Philippine California Advanced Research Institutes (CHED-PCARI).
Read more about Rowel Atienza

Right arrow

5. Unsupervised clustering implementation in Keras

The network model implementation in Keras for unsupervised clustering is shown in Listing 13.5.1. Only the initialization is shown. The network hyperparameters are stored in args. The VGG backbone object is supplied during initializations. Given a backbone, the model is actually just a Dense layer with a softmax activation, as shown in the build_model() method. There is an option to create multiple heads.

Similar to Chapter 11, Object Detection, we implemented a DataGenerator class to efficiently serve input data in a multithreaded fashion. A DataGenerator object generates the required paired train input data (that is, a Siamese input image) made of the input image X and its transformed image . The most critical method, __data_generation(), of the DataGenerator class is shown in Listing 13.5.2. The input image X is center cropped from the original input image. In the case of MNIST, this is 24 x 24-pixel center cropping...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Advanced Deep Learning with TensorFlow 2 and Keras - Second Edition
Published in: Feb 2020Publisher: PacktISBN-13: 9781838821654

Author (1)

author image
Rowel Atienza

Rowel Atienza is an Associate Professor at the Electrical and Electronics Engineering Institute of the University of the Philippines, Diliman. He holds the Dado and Maria Banatao Institute Professorial Chair in Artificial Intelligence. Rowel has been fascinated with intelligent robots since he graduated from the University of the Philippines. He received his MEng from the National University of Singapore for his work on an AI-enhanced four-legged robot. He finished his Ph.D. at The Australian National University for his contribution on the field of active gaze tracking for human-robot interaction. Rowel's current research work focuses on AI and computer vision. He dreams on building useful machines that can perceive, understand, and reason. To help make his dreams become real, Rowel has been supported by grants from the Department of Science and Technology (DOST), Samsung Research Philippines, and Commission on Higher Education-Philippine California Advanced Research Institutes (CHED-PCARI).
Read more about Rowel Atienza