Packt+ | Advance your knowledge in tech

You're reading from Apache Spark Deep Learning Cookbook Over 80 best practice recipes for the distributed training and deployment of neural networks using Keras and TensorFlow

Product type Paperback

Published in Jul 2018

Publisher Packt

ISBN-13 9781788474221

Length 474 pages

Edition 1st Edition

Languages

Scala

Tools

Apache Spark

Concepts

Deep Learning

Authors (2):

Ahmed Sherif

Amrith Ravindra

View More author details

Table of Contents (15) Chapters

Preface

1. Setting Up Spark for Deep Learning Development FREE CHAPTER

2. Creating a Neural Network in Spark

3. Pain Points of Convolutional Neural Networks

4. Pain Points of Recurrent Neural Networks

5. Predicting Fire Department Calls with Spark ML

6. Using LSTMs in Generative Networks

7. Natural Language Processing with TF-IDF

8. Real Estate Value Prediction Using XGBoost

9. Predicting Apple Stock Market Cost with LSTM

10. Face Recognition Using Deep Convolutional Networks

11. Creating and Visualizing Word Vectors Using Word2Vec

12. Creating a Movie Recommendation Engine with Keras

13. Image Classification with TensorFlow on Spark

14. Other Books You May Enjoy

Leave a review - let other readers know what you think

Downloading and loading the MIT-CBCL dataset into the memory

In this recipe, we will understand how to download the MIT-CBCL dataset and load it into the memory.

With a predicted worth of $15 billion by 2025, the biometrics industry is poised to grow like never before. Some of the examples of physiological characteristics used for biometric authentication include fingerprints, DNA, face, retina or ear features, and voice. While technologies such as DNA authentication and fingerprints are quite advanced, face recognition brings its own advantages to the table.

Ease of use and robustness due to recent developments in deep learning models are some of the driving factors behind face recognition algorithms gaining so much popularity.

Getting ready

The following key points need to be considered for this recipe:

The MIT-CBCL dataset is composed of 3,240 images (324 images per subject). In our model, we will make arrangements to augment the data in order to increase model robustness. We will employ techniques...