Packt+ | Advance your knowledge in tech

You're reading from Java Deep Learning Projects Implement 10 real-world deep learning applications using Deeplearning4j and open source APIs

Product type Paperback

Published in Jun 2018

Publisher Packt

ISBN-13 9781788997454

Length 436 pages

Edition 1st Edition

Languages

Java

Tools

Deeplearning4j

Concepts

Deep Learning

Author (1):

Md. Rezaul Karim

View More author details

Table of Contents (17) Chapters

Title Page

Packt Upsell

Contributors

Preface

1. Getting Started with Deep Learning FREE CHAPTER

2. Cancer Types Prediction Using Recurrent Type Networks

3. Multi-Label Image Classification Using Convolutional Neural Networks

4. Sentiment Analysis Using Word2Vec and LSTM Network

5. Transfer Learning for Image Classification

6. Real-Time Object Detection using YOLO, JavaCV, and DL4J

7. Stock Price Prediction Using LSTM Network

8. Distributed Deep Learning – Video Classification Using Convolutional LSTM Networks

9. Playing GridWorld Game Using Deep Reinforcement Learning

10. Developing Movie Recommendation Systems Using Factorization Machines

11. Discussion, Current Trends, and Outlook

1. Other Books You May Enjoy

Leave a review - let other readers know what you think

Index

Chapter 5. Transfer Learning for Image Classification

In Chapter 3, Multi-LabelImage Classification using Convolutional Neural Networks, we saw how to develop an end-to-end project for handling multi-label image classification problems using CNN based on Java and the Deeplearning4J (DL4J) framework on real Yelp image datasets. For that purpose, we developed a CNN model from scratch.

Unfortunately, developing such a model from scratch is very time consuming and requires a significant amount of computational resources. Secondly, sometimes, we may not even have enough data to train such deep networks. For example, ImageNet is one of the largest image datasets at the moment and has millions of labeled images.

Therefore, we will develop an end-to-end project to solve dog versus cat image classification using a pretrained VGG-16 model, which is already trained with ImageNet. In the end, we will wrap up everything in a Java JFrame and JPanel application to make the overall pipeline understandable...