O'Reilly logo

Java Deep Learning Projects by Md. Rezaul Karim

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Transfer Learning for Image Classification

In Chapter 3, Multi-Label Image 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 ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required