Use the example found at https://github.com/PacktPublishing/Java-Deep-Learning-Cookbook/blob/master/05_Implementing_NLP/sourceCode/cookbookapp/src/main/java/com/javadeeplearningcookbook/examples/CnnWord2VecSentenceClassificationExample.java for reference.

You should also make sure that you add more Java heap space through changing the VM options—for example, if you have 8 GB of RAM, then you may set -Xmx2G -Xmx6G as VM arguments.

We will extract the IMDB data to start with in step 1. The file structure will look like the following:

If we further navigate to the dataset directories, you will see them labeled as follows: