The project directory has a resource folder with the required data for the LineIterator examples:
For CnnWord2VecSentenceClassificationExample or GoogleNewsVectorExampleYou, you can download datasets from the following URLs:
- Google News vector: https://deeplearning4jblob.blob.core.windows.net/resources/wordvectors/GoogleNews-vectors-negative300.bin.gz
- IMDB review data: http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz
Note that IMDB review data needs to be extracted twice in order to get the actual dataset folder.
For the t-Distributed Stochastic Neighbor Embedding (t-SNE) visualization example, the required data (words.txt) can be located in the project root directory itself.