ml-java-samples

some experiments with machine learning libraries:

• Stanford CoreNLP: https://stanfordnlp.github.io/CoreNLP/
• Weka 3: https://www.cs.waikato.ac.nz/ml/weka/
• WekaDeeplearning4j: https://deeplearning.cms.waikato.ac.nz and https://github.com/Waikato/wekaDeeplearning4j
• Tensorflow Object Detection API: https://github.com/tensorflow/models/tree/master/research/object_detection

Stanford NLP features

For some operations it can consume a lot of time and memory. See https://stanfordnlp.github.io/CoreNLP/memory-time.html For instance, StanfordNlpAnalyzer uses quite expensive operations and in my machine it works only if I run it with 5 Gb memory. So, it is recommended to run

    java -Xms1g -Xmx5g

WekaDeeplearning4j features

As of now it is not provided in any maven repository, therefore you need to install this package to your local .m2 repository:

git clone https://github.com/Waikato/wekaDeeplearning4j.git
cd wekaDeeplearning4j
./gradlew build -x test publishToMavenLocal

How to run

mvn exec:java

it will run WekaAnalizer class