Tensorflow interop Key features and brief samples.

Nd4j allows execution of models via javacpp's tensorflow bindings using nd4j's INDArray as a data structure. Leveraging the nd4j-tensorflow interop is fairly simple.

Note, this is based on tensorflow 1.x. TF java 2 will be coming at a later time.

A tensorflow model can be loaded and executed as follows:

        File f = new File ("path/to/your/model.pb");
        INDArray x = Nd4j.scalar(1.0f).reshape(1,1);
        INDArray y = Nd4j.scalar(1.0f).reshape(1,1);
        List<String> inputNames = Arrays.asList("x","y");
        List<String> outputNames = Arrays.asList("z");
        GraphRunner tensorflowRunner = GraphRunner.builder()
        Map<String,INDArray> inputs = new LinkedHashMap<>();
        Map<String, INDArray> exec = tensorflowRunner.exec(inputs);
        INDArray z = exec.get("z");

This outputs a result with a map of output names to the ndarray result from tensorflow.

In maven, add the following dependency:


Note, this depends on javacpp's tensorflow bindings. This means tensorflow's native binaries are managed by javacpp. Javacpp will bundle all native binaries for all platforms by default unless you specify a platform. You can do this by specifying a -Dplatform=your-platform-of-choice. You may find more here in the javacpp docs.

Last updated