Tensorflow Java Api Set Placeholder For Categorical Columns

I want to predict on my trained Model from Python Tensorflow API with the Java API, but have problems to feed in the features to predict in Java. My Python Code is like this: from

Solution 1:

Since you're using tf.estimator.export.build_parsing_serving_input_receiver_fn, the exported saved model you've created expects a serialized tf.Example protocol buffer as input.

You can use the tf.Example protocol buffer in Java (maven, javadoc), using something like this:

import com.google.protobuf.ByteString;
import java.util.Arrays;
import org.tensorflow.*;
import org.tensorflow.example.*;

publicclassMain {
  // Returns a Feature containing a BytesList, where each element of the list// is the UTF-8 encoded bytes of the Java string.publicstatic Feature feature(String... strings) {
    BytesList.Builderb= BytesList.newBuilder();
    for (String s : strings) {
      b.addValue(ByteString.copyFromUtf8(s));
    }
    return Feature.newBuilder().setBytesList(b).build();
  }

  publicstatic Feature feature(float... values) {
    FloatList.Builderb= FloatList.newBuilder();
    for (float v : values) {
      b.addValue(v);
    }
    return Feature.newBuilder().setFloatList(b).build();
  }

  publicstaticvoidmain(String[] args)throws Exception {
    Featuresfeatures=
        Features.newBuilder()
            .putFeature("Attribute1", feature("A12"))
            .putFeature("Attribute2", feature(12))
            .putFeature("Attribute3", feature("A32"))
            .putFeature("Attribute4", feature("A40"))
            .putFeature("Attribute5", feature(7472))
            .putFeature("Attribute6", feature("A65"))
            .putFeature("Attribute7", feature("A71"))
            .putFeature("Attribute8", feature(1))
            .putFeature("Attribute9", feature("A92"))
            .putFeature("Attribute10", feature("A101"))
            .putFeature("Attribute11", feature(2))
            .putFeature("Attribute12", feature("A121"))
            .putFeature("Attribute13", feature(24))
            .putFeature("Attribute14", feature("A143"))
            .putFeature("Attribute15", feature("A151"))
            .putFeature("Attribute16", feature(1))
            .putFeature("Attribute17", feature("A171"))
            .putFeature("Attribute18", feature(1))
            .putFeature("Attribute19", feature("A191"))
            .putFeature("Attribute20", feature("A201"))
            .build();
    Exampleexample= Example.newBuilder().setFeatures(features).build();

    Stringpfad= System.getProperty("user.dir") + "\\1511523781";
    try (SavedModelBundlemodel= SavedModelBundle.load(pfad, "serve")) {
      Sessionsession= model.session();
      finalStringxName="input_example_tensor";
      finalStringscoresName="dnn/head/predictions/probabilities:0";

      try (Tensor<String> inputBatch = Tensors.create(newbyte[][] {example.toByteArray()});
          Tensor<Float> output =
              session
                  .runner()
                  .feed(xName, inputBatch)
                  .fetch(scoresName)
                  .run()
                  .get(0)
                  .expect(Float.class)) {
        System.out.println(Arrays.deepToString(output.copyTo(newfloat[1][2])));
      }
    }
  }
}

Much of the boilerplate here is to construct the protocol buffer example. Alternatively, you could use something other than build_arsing_serving_input_receiver_fn to setup the exported model to accept input in a different format.

Side note: You can use the saved_model_cli command-line tool that is included with TensorFlow Python installation to inspect the saved model. For example, something like:

saved_model_cli show  \
  --dir ./export/1511523781 \--tag_set serve \--signature_def predict

will show something like:

ThegivenSavedModelSignatureDefcontainsthefollowinginput(s):inputs['examples']tensor_info:dtype:DT_STRINGshape:(-1)name:input_example_tensor:0ThegivenSavedModelSignatureDefcontainsthefollowingoutput(s):...outputs['probabilities']tensor_info:dtype:DT_FLOATshape:(-1,2)name:dnn/head/predictions/probabilities:0

Suggesting that the saved model takes a single input - a batch of DT_STRING elements and the output probabilities are a batch of 2-dimensional float vectors.

Hope that helps.