How to input data and recive returned results after loading the categorization model

dependency:

            <groupId>org.tensorflow</groupId>
            <artifactId>tensorflow-core-platform</artifactId>
            <version>0.4.1</version>
        </dependency>

code:

import org.{tensorflow=>tf}
val result = tf.SavedModelBundle
      .load("D:\\model\\categorization","serve")
      .session()
      .runner()
      .feed("serving_default_inputs:0", tf.create(List("....", "....")))
      .fetch("StatefulPartitionedCall:0")
      .run()
      .get(0);

However, no any create method found within tf, why ??

Start with the tensorflow-core-platform 0.4.1 dependency and the Scala code using SavedModelBundle, session, runner, feed, and fetch. Check the TensorFlow Java API for the supported way to construct the input tensor and retrieve the returned result; done means the loading, input, and output flow is documented for this example.