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

[xmings]

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 ??

[Craigacp]

What do you expect tf.create to do? As far as I can tell there isn't an equivalent method in TF Python.

Depending on what your input looks like you can use the different tensor types (e.g. TFloat32, TInt32) and their factory methods (e.g. scalarOf, vectorOf), or the ndarray library (https://github.com/tensorflow/java-ndarray) to construct the right inputs for your model.