Skip to content

siddhi-execution-tensorflow

The siddhi-execution-tensorflow is an extension to Siddhi that adds support for inferences from pre-built TensorFlow SavedModels using Siddhi.

Find some useful links below:

Latest API Docs

Latest API Docs is 1.1.0.

How to use

Using the extension in WSO2 Stream Processor

Using the extension as a java library

  • This extension can be added as a maven dependency along with other Siddhi dependencies to your project.
     <dependency>
        <groupId>org.wso2.extension.siddhi.execution.tensorflow</groupId>
        <artifactId>siddhi-execution-tensorflow</artifactId>
        <version>x.x.x</version>
     </dependency>

Jenkins Build Status


Branch Build Status
master Build Status

Features

  • predict (Stream Processor)

    Performs inferences (prediction) from an already built TensorFlow machine learning model. The types of models are unlimited (including image classifiers, deep learning models) as long as they satisfy the following conditions.
    1. They are saved with the tag 'serve' in SavedModel format (See https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md)
    2. Model is initially trained and ready for inferences
    3. Inference logic is written and saved in the model
    4. signature_def is properly included in the metaGraphDef (a protocol buffer file which has information about the graph) and the key for prediction signature def is 'serving-default'

    Also the prerequisites for inference are as follows.
    1. User knows the names of the input and output nodes
    2. Has a preprocessed data set of Java primitive types or their multidimensional arrays

    Since each input is directly used to create a Tensor they should be of compatible shape and data type with the model.
    The information related to input and output nodes can be retrieved from saved model signature def.signature_def can be read by using the saved_model_cli commands found at https://www.tensorflow.org/programmers_guide/saved_model
    signature_def can be read in Python as follows
    with tf.Session() as sess:
      md = tf.saved_model.loader.load(sess, ['serve'], export_dir)
      sig = md.signature_def[tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY]
      print(sig)

    Or you can read signature def from Java as follows,
    final String DEFAULT_SERVING_SIGNATURE_DEF_KEY = "serving_default";

    final SignatureDef sig =
          MetaGraphDef.parseFrom(model.metaGraphDef())
              .getSignatureDefOrThrow(DEFAULT_SERVING_SIGNATURE_DEF_KEY);

    You will have to import the following in Java.
    import org.tensorflow.framework.MetaGraphDef;
    import org.tensorflow.framework.SignatureDef;

How to Contribute

Contact us

Support

  • We are committed to ensuring support for this extension in production. Our unique approach ensures that all support leverages our open development methodology and is provided by the very same engineers who build the technology.

  • For more details and to take advantage of this unique opportunity contact us via http://wso2.com/support/.