Package com.codedstream.otterstream.inference.model

Enum ModelFormat

  • All Implemented Interfaces:
    Serializable, Comparable<ModelFormat>
    public enum ModelFormat
extends Enum<ModelFormat>
    Enumeration of supported ML model formats in Otter Stream.

    Defines all model formats that can be loaded and executed by the framework. Each format corresponds to a specific inference engine implementation.

    Local Model Formats:

    • ONNX: Cross-platform neural network format
    • TENSORFLOW_SAVEDMODEL: TensorFlow 2.x SavedModel format
    • TENSORFLOW_GRAPHDEF: TensorFlow 1.x frozen graph (.pb)
    • PYTORCH_TORCHSCRIPT: PyTorch TorchScript models
    • XGBOOST_BINARY: XGBoost binary model files
    • PMML: Predictive Model Markup Language

    Remote Inference Formats:

    • REMOTE_HTTP: Generic REST API endpoints
    • REMOTE_GRPC: gRPC endpoints
    • SAGEMAKER: AWS SageMaker endpoints
    • VERTEX_AI: Google Cloud Vertex AI
    • AZURE_ML: Azure Machine Learning

    Usage Example:

    
 ModelFormat format = ModelFormat.ONNX;
 System.out.println(format.getDescription());  // "Open Neural Network Exchange"
 System.out.println(format.getExtension());    // "onnx"
    Since:
    1.0.0
    Author:
    Nestor Martourez, Sr Software and Data Streaming Engineer @ CodedStreams
    See Also:
    ModelConfig

    • Enum Constant Detail

      • ONNX

        public static final ModelFormat ONNX
        Open Neural Network Exchange format - cross-platform standard

      • TENSORFLOW_SAVEDMODEL

        public static final ModelFormat TENSORFLOW_SAVEDMODEL
        TensorFlow SavedModel format - TensorFlow 2.x default

      • TENSORFLOW_GRAPHDEF

        public static final ModelFormat TENSORFLOW_GRAPHDEF
        TensorFlow GraphDef format - TensorFlow 1.x frozen graphs

      • PYTORCH_TORCHSCRIPT

        public static final ModelFormat PYTORCH_TORCHSCRIPT
        PyTorch TorchScript format - serialized PyTorch models

      • XGBOOST_BINARY

        public static final ModelFormat XGBOOST_BINARY
        XGBoost binary format - gradient boosting models

      • XGBOOST_JSON

        public static final ModelFormat XGBOOST_JSON

      • PMML

        public static final ModelFormat PMML
        Predictive Model Markup Language - XML-based standard

      • REMOTE_HTTP

        public static final ModelFormat REMOTE_HTTP
        Remote HTTP/REST endpoint

      • REMOTE_GRPC

        public static final ModelFormat REMOTE_GRPC
        Remote gRPC endpoint

      • SAGEMAKER

        public static final ModelFormat SAGEMAKER
        AWS SageMaker hosting service

      • VERTEX_AI

        public static final ModelFormat VERTEX_AI
        Google Cloud Vertex AI service

      • AZURE_ML

        public static final ModelFormat AZURE_ML
        Azure Machine Learning service

    • Method Detail

      • values

        public static ModelFormat[] values()
        Returns an array containing the constants of this enum type, in the order they are declared. This method may be used to iterate over the constants as follows: 
        for (ModelFormat c : ModelFormat.values())
    System.out.println(c);
        Returns:
        an array containing the constants of this enum type, in the order they are declared

      • valueOf

        public static ModelFormat valueOf​(String name)
        Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)
        Parameters:
        name - the name of the enum constant to be returned.
        Returns:
        the enum constant with the specified name
        Throws:
        IllegalArgumentException - if this enum type has no constant with the specified name
        NullPointerException - if the argument is null

      • getExtension

        public String getExtension()
        Gets the file extension for this model format.
        Returns:
        file extension (without dot)

      • getDescription

        public String getDescription()
        Gets the human-readable description.
        Returns:
        format description