Package onnx

Enum Onnx.Version

  • All Implemented Interfaces:
    Serializable, Comparable<Onnx.Version>, org.nd4j.shade.protobuf.Internal.EnumLite, org.nd4j.shade.protobuf.ProtocolMessageEnum
    Enclosing class:
    Onnx
    public static enum Onnx.Version
extends Enum<Onnx.Version>
implements org.nd4j.shade.protobuf.ProtocolMessageEnum
     Versioning
 ONNX versioning is specified in docs/IR.md and elaborated on in docs/Versioning.md
 To be compatible with both proto2 and proto3, we will use a version number
 that is not defined by the default value but an explicit enum number.
    Protobuf enum onnx.Version

    • Enum Constant Summary

      Enum Constants 
      Enum Constant Description
      _START_VERSION
      proto3 requires the first enum value to be zero.
      IR_VERSION
      IR VERSION 8 published on <TBD> Introduce TypeProto.SparseTensor Introduce TypeProto.Optional Added a list of FunctionProtos local to the model Deprecated since_version and operator status from FunctionProto
      IR_VERSION_2017_10_10
      The version field is always serialized and we will use it to store the version that the graph is generated from.
      IR_VERSION_2017_10_30
      IR_VERSION 2 published on Oct 30, 2017 - Added type discriminator to AttributeProto to support proto3 users
      IR_VERSION_2017_11_3
      IR VERSION 3 published on Nov 3, 2017 - For operator versioning: - Added new message OperatorSetIdProto - Added opset_import in ModelProto - For vendor extensions, added domain in NodeProto
      IR_VERSION_2019_1_22
      IR VERSION 4 published on Jan 22, 2019 - Relax constraint that initializers should be a subset of graph inputs - Add type BFLOAT16
      IR_VERSION_2019_3_18
      IR VERSION 5 published on March 18, 2019 - Add message TensorAnnotation.
      IR_VERSION_2019_9_19
      IR VERSION 6 published on Sep 19, 2019 - Add support for sparse tensor constants stored in model.
      IR_VERSION_2020_5_8
      IR VERSION 7 published on May 8, 2020 - Add support to allow function body graph to rely on multiple external opreator sets.
      UNRECOGNIZED  

    • Field Summary

      Fields 
      Modifier and Type Field Description
      static int _START_VERSION_VALUE
      proto3 requires the first enum value to be zero.
      static int IR_VERSION_2017_10_10_VALUE
      The version field is always serialized and we will use it to store the version that the graph is generated from.
      static int IR_VERSION_2017_10_30_VALUE
      IR_VERSION 2 published on Oct 30, 2017 - Added type discriminator to AttributeProto to support proto3 users
      static int IR_VERSION_2017_11_3_VALUE
      IR VERSION 3 published on Nov 3, 2017 - For operator versioning: - Added new message OperatorSetIdProto - Added opset_import in ModelProto - For vendor extensions, added domain in NodeProto
      static int IR_VERSION_2019_1_22_VALUE
      IR VERSION 4 published on Jan 22, 2019 - Relax constraint that initializers should be a subset of graph inputs - Add type BFLOAT16
      static int IR_VERSION_2019_3_18_VALUE
      IR VERSION 5 published on March 18, 2019 - Add message TensorAnnotation.
      static int IR_VERSION_2019_9_19_VALUE
      IR VERSION 6 published on Sep 19, 2019 - Add support for sparse tensor constants stored in model.
      static int IR_VERSION_2020_5_8_VALUE
      IR VERSION 7 published on May 8, 2020 - Add support to allow function body graph to rely on multiple external opreator sets.
      static int IR_VERSION_VALUE
      IR VERSION 8 published on <TBD> Introduce TypeProto.SparseTensor Introduce TypeProto.Optional Added a list of FunctionProtos local to the model Deprecated since_version and operator status from FunctionProto

    • Enum Constant Detail

      • _START_VERSION

        public static final Onnx.Version _START_VERSION
         proto3 requires the first enum value to be zero.
 We add this just to appease the compiler.
        _START_VERSION = 0;

      • IR_VERSION_2017_10_10

        public static final Onnx.Version IR_VERSION_2017_10_10
         The version field is always serialized and we will use it to store the
 version that the  graph is generated from. This helps us set up version
 control.
 For the IR, we are using simple numbers starting with 0x00000001,
 which was the version we published on Oct 10, 2017.
        IR_VERSION_2017_10_10 = 1;

      • IR_VERSION_2017_10_30

        public static final Onnx.Version IR_VERSION_2017_10_30
         IR_VERSION 2 published on Oct 30, 2017
 - Added type discriminator to AttributeProto to support proto3 users
        IR_VERSION_2017_10_30 = 2;

      • IR_VERSION_2017_11_3

        public static final Onnx.Version IR_VERSION_2017_11_3
         IR VERSION 3 published on Nov 3, 2017
 - For operator versioning:
    - Added new message OperatorSetIdProto
    - Added opset_import in ModelProto
 - For vendor extensions, added domain in NodeProto
        IR_VERSION_2017_11_3 = 3;

      • IR_VERSION_2019_1_22

        public static final Onnx.Version IR_VERSION_2019_1_22
         IR VERSION 4 published on Jan 22, 2019
 - Relax constraint that initializers should be a subset of graph inputs
 - Add type BFLOAT16
        IR_VERSION_2019_1_22 = 4;

      • IR_VERSION_2019_3_18

        public static final Onnx.Version IR_VERSION_2019_3_18
         IR VERSION 5 published on March 18, 2019
 - Add message TensorAnnotation.
 - Add quantization annotation in GraphProto to map tensor with its scale and zero point quantization parameters.
        IR_VERSION_2019_3_18 = 5;

      • IR_VERSION_2019_9_19

        public static final Onnx.Version IR_VERSION_2019_9_19
         IR VERSION 6 published on Sep 19, 2019
 - Add support for sparse tensor constants stored in model.
   - Add message SparseTensorProto
   - Add sparse initializers
        IR_VERSION_2019_9_19 = 6;

      • IR_VERSION_2020_5_8

        public static final Onnx.Version IR_VERSION_2020_5_8
         IR VERSION 7 published on May 8, 2020
 - Add support to allow function body graph to rely on multiple external opreator sets.
 - Add a list to promote inference graph's initializers to global and
   mutable variables. Global variables are visible in all graphs of the
   stored models.
 - Add message TrainingInfoProto to store initialization
   method and training algorithm. The execution of TrainingInfoProto
   can modify the values of mutable variables.
 - Implicitly add inference graph into each TrainingInfoProto's algorithm.
        IR_VERSION_2020_5_8 = 7;

      • IR_VERSION

        public static final Onnx.Version IR_VERSION
         IR VERSION 8 published on <TBD>
 Introduce TypeProto.SparseTensor
 Introduce TypeProto.Optional
 Added a list of FunctionProtos local to the model
 Deprecated since_version and operator status from FunctionProto
        IR_VERSION = 8;

      • UNRECOGNIZED

        public static final Onnx.Version UNRECOGNIZED

    • Field Detail

      • _START_VERSION_VALUE

        public static final int _START_VERSION_VALUE
         proto3 requires the first enum value to be zero.
 We add this just to appease the compiler.
        _START_VERSION = 0;
        See Also:
        Constant Field Values

      • IR_VERSION_2017_10_10_VALUE

        public static final int IR_VERSION_2017_10_10_VALUE
         The version field is always serialized and we will use it to store the
 version that the  graph is generated from. This helps us set up version
 control.
 For the IR, we are using simple numbers starting with 0x00000001,
 which was the version we published on Oct 10, 2017.
        IR_VERSION_2017_10_10 = 1;
        See Also:
        Constant Field Values

      • IR_VERSION_2017_10_30_VALUE

        public static final int IR_VERSION_2017_10_30_VALUE
         IR_VERSION 2 published on Oct 30, 2017
 - Added type discriminator to AttributeProto to support proto3 users
        IR_VERSION_2017_10_30 = 2;
        See Also:
        Constant Field Values

      • IR_VERSION_2017_11_3_VALUE

        public static final int IR_VERSION_2017_11_3_VALUE
         IR VERSION 3 published on Nov 3, 2017
 - For operator versioning:
    - Added new message OperatorSetIdProto
    - Added opset_import in ModelProto
 - For vendor extensions, added domain in NodeProto
        IR_VERSION_2017_11_3 = 3;
        See Also:
        Constant Field Values

      • IR_VERSION_2019_1_22_VALUE

        public static final int IR_VERSION_2019_1_22_VALUE
         IR VERSION 4 published on Jan 22, 2019
 - Relax constraint that initializers should be a subset of graph inputs
 - Add type BFLOAT16
        IR_VERSION_2019_1_22 = 4;
        See Also:
        Constant Field Values

      • IR_VERSION_2019_3_18_VALUE

        public static final int IR_VERSION_2019_3_18_VALUE
         IR VERSION 5 published on March 18, 2019
 - Add message TensorAnnotation.
 - Add quantization annotation in GraphProto to map tensor with its scale and zero point quantization parameters.
        IR_VERSION_2019_3_18 = 5;
        See Also:
        Constant Field Values

      • IR_VERSION_2019_9_19_VALUE

        public static final int IR_VERSION_2019_9_19_VALUE
         IR VERSION 6 published on Sep 19, 2019
 - Add support for sparse tensor constants stored in model.
   - Add message SparseTensorProto
   - Add sparse initializers
        IR_VERSION_2019_9_19 = 6;
        See Also:
        Constant Field Values

      • IR_VERSION_2020_5_8_VALUE

        public static final int IR_VERSION_2020_5_8_VALUE
         IR VERSION 7 published on May 8, 2020
 - Add support to allow function body graph to rely on multiple external opreator sets.
 - Add a list to promote inference graph's initializers to global and
   mutable variables. Global variables are visible in all graphs of the
   stored models.
 - Add message TrainingInfoProto to store initialization
   method and training algorithm. The execution of TrainingInfoProto
   can modify the values of mutable variables.
 - Implicitly add inference graph into each TrainingInfoProto's algorithm.
        IR_VERSION_2020_5_8 = 7;
        See Also:
        Constant Field Values

      • IR_VERSION_VALUE

        public static final int IR_VERSION_VALUE
         IR VERSION 8 published on <TBD>
 Introduce TypeProto.SparseTensor
 Introduce TypeProto.Optional
 Added a list of FunctionProtos local to the model
 Deprecated since_version and operator status from FunctionProto
        IR_VERSION = 8;
        See Also:
        Constant Field Values

    • Method Detail

      • values

        public static Onnx.Version[] 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 (Onnx.Version c : Onnx.Version.values())
    System.out.println(c);
        Returns:
        an array containing the constants of this enum type, in the order they are declared

      • valueOf

        public static Onnx.Version 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

      • getNumber

        public final int getNumber()
        Specified by:
        getNumber in interface org.nd4j.shade.protobuf.Internal.EnumLite
        Specified by:
        getNumber in interface org.nd4j.shade.protobuf.ProtocolMessageEnum

      • valueOf

        @Deprecated
public static Onnx.Version valueOf​(int value)
        Deprecated.
        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:
        value - 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

      • forNumber

        public static Onnx.Version forNumber​(int value)
        Parameters:
        value - The numeric wire value of the corresponding enum entry.
        Returns:
        The enum associated with the given numeric wire value.

      • internalGetValueMap

        public static org.nd4j.shade.protobuf.Internal.EnumLiteMap<Onnx.Version> internalGetValueMap()

      • getValueDescriptor

        public final org.nd4j.shade.protobuf.Descriptors.EnumValueDescriptor getValueDescriptor()
        Specified by:
        getValueDescriptor in interface org.nd4j.shade.protobuf.ProtocolMessageEnum

      • getDescriptorForType

        public final org.nd4j.shade.protobuf.Descriptors.EnumDescriptor getDescriptorForType()
        Specified by:
        getDescriptorForType in interface org.nd4j.shade.protobuf.ProtocolMessageEnum

      • getDescriptor

        public static final org.nd4j.shade.protobuf.Descriptors.EnumDescriptor getDescriptor()

      • valueOf

        public static Onnx.Version valueOf​(org.nd4j.shade.protobuf.Descriptors.EnumValueDescriptor desc)
        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:
        desc - 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