final case class ModelProto(irVersion: Option[Long] = _root_.scala.None, opsetImport: Seq[OperatorSetIdProto] = _root_.scala.Seq.empty, producerName: Option[String] = _root_.scala.None, producerVersion: Option[String] = _root_.scala.None, domain: Option[String] = _root_.scala.None, modelVersion: Option[Long] = _root_.scala.None, docString: Option[String] = _root_.scala.None, graph: Option[GraphProto] = _root_.scala.None, metadataProps: Seq[StringStringEntryProto] = _root_.scala.Seq.empty, trainingInfo: Seq[TrainingInfoProto] = _root_.scala.Seq.empty, unknownFields: UnknownFieldSet = _root_.scalapb.UnknownFieldSet.empty) extends GeneratedMessage with Updatable[ModelProto] with Product with Serializable

Models

ModelProto is a top-level file/container format for bundling a ML model and associating its computation graph with metadata.

The semantics of the model are described by the associated GraphProto's.

irVersion

The version of the IR this model targets. See Version enum above. This field MUST be present.

opsetImport

The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.

producerName

The name of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.

producerVersion

The version of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.

domain

Domain name of the model. We use reverse domain names as name space indicators. For example: com.facebook.fair or com.microsoft.cognitiveservices Together with model_version and GraphProto.name, this forms the unique identity of the graph.

modelVersion

The version of the graph encoded. See Version enum below.

docString

A human-readable documentation for this model. Markdown is allowed.

graph

The parameterized graph that is evaluated to execute the model.

metadataProps

Named metadata values; keys should be distinct.

trainingInfo

Training-specific information. Sequentially executing all stored TrainingInfoProto.algorithms and assigning their outputs following the corresponding TrainingInfoProto.update_bindings is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all stored TrainingInfoProto.initializations and assigns their outputs using TrainingInfoProto.initialization_bindings. If this field is empty, the training behavior of the model is undefined.

Annotations
@SerialVersionUID()
Linear Supertypes
Updatable[ModelProto], GeneratedMessage, Serializable, Product, Equals, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. ModelProto
  2. Updatable
  3. GeneratedMessage
  4. Serializable
  5. Product
  6. Equals
  7. AnyRef
  8. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Instance Constructors

  1. new ModelProto(irVersion: Option[Long] = _root_.scala.None, opsetImport: Seq[OperatorSetIdProto] = _root_.scala.Seq.empty, producerName: Option[String] = _root_.scala.None, producerVersion: Option[String] = _root_.scala.None, domain: Option[String] = _root_.scala.None, modelVersion: Option[Long] = _root_.scala.None, docString: Option[String] = _root_.scala.None, graph: Option[GraphProto] = _root_.scala.None, metadataProps: Seq[StringStringEntryProto] = _root_.scala.Seq.empty, trainingInfo: Seq[TrainingInfoProto] = _root_.scala.Seq.empty, unknownFields: UnknownFieldSet = _root_.scalapb.UnknownFieldSet.empty)

    irVersion

    The version of the IR this model targets. See Version enum above. This field MUST be present.

    opsetImport

    The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.

    producerName

    The name of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.

    producerVersion

    The version of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.

    domain

    Domain name of the model. We use reverse domain names as name space indicators. For example: com.facebook.fair or com.microsoft.cognitiveservices Together with model_version and GraphProto.name, this forms the unique identity of the graph.

    modelVersion

    The version of the graph encoded. See Version enum below.

    docString

    A human-readable documentation for this model. Markdown is allowed.

    graph

    The parameterized graph that is evaluated to execute the model.

    metadataProps

    Named metadata values; keys should be distinct.

    trainingInfo

    Training-specific information. Sequentially executing all stored TrainingInfoProto.algorithms and assigning their outputs following the corresponding TrainingInfoProto.update_bindings is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all stored TrainingInfoProto.initializations and assigns their outputs using TrainingInfoProto.initialization_bindings. If this field is empty, the training behavior of the model is undefined.

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##: Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. def addAllMetadataProps(__vs: Iterable[StringStringEntryProto]): ModelProto
  5. def addAllOpsetImport(__vs: Iterable[OperatorSetIdProto]): ModelProto
  6. def addAllTrainingInfo(__vs: Iterable[TrainingInfoProto]): ModelProto
  7. def addMetadataProps(__vs: StringStringEntryProto*): ModelProto
  8. def addOpsetImport(__vs: OperatorSetIdProto*): ModelProto
  9. def addTrainingInfo(__vs: TrainingInfoProto*): ModelProto
  10. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  11. def clearDocString: ModelProto
  12. def clearDomain: ModelProto
  13. def clearGraph: ModelProto
  14. def clearIrVersion: ModelProto
  15. def clearMetadataProps: ModelProto
  16. def clearModelVersion: ModelProto
  17. def clearOpsetImport: ModelProto
  18. def clearProducerName: ModelProto
  19. def clearProducerVersion: ModelProto
  20. def clearTrainingInfo: ModelProto
  21. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @native()
  22. def companion: ModelProto.type
    Definition Classes
    ModelProto → GeneratedMessage
  23. def discardUnknownFields: ModelProto
  24. val docString: Option[String]
  25. val domain: Option[String]
  26. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  27. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.Throwable])
  28. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  29. def getDocString: String
  30. def getDomain: String
  31. def getField(__field: FieldDescriptor): PValue
    Definition Classes
    ModelProto → GeneratedMessage
  32. def getFieldByNumber(__fieldNumber: Int): Any
    Definition Classes
    ModelProto → GeneratedMessage
  33. def getGraph: GraphProto
  34. def getIrVersion: Long
  35. def getModelVersion: Long
  36. def getProducerName: String
  37. def getProducerVersion: String
  38. val graph: Option[GraphProto]
  39. val irVersion: Option[Long]
  40. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  41. val metadataProps: Seq[StringStringEntryProto]
  42. val modelVersion: Option[Long]
  43. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  44. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  45. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  46. val opsetImport: Seq[OperatorSetIdProto]
  47. val producerName: Option[String]
  48. val producerVersion: Option[String]
  49. def productElementNames: Iterator[String]
    Definition Classes
    Product
  50. def serializedSize: Int
    Definition Classes
    ModelProto → GeneratedMessage
  51. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  52. final def toByteArray: Array[Byte]
    Definition Classes
    GeneratedMessage
  53. final def toByteString: ByteString
    Definition Classes
    GeneratedMessage
  54. final def toPMessage: PMessage
    Definition Classes
    GeneratedMessage
  55. def toProtoString: String
    Definition Classes
    ModelProto → GeneratedMessage
  56. val trainingInfo: Seq[TrainingInfoProto]
  57. val unknownFields: UnknownFieldSet
  58. def update(ms: (Lens[ModelProto, ModelProto]) => Mutation[ModelProto]*): ModelProto
    Definition Classes
    Updatable
  59. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  60. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  61. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()
  62. def withDocString(__v: String): ModelProto
  63. def withDomain(__v: String): ModelProto
  64. def withGraph(__v: GraphProto): ModelProto
  65. def withIrVersion(__v: Long): ModelProto
  66. def withMetadataProps(__v: Seq[StringStringEntryProto]): ModelProto
  67. def withModelVersion(__v: Long): ModelProto
  68. def withOpsetImport(__v: Seq[OperatorSetIdProto]): ModelProto
  69. def withProducerName(__v: String): ModelProto
  70. def withProducerVersion(__v: String): ModelProto
  71. def withTrainingInfo(__v: Seq[TrainingInfoProto]): ModelProto
  72. def withUnknownFields(__v: UnknownFieldSet): ModelProto
  73. final def writeDelimitedTo(output: OutputStream): Unit
    Definition Classes
    GeneratedMessage
  74. def writeTo(_output__: CodedOutputStream): Unit
    Definition Classes
    ModelProto → GeneratedMessage
  75. final def writeTo(output: OutputStream): Unit
    Definition Classes
    GeneratedMessage

Inherited from Updatable[ModelProto]

Inherited from GeneratedMessage

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from AnyRef

Inherited from Any

Ungrouped