Class/Object

io.hydrosphere.serving.onnx.onnx

ModelProto

Related Docs: object ModelProto | package onnx

Permalink

final case class ModelProto(irVersion: Long = 0L, opsetImport: Seq[OperatorSetIdProto] = _root_.scala.collection.Seq.empty, producerName: String = "", producerVersion: String = "", domain: String = "", modelVersion: Long = 0L, docString: String = "", graph: Option[GraphProto] = None, metadataProps: Seq[StringStringEntryProto] = _root_.scala.collection.Seq.empty) extends GeneratedMessage with Message[ModelProto] 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.

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.

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

Instance Constructors

  1. new ModelProto(irVersion: Long = 0L, opsetImport: Seq[OperatorSetIdProto] = _root_.scala.collection.Seq.empty, producerName: String = "", producerVersion: String = "", domain: String = "", modelVersion: Long = 0L, docString: String = "", graph: Option[GraphProto] = None, metadataProps: Seq[StringStringEntryProto] = _root_.scala.collection.Seq.empty)

    Permalink

    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.

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  4. def addAllMetadataProps(__vs: TraversableOnce[StringStringEntryProto]): ModelProto

    Permalink

  5. def addAllOpsetImport(__vs: TraversableOnce[OperatorSetIdProto]): ModelProto

    Permalink

  6. def addMetadataProps(__vs: StringStringEntryProto*): ModelProto

    Permalink

  7. def addOpsetImport(__vs: OperatorSetIdProto*): ModelProto

    Permalink

  8. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  9. def clearGraph: ModelProto

    Permalink

  10. def clearMetadataProps: ModelProto

    Permalink

  11. def clearOpsetImport: ModelProto

    Permalink

  12. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  13. def companion: ModelProto.type

    Permalink
    Definition Classes
    ModelProto → GeneratedMessage

  14. val docString: String

    Permalink

    A human-readable documentation for this model.

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

  15. val domain: String

    Permalink

    Domain name of the model.

    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.

  16. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  17. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  18. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any

  19. def getField(__field: FieldDescriptor): PValue

    Permalink
    Definition Classes
    ModelProto → GeneratedMessage

  20. def getFieldByNumber(__fieldNumber: Int): Any

    Permalink
    Definition Classes
    ModelProto → GeneratedMessage

  21. def getGraph: GraphProto

    Permalink

  22. val graph: Option[GraphProto]

    Permalink

    The parameterized graph that is evaluated to execute the model.

  23. val irVersion: Long

    Permalink

    The version of the IR this model targets.

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

  24. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  25. def mergeFrom(_input__: CodedInputStream): ModelProto

    Permalink
    Definition Classes
    ModelProto → Message

  26. val metadataProps: Seq[StringStringEntryProto]

    Permalink

    Named metadata values; keys should be distinct.

  27. val modelVersion: Long

    Permalink

    The version of the graph encoded.

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

  28. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  29. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  30. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  31. val opsetImport: Seq[OperatorSetIdProto]

    Permalink

    The OperatorSets this model relies on.

    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.

  32. val producerName: String

    Permalink

    The name of the framework or tool used to generate this model.

    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.

  33. val producerVersion: String

    Permalink

    The version of the framework or tool used to generate this model.

    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.

  34. final def serializedSize: Int

    Permalink
    Definition Classes
    ModelProto → GeneratedMessage

  35. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef

  36. def toByteArray: Array[Byte]

    Permalink
    Definition Classes
    GeneratedMessage

  37. def toByteString: ByteString

    Permalink
    Definition Classes
    GeneratedMessage

  38. def toPMessage: PMessage

    Permalink
    Definition Classes
    GeneratedMessage

  39. def toProtoString: String

    Permalink
    Definition Classes
    ModelProto → GeneratedMessage

  40. def update(ms: (Lens[ModelProto, ModelProto]) ⇒ Mutation[ModelProto]*): ModelProto

    Permalink
    Definition Classes
    Updatable

  41. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  42. final def wait(arg0: Long, arg1: Int): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  43. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  44. def withDocString(__v: String): ModelProto

    Permalink

  45. def withDomain(__v: String): ModelProto

    Permalink

  46. def withGraph(__v: GraphProto): ModelProto

    Permalink

  47. def withIrVersion(__v: Long): ModelProto

    Permalink

  48. def withMetadataProps(__v: Seq[StringStringEntryProto]): ModelProto

    Permalink

  49. def withModelVersion(__v: Long): ModelProto

    Permalink

  50. def withOpsetImport(__v: Seq[OperatorSetIdProto]): ModelProto

    Permalink

  51. def withProducerName(__v: String): ModelProto

    Permalink

  52. def withProducerVersion(__v: String): ModelProto

    Permalink

  53. def writeDelimitedTo(output: OutputStream): Unit

    Permalink
    Definition Classes
    GeneratedMessage

  54. def writeTo(_output__: CodedOutputStream): Unit

    Permalink
    Definition Classes
    ModelProto → GeneratedMessage

  55. def writeTo(output: OutputStream): Unit

    Permalink
    Definition Classes
    GeneratedMessage

Deprecated Value Members

  1. def getAllFields: Map[FieldDescriptor, Any]

    Permalink
    Definition Classes
    GeneratedMessage
    Annotations
    @deprecated
    Deprecated

    (Since version 0.6.0) Use toPMessage

  2. def getField(field: FieldDescriptor): Any

    Permalink
    Definition Classes
    GeneratedMessage
    Annotations
    @deprecated
    Deprecated

    (Since version 0.6.0) Use getField that accepts a ScalaPB descriptor and returns PValue

Inherited from Product

Inherited from Equals

Inherited from Updatable[ModelProto]

Inherited from Message[ModelProto]

Inherited from GeneratedMessage

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped