Package onnx

Interface Onnx.ModelProtoOrBuilder

  • All Superinterfaces:
    org.nd4j.shade.protobuf.MessageLiteOrBuilder, org.nd4j.shade.protobuf.MessageOrBuilder
    All Known Implementing Classes:
    Onnx.ModelProto, Onnx.ModelProto.Builder
    Enclosing class:
    Onnx
    public static interface Onnx.ModelProtoOrBuilder
extends org.nd4j.shade.protobuf.MessageOrBuilder

    • Method Detail

      • getIrVersion

        long getIrVersion()
         The version of the IR this model targets. See Version enum above.
 This field MUST be present.
        int64 ir_version = 1;
        Returns:
        The irVersion.

      • getOpsetImportList

        List<Onnx.OperatorSetIdProto> getOpsetImportList()
         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.
        repeated .onnx.OperatorSetIdProto opset_import = 8;

      • getOpsetImport

        Onnx.OperatorSetIdProto getOpsetImport​(int index)
         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.
        repeated .onnx.OperatorSetIdProto opset_import = 8;

      • getOpsetImportCount

        int getOpsetImportCount()
         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.
        repeated .onnx.OperatorSetIdProto opset_import = 8;

      • getOpsetImportOrBuilderList

        List<? extends Onnx.OperatorSetIdProtoOrBuilder> getOpsetImportOrBuilderList()
         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.
        repeated .onnx.OperatorSetIdProto opset_import = 8;

      • getOpsetImportOrBuilder

        Onnx.OperatorSetIdProtoOrBuilder getOpsetImportOrBuilder​(int index)
         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.
        repeated .onnx.OperatorSetIdProto opset_import = 8;

      • getProducerName

        String getProducerName()
         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.
        string producer_name = 2;
        Returns:
        The producerName.

      • getProducerNameBytes

        org.nd4j.shade.protobuf.ByteString getProducerNameBytes()
         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.
        string producer_name = 2;
        Returns:
        The bytes for producerName.

      • getProducerVersion

        String getProducerVersion()
         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.
        string producer_version = 3;
        Returns:
        The producerVersion.

      • getProducerVersionBytes

        org.nd4j.shade.protobuf.ByteString getProducerVersionBytes()
         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.
        string producer_version = 3;
        Returns:
        The bytes for producerVersion.

      • getDomain

        String getDomain()
         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.
        string domain = 4;
        Returns:
        The domain.

      • getDomainBytes

        org.nd4j.shade.protobuf.ByteString getDomainBytes()
         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.
        string domain = 4;
        Returns:
        The bytes for domain.

      • getModelVersion

        long getModelVersion()
         The version of the graph encoded. See Version enum below.
        int64 model_version = 5;
        Returns:
        The modelVersion.

      • getDocString

        String getDocString()
         A human-readable documentation for this model. Markdown is allowed.
        string doc_string = 6;
        Returns:
        The docString.

      • getDocStringBytes

        org.nd4j.shade.protobuf.ByteString getDocStringBytes()
         A human-readable documentation for this model. Markdown is allowed.
        string doc_string = 6;
        Returns:
        The bytes for docString.

      • hasGraph

        boolean hasGraph()
         The parameterized graph that is evaluated to execute the model.
        .onnx.GraphProto graph = 7;
        Returns:
        Whether the graph field is set.

      • getGraph

        Onnx.GraphProto getGraph()
         The parameterized graph that is evaluated to execute the model.
        .onnx.GraphProto graph = 7;
        Returns:
        The graph.

      • getGraphOrBuilder

        Onnx.GraphProtoOrBuilder getGraphOrBuilder()
         The parameterized graph that is evaluated to execute the model.
        .onnx.GraphProto graph = 7;

      • getMetadataPropsList

        List<Onnx.StringStringEntryProto> getMetadataPropsList()
         Named metadata values; keys should be distinct.
        repeated .onnx.StringStringEntryProto metadata_props = 14;

      • getMetadataProps

        Onnx.StringStringEntryProto getMetadataProps​(int index)
         Named metadata values; keys should be distinct.
        repeated .onnx.StringStringEntryProto metadata_props = 14;

      • getMetadataPropsCount

        int getMetadataPropsCount()
         Named metadata values; keys should be distinct.
        repeated .onnx.StringStringEntryProto metadata_props = 14;

      • getMetadataPropsOrBuilderList

        List<? extends Onnx.StringStringEntryProtoOrBuilder> getMetadataPropsOrBuilderList()
         Named metadata values; keys should be distinct.
        repeated .onnx.StringStringEntryProto metadata_props = 14;

      • getMetadataPropsOrBuilder

        Onnx.StringStringEntryProtoOrBuilder getMetadataPropsOrBuilder​(int index)
         Named metadata values; keys should be distinct.
        repeated .onnx.StringStringEntryProto metadata_props = 14;

      • getTrainingInfoList

        List<Onnx.TrainingInfoProto> getTrainingInfoList()
         Training-specific information. Sequentially executing all stored
 `TrainingInfoProto.algorithm`s and assigning their outputs following
 the corresponding `TrainingInfoProto.update_binding`s is one training
 iteration. Similarly, to initialize the model
 (as if training hasn't happened), the user should sequentially execute
 all stored `TrainingInfoProto.initialization`s and assigns their outputs
 using `TrainingInfoProto.initialization_binding`s.
 If this field is empty, the training behavior of the model is undefined.
        repeated .onnx.TrainingInfoProto training_info = 20;

      • getTrainingInfo

        Onnx.TrainingInfoProto getTrainingInfo​(int index)
         Training-specific information. Sequentially executing all stored
 `TrainingInfoProto.algorithm`s and assigning their outputs following
 the corresponding `TrainingInfoProto.update_binding`s is one training
 iteration. Similarly, to initialize the model
 (as if training hasn't happened), the user should sequentially execute
 all stored `TrainingInfoProto.initialization`s and assigns their outputs
 using `TrainingInfoProto.initialization_binding`s.
 If this field is empty, the training behavior of the model is undefined.
        repeated .onnx.TrainingInfoProto training_info = 20;

      • getTrainingInfoCount

        int getTrainingInfoCount()
         Training-specific information. Sequentially executing all stored
 `TrainingInfoProto.algorithm`s and assigning their outputs following
 the corresponding `TrainingInfoProto.update_binding`s is one training
 iteration. Similarly, to initialize the model
 (as if training hasn't happened), the user should sequentially execute
 all stored `TrainingInfoProto.initialization`s and assigns their outputs
 using `TrainingInfoProto.initialization_binding`s.
 If this field is empty, the training behavior of the model is undefined.
        repeated .onnx.TrainingInfoProto training_info = 20;

      • getTrainingInfoOrBuilderList

        List<? extends Onnx.TrainingInfoProtoOrBuilder> getTrainingInfoOrBuilderList()
         Training-specific information. Sequentially executing all stored
 `TrainingInfoProto.algorithm`s and assigning their outputs following
 the corresponding `TrainingInfoProto.update_binding`s is one training
 iteration. Similarly, to initialize the model
 (as if training hasn't happened), the user should sequentially execute
 all stored `TrainingInfoProto.initialization`s and assigns their outputs
 using `TrainingInfoProto.initialization_binding`s.
 If this field is empty, the training behavior of the model is undefined.
        repeated .onnx.TrainingInfoProto training_info = 20;

      • getTrainingInfoOrBuilder

        Onnx.TrainingInfoProtoOrBuilder getTrainingInfoOrBuilder​(int index)
         Training-specific information. Sequentially executing all stored
 `TrainingInfoProto.algorithm`s and assigning their outputs following
 the corresponding `TrainingInfoProto.update_binding`s is one training
 iteration. Similarly, to initialize the model
 (as if training hasn't happened), the user should sequentially execute
 all stored `TrainingInfoProto.initialization`s and assigns their outputs
 using `TrainingInfoProto.initialization_binding`s.
 If this field is empty, the training behavior of the model is undefined.
        repeated .onnx.TrainingInfoProto training_info = 20;

      • getFunctionsList

        List<Onnx.FunctionProto> getFunctionsList()
         A list of function protos local to the model.
 Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain".
 In case of any conflicts the behavior (whether the model local functions are given higher priority,
 or standard opserator sets are given higher priotity or this is treated as error) is defined by
 the runtimes.
 The operator sets imported by FunctionProto should be compatible with the ones
 imported by ModelProto and other model local FunctionProtos.
 Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto
 or by 2 FunctionProtos then versions for the operator set may be different but,
 the operator schema returned for op_type, domain, version combination
 for both the versions should be same for every node in the function body.
 One FunctionProto can reference other FunctionProto in the model, however, recursive reference
 is not allowed.
        repeated .onnx.FunctionProto functions = 25;

      • getFunctions

        Onnx.FunctionProto getFunctions​(int index)
         A list of function protos local to the model.
 Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain".
 In case of any conflicts the behavior (whether the model local functions are given higher priority,
 or standard opserator sets are given higher priotity or this is treated as error) is defined by
 the runtimes.
 The operator sets imported by FunctionProto should be compatible with the ones
 imported by ModelProto and other model local FunctionProtos.
 Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto
 or by 2 FunctionProtos then versions for the operator set may be different but,
 the operator schema returned for op_type, domain, version combination
 for both the versions should be same for every node in the function body.
 One FunctionProto can reference other FunctionProto in the model, however, recursive reference
 is not allowed.
        repeated .onnx.FunctionProto functions = 25;

      • getFunctionsCount

        int getFunctionsCount()
         A list of function protos local to the model.
 Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain".
 In case of any conflicts the behavior (whether the model local functions are given higher priority,
 or standard opserator sets are given higher priotity or this is treated as error) is defined by
 the runtimes.
 The operator sets imported by FunctionProto should be compatible with the ones
 imported by ModelProto and other model local FunctionProtos.
 Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto
 or by 2 FunctionProtos then versions for the operator set may be different but,
 the operator schema returned for op_type, domain, version combination
 for both the versions should be same for every node in the function body.
 One FunctionProto can reference other FunctionProto in the model, however, recursive reference
 is not allowed.
        repeated .onnx.FunctionProto functions = 25;

      • getFunctionsOrBuilderList

        List<? extends Onnx.FunctionProtoOrBuilder> getFunctionsOrBuilderList()
         A list of function protos local to the model.
 Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain".
 In case of any conflicts the behavior (whether the model local functions are given higher priority,
 or standard opserator sets are given higher priotity or this is treated as error) is defined by
 the runtimes.
 The operator sets imported by FunctionProto should be compatible with the ones
 imported by ModelProto and other model local FunctionProtos.
 Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto
 or by 2 FunctionProtos then versions for the operator set may be different but,
 the operator schema returned for op_type, domain, version combination
 for both the versions should be same for every node in the function body.
 One FunctionProto can reference other FunctionProto in the model, however, recursive reference
 is not allowed.
        repeated .onnx.FunctionProto functions = 25;

      • getFunctionsOrBuilder

        Onnx.FunctionProtoOrBuilder getFunctionsOrBuilder​(int index)
         A list of function protos local to the model.
 Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain".
 In case of any conflicts the behavior (whether the model local functions are given higher priority,
 or standard opserator sets are given higher priotity or this is treated as error) is defined by
 the runtimes.
 The operator sets imported by FunctionProto should be compatible with the ones
 imported by ModelProto and other model local FunctionProtos.
 Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto
 or by 2 FunctionProtos then versions for the operator set may be different but,
 the operator schema returned for op_type, domain, version combination
 for both the versions should be same for every node in the function body.
 One FunctionProto can reference other FunctionProto in the model, however, recursive reference
 is not allowed.
        repeated .onnx.FunctionProto functions = 25;