Package onnx

Interface Onnx.TensorAnnotationOrBuilder

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

    • Method Detail

      • getTensorName

        String getTensorName()
        string tensor_name = 1;
        Returns:
        The tensorName.

      • getTensorNameBytes

        org.nd4j.shade.protobuf.ByteString getTensorNameBytes()
        string tensor_name = 1;
        Returns:
        The bytes for tensorName.

      • getQuantParameterTensorNamesList

        List<Onnx.StringStringEntryProto> getQuantParameterTensorNamesList()
         <key, value> pairs to annotate tensor specified by <tensor_name> above.
 The keys used in the mapping below must be pre-defined in ONNX spec.
 For example, for 8-bit linear quantization case, 'SCALE_TENSOR', 'ZERO_POINT_TENSOR' will be pre-defined as
 quantization parameter keys.
        repeated .onnx.StringStringEntryProto quant_parameter_tensor_names = 2;

      • getQuantParameterTensorNames

        Onnx.StringStringEntryProto getQuantParameterTensorNames​(int index)
         <key, value> pairs to annotate tensor specified by <tensor_name> above.
 The keys used in the mapping below must be pre-defined in ONNX spec.
 For example, for 8-bit linear quantization case, 'SCALE_TENSOR', 'ZERO_POINT_TENSOR' will be pre-defined as
 quantization parameter keys.
        repeated .onnx.StringStringEntryProto quant_parameter_tensor_names = 2;

      • getQuantParameterTensorNamesCount

        int getQuantParameterTensorNamesCount()
         <key, value> pairs to annotate tensor specified by <tensor_name> above.
 The keys used in the mapping below must be pre-defined in ONNX spec.
 For example, for 8-bit linear quantization case, 'SCALE_TENSOR', 'ZERO_POINT_TENSOR' will be pre-defined as
 quantization parameter keys.
        repeated .onnx.StringStringEntryProto quant_parameter_tensor_names = 2;

      • getQuantParameterTensorNamesOrBuilderList

        List<? extends Onnx.StringStringEntryProtoOrBuilder> getQuantParameterTensorNamesOrBuilderList()
         <key, value> pairs to annotate tensor specified by <tensor_name> above.
 The keys used in the mapping below must be pre-defined in ONNX spec.
 For example, for 8-bit linear quantization case, 'SCALE_TENSOR', 'ZERO_POINT_TENSOR' will be pre-defined as
 quantization parameter keys.
        repeated .onnx.StringStringEntryProto quant_parameter_tensor_names = 2;

      • getQuantParameterTensorNamesOrBuilder

        Onnx.StringStringEntryProtoOrBuilder getQuantParameterTensorNamesOrBuilder​(int index)
         <key, value> pairs to annotate tensor specified by <tensor_name> above.
 The keys used in the mapping below must be pre-defined in ONNX spec.
 For example, for 8-bit linear quantization case, 'SCALE_TENSOR', 'ZERO_POINT_TENSOR' will be pre-defined as
 quantization parameter keys.
        repeated .onnx.StringStringEntryProto quant_parameter_tensor_names = 2;