Package onnx

Interface Onnx.TensorProtoOrBuilder

  • All Superinterfaces:
    com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
    All Known Implementing Classes:
    Onnx.TensorProto, Onnx.TensorProto.Builder
    Enclosing class:
    Onnx
    public static interface Onnx.TensorProtoOrBuilder
extends com.google.protobuf.MessageOrBuilder

    • Method Summary

      All Methods Instance Methods Abstract Methods 
      Modifier and Type Method Description
      Onnx.TensorProto.DataType getDataType()
      The data type of the tensor.
      long getDims​(int index)
      The shape of the tensor.
      int getDimsCount()
      The shape of the tensor.
      List<Long> getDimsList()
      The shape of the tensor.
      String getDocString()
      A human-readable documentation for this tensor.
      com.google.protobuf.ByteString getDocStringBytes()
      A human-readable documentation for this tensor.
      double getDoubleData​(int index)
      For double Complex64 tensors are encoded as a single array of doubles, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position.
      int getDoubleDataCount()
      For double Complex64 tensors are encoded as a single array of doubles, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position.
      List<Double> getDoubleDataList()
      For double Complex64 tensors are encoded as a single array of doubles, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position.
      float getFloatData​(int index)
      For float and complex64 values Complex64 tensors are encoded as a single array of floats, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position.
      int getFloatDataCount()
      For float and complex64 values Complex64 tensors are encoded as a single array of floats, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position.
      List<Float> getFloatDataList()
      For float and complex64 values Complex64 tensors are encoded as a single array of floats, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position.
      int getInt32Data​(int index)
      For int32, uint8, int8, uint16, int16, bool, and float16 values float16 values must be bit-wise converted to an uint16_t prior to writing to the buffer.
      int getInt32DataCount()
      For int32, uint8, int8, uint16, int16, bool, and float16 values float16 values must be bit-wise converted to an uint16_t prior to writing to the buffer.
      List<Integer> getInt32DataList()
      For int32, uint8, int8, uint16, int16, bool, and float16 values float16 values must be bit-wise converted to an uint16_t prior to writing to the buffer.
      long getInt64Data​(int index)
      For int64.
      int getInt64DataCount()
      For int64.
      List<Long> getInt64DataList()
      For int64.
      String getName()
      Optionally, a name for the tensor.
      com.google.protobuf.ByteString getNameBytes()
      Optionally, a name for the tensor.
      com.google.protobuf.ByteString getRawData()
      Serializations can either use one of the fields above, or use this raw bytes field.
      Onnx.TensorProto.Segment getSegment()
      optional .onnx.TensorProto.Segment segment = 3;
      Onnx.TensorProto.SegmentOrBuilder getSegmentOrBuilder()
      optional .onnx.TensorProto.Segment segment = 3;
      com.google.protobuf.ByteString getStringData​(int index)
      For strings.
      int getStringDataCount()
      For strings.
      List<com.google.protobuf.ByteString> getStringDataList()
      For strings.
      long getUint64Data​(int index)
      For uint64 and uint32 values When this field is present, the data_type field MUST be UINT32 or UINT64
      int getUint64DataCount()
      For uint64 and uint32 values When this field is present, the data_type field MUST be UINT32 or UINT64
      List<Long> getUint64DataList()
      For uint64 and uint32 values When this field is present, the data_type field MUST be UINT32 or UINT64
      boolean hasDataType()
      The data type of the tensor.
      boolean hasDocString()
      A human-readable documentation for this tensor.
      boolean hasName()
      Optionally, a name for the tensor.
      boolean hasRawData()
      Serializations can either use one of the fields above, or use this raw bytes field.
      boolean hasSegment()
      optional .onnx.TensorProto.Segment segment = 3;

      • Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

        isInitialized

      • Methods inherited from interface com.google.protobuf.MessageOrBuilder

        findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof

    • Method Detail

      • getDimsList

        List<Long> getDimsList()
         The shape of the tensor.
        repeated int64 dims = 1;
        Returns:
        A list containing the dims.

      • getDimsCount

        int getDimsCount()
         The shape of the tensor.
        repeated int64 dims = 1;
        Returns:
        The count of dims.

      • getDims

        long getDims​(int index)
         The shape of the tensor.
        repeated int64 dims = 1;
        Parameters:
        index - The index of the element to return.
        Returns:
        The dims at the given index.

      • hasDataType

        boolean hasDataType()
         The data type of the tensor.
        optional .onnx.TensorProto.DataType data_type = 2;
        Returns:
        Whether the dataType field is set.

      • getDataType

        Onnx.TensorProto.DataType getDataType()
         The data type of the tensor.
        optional .onnx.TensorProto.DataType data_type = 2;
        Returns:
        The dataType.

      • hasSegment

        boolean hasSegment()
        optional .onnx.TensorProto.Segment segment = 3;
        Returns:
        Whether the segment field is set.

      • getSegment

        Onnx.TensorProto.Segment getSegment()
        optional .onnx.TensorProto.Segment segment = 3;
        Returns:
        The segment.

      • getFloatDataList

        List<Float> getFloatDataList()
         For float and complex64 values
 Complex64 tensors are encoded as a single array of floats,
 with the real components appearing in odd numbered positions,
 and the corresponding imaginary component apparing in the
 subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i]
 is encoded as [1.0, 2.0 ,3.0 ,4.0]
 When this field is present, the data_type field MUST be FLOAT or COMPLEX64.
        repeated float float_data = 4 [packed = true];
        Returns:
        A list containing the floatData.

      • getFloatDataCount

        int getFloatDataCount()
         For float and complex64 values
 Complex64 tensors are encoded as a single array of floats,
 with the real components appearing in odd numbered positions,
 and the corresponding imaginary component apparing in the
 subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i]
 is encoded as [1.0, 2.0 ,3.0 ,4.0]
 When this field is present, the data_type field MUST be FLOAT or COMPLEX64.
        repeated float float_data = 4 [packed = true];
        Returns:
        The count of floatData.

      • getFloatData

        float getFloatData​(int index)
         For float and complex64 values
 Complex64 tensors are encoded as a single array of floats,
 with the real components appearing in odd numbered positions,
 and the corresponding imaginary component apparing in the
 subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i]
 is encoded as [1.0, 2.0 ,3.0 ,4.0]
 When this field is present, the data_type field MUST be FLOAT or COMPLEX64.
        repeated float float_data = 4 [packed = true];
        Parameters:
        index - The index of the element to return.
        Returns:
        The floatData at the given index.

      • getInt32DataList

        List<Integer> getInt32DataList()
         For int32, uint8, int8, uint16, int16, bool, and float16 values
 float16 values must be bit-wise converted to an uint16_t prior
 to writing to the buffer.
 When this field is present, the data_type field MUST be
 INT32, INT16, INT8, UINT16, INT8, BOOL, or FLOAT32
        repeated int32 int32_data = 5 [packed = true];
        Returns:
        A list containing the int32Data.

      • getInt32DataCount

        int getInt32DataCount()
         For int32, uint8, int8, uint16, int16, bool, and float16 values
 float16 values must be bit-wise converted to an uint16_t prior
 to writing to the buffer.
 When this field is present, the data_type field MUST be
 INT32, INT16, INT8, UINT16, INT8, BOOL, or FLOAT32
        repeated int32 int32_data = 5 [packed = true];
        Returns:
        The count of int32Data.

      • getInt32Data

        int getInt32Data​(int index)
         For int32, uint8, int8, uint16, int16, bool, and float16 values
 float16 values must be bit-wise converted to an uint16_t prior
 to writing to the buffer.
 When this field is present, the data_type field MUST be
 INT32, INT16, INT8, UINT16, INT8, BOOL, or FLOAT32
        repeated int32 int32_data = 5 [packed = true];
        Parameters:
        index - The index of the element to return.
        Returns:
        The int32Data at the given index.

      • getStringDataList

        List<com.google.protobuf.ByteString> getStringDataList()
         For strings.
 Each element of string_data is a UTF-8 encoded Unicode
 string. No trailing null, no leading BOM. The protobuf "string"
 scalar type is not used to match ML community conventions.
 When this field is present, the data_type field MUST be STRING
        repeated bytes string_data = 6;
        Returns:
        A list containing the stringData.

      • getStringDataCount

        int getStringDataCount()
         For strings.
 Each element of string_data is a UTF-8 encoded Unicode
 string. No trailing null, no leading BOM. The protobuf "string"
 scalar type is not used to match ML community conventions.
 When this field is present, the data_type field MUST be STRING
        repeated bytes string_data = 6;
        Returns:
        The count of stringData.

      • getStringData

        com.google.protobuf.ByteString getStringData​(int index)
         For strings.
 Each element of string_data is a UTF-8 encoded Unicode
 string. No trailing null, no leading BOM. The protobuf "string"
 scalar type is not used to match ML community conventions.
 When this field is present, the data_type field MUST be STRING
        repeated bytes string_data = 6;
        Parameters:
        index - The index of the element to return.
        Returns:
        The stringData at the given index.

      • getInt64DataList

        List<Long> getInt64DataList()
         For int64.
 When this field is present, the data_type field MUST be INT64
        repeated int64 int64_data = 7 [packed = true];
        Returns:
        A list containing the int64Data.

      • getInt64DataCount

        int getInt64DataCount()
         For int64.
 When this field is present, the data_type field MUST be INT64
        repeated int64 int64_data = 7 [packed = true];
        Returns:
        The count of int64Data.

      • getInt64Data

        long getInt64Data​(int index)
         For int64.
 When this field is present, the data_type field MUST be INT64
        repeated int64 int64_data = 7 [packed = true];
        Parameters:
        index - The index of the element to return.
        Returns:
        The int64Data at the given index.

      • hasName

        boolean hasName()
         Optionally, a name for the tensor.
        optional string name = 8;
        Returns:
        Whether the name field is set.

      • getName

        String getName()
         Optionally, a name for the tensor.
        optional string name = 8;
        Returns:
        The name.

      • getNameBytes

        com.google.protobuf.ByteString getNameBytes()
         Optionally, a name for the tensor.
        optional string name = 8;
        Returns:
        The bytes for name.

      • hasDocString

        boolean hasDocString()
         A human-readable documentation for this tensor. Markdown is allowed.
        optional string doc_string = 12;
        Returns:
        Whether the docString field is set.

      • getDocString

        String getDocString()
         A human-readable documentation for this tensor. Markdown is allowed.
        optional string doc_string = 12;
        Returns:
        The docString.

      • getDocStringBytes

        com.google.protobuf.ByteString getDocStringBytes()
         A human-readable documentation for this tensor. Markdown is allowed.
        optional string doc_string = 12;
        Returns:
        The bytes for docString.

      • hasRawData

        boolean hasRawData()
         Serializations can either use one of the fields above, or use this
 raw bytes field. The only exception is the string case, where one is
 required to store the content in the repeated bytes string_data field.
 When this raw_data field is used to store tensor value, elements MUST
 be stored in as fixed-width, little-endian order.
 Floating-point data types MUST be stored in IEEE 754 format.
 Complex64 elements must be written as two consecutive FLOAT values, real component first.
 Complex128 elements must be written as two consecutive DOUBLE values, real component first.
 Boolean type MUST be written one byte per tensor element (00000001 for true, 00000000 for false).
 Note: the advantage of specific field rather than the raw_data field is
 that in some cases (e.g. int data), protobuf does a better packing via
 variable length storage, and may lead to smaller binary footprint.
 When this field is present, the data_type field MUST NOT be STRING or UNDEFINED
        optional bytes raw_data = 9;
        Returns:
        Whether the rawData field is set.

      • getRawData

        com.google.protobuf.ByteString getRawData()
         Serializations can either use one of the fields above, or use this
 raw bytes field. The only exception is the string case, where one is
 required to store the content in the repeated bytes string_data field.
 When this raw_data field is used to store tensor value, elements MUST
 be stored in as fixed-width, little-endian order.
 Floating-point data types MUST be stored in IEEE 754 format.
 Complex64 elements must be written as two consecutive FLOAT values, real component first.
 Complex128 elements must be written as two consecutive DOUBLE values, real component first.
 Boolean type MUST be written one byte per tensor element (00000001 for true, 00000000 for false).
 Note: the advantage of specific field rather than the raw_data field is
 that in some cases (e.g. int data), protobuf does a better packing via
 variable length storage, and may lead to smaller binary footprint.
 When this field is present, the data_type field MUST NOT be STRING or UNDEFINED
        optional bytes raw_data = 9;
        Returns:
        The rawData.

      • getDoubleDataList

        List<Double> getDoubleDataList()
         For double
 Complex64 tensors are encoded as a single array of doubles,
 with the real components appearing in odd numbered positions,
 and the corresponding imaginary component apparing in the
 subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i]
 is encoded as [1.0, 2.0 ,3.0 ,4.0]
 When this field is present, the data_type field MUST be DOUBLE or COMPLEX128
        repeated double double_data = 10 [packed = true];
        Returns:
        A list containing the doubleData.

      • getDoubleDataCount

        int getDoubleDataCount()
         For double
 Complex64 tensors are encoded as a single array of doubles,
 with the real components appearing in odd numbered positions,
 and the corresponding imaginary component apparing in the
 subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i]
 is encoded as [1.0, 2.0 ,3.0 ,4.0]
 When this field is present, the data_type field MUST be DOUBLE or COMPLEX128
        repeated double double_data = 10 [packed = true];
        Returns:
        The count of doubleData.

      • getDoubleData

        double getDoubleData​(int index)
         For double
 Complex64 tensors are encoded as a single array of doubles,
 with the real components appearing in odd numbered positions,
 and the corresponding imaginary component apparing in the
 subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i]
 is encoded as [1.0, 2.0 ,3.0 ,4.0]
 When this field is present, the data_type field MUST be DOUBLE or COMPLEX128
        repeated double double_data = 10 [packed = true];
        Parameters:
        index - The index of the element to return.
        Returns:
        The doubleData at the given index.

      • getUint64DataList

        List<Long> getUint64DataList()
         For uint64 and uint32 values
 When this field is present, the data_type field MUST be
 UINT32 or UINT64
        repeated uint64 uint64_data = 11 [packed = true];
        Returns:
        A list containing the uint64Data.

      • getUint64DataCount

        int getUint64DataCount()
         For uint64 and uint32 values
 When this field is present, the data_type field MUST be
 UINT32 or UINT64
        repeated uint64 uint64_data = 11 [packed = true];
        Returns:
        The count of uint64Data.

      • getUint64Data

        long getUint64Data​(int index)
         For uint64 and uint32 values
 When this field is present, the data_type field MUST be
 UINT32 or UINT64
        repeated uint64 uint64_data = 11 [packed = true];
        Parameters:
        index - The index of the element to return.
        Returns:
        The uint64Data at the given index.