ai.onnx.proto

Interface OnnxMl.SparseTensorProtoOrBuilder

All Superinterfaces:

com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder

All Known Implementing Classes:

OnnxMl.SparseTensorProto, OnnxMl.SparseTensorProto.Builder

Enclosing class:

OnnxMl

public static interface OnnxMl.SparseTensorProtoOrBuilder
extends com.google.protobuf.MessageOrBuilder

Method Summary

Modifier and Type	Method and Description
long	getDims(int index) The shape of the underlying dense-tensor: [dim_1, dim_2, ...
int	getDimsCount() The shape of the underlying dense-tensor: [dim_1, dim_2, ...
java.util.List<java.lang.Long>	getDimsList() The shape of the underlying dense-tensor: [dim_1, dim_2, ...
OnnxMl.TensorProto	getIndices() The indices of the non-default values, which may be stored in one of two formats.
OnnxMl.TensorProtoOrBuilder	getIndicesOrBuilder() The indices of the non-default values, which may be stored in one of two formats.
OnnxMl.TensorProto	getValues() The sequence of non-default values are encoded as a tensor of shape [NNZ].
OnnxMl.TensorProtoOrBuilder	getValuesOrBuilder() The sequence of non-default values are encoded as a tensor of shape [NNZ].
boolean	hasIndices() The indices of the non-default values, which may be stored in one of two formats.
boolean	hasValues() The sequence of non-default values are encoded as a tensor of shape [NNZ].

Methods inherited from interface com.google.protobuf.MessageOrBuilder

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

Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

isInitialized

Method Detail

hasValues

boolean hasValues()

 The sequence of non-default values are encoded as a tensor of shape [NNZ].
 The default-value is zero for numeric tensors, and empty-string for string tensors.
 values must have a non-empty name present which serves as a name for SparseTensorProto
 when used in sparse_initializer list.
 

optional .onnx.TensorProto values = 1;

Returns:

Whether the values field is set.

getValues

OnnxMl.TensorProto getValues()

 The sequence of non-default values are encoded as a tensor of shape [NNZ].
 The default-value is zero for numeric tensors, and empty-string for string tensors.
 values must have a non-empty name present which serves as a name for SparseTensorProto
 when used in sparse_initializer list.
 

optional .onnx.TensorProto values = 1;

Returns:

The values.

getValuesOrBuilder

OnnxMl.TensorProtoOrBuilder getValuesOrBuilder()

 The sequence of non-default values are encoded as a tensor of shape [NNZ].
 The default-value is zero for numeric tensors, and empty-string for string tensors.
 values must have a non-empty name present which serves as a name for SparseTensorProto
 when used in sparse_initializer list.
 

optional .onnx.TensorProto values = 1;

hasIndices

boolean hasIndices()

 The indices of the non-default values, which may be stored in one of two formats.
 (a) Indices can be a tensor of shape [NNZ, rank] with the [i,j]-th value
 corresponding to the j-th index of the i-th value (in the values tensor).
 (b) Indices can be a tensor of shape [NNZ], in which case the i-th value
 must be the linearized-index of the i-th value (in the values tensor).
 The linearized-index can be converted into an index tuple (k_1,...,k_rank)
 using the shape provided below.
 The indices must appear in ascending order without duplication.
 In the first format, the ordering is lexicographic-ordering:
 e.g., index-value [1,4] must appear before [2,1]
 

optional .onnx.TensorProto indices = 2;

Returns:

Whether the indices field is set.

getIndices

OnnxMl.TensorProto getIndices()

 The indices of the non-default values, which may be stored in one of two formats.
 (a) Indices can be a tensor of shape [NNZ, rank] with the [i,j]-th value
 corresponding to the j-th index of the i-th value (in the values tensor).
 (b) Indices can be a tensor of shape [NNZ], in which case the i-th value
 must be the linearized-index of the i-th value (in the values tensor).
 The linearized-index can be converted into an index tuple (k_1,...,k_rank)
 using the shape provided below.
 The indices must appear in ascending order without duplication.
 In the first format, the ordering is lexicographic-ordering:
 e.g., index-value [1,4] must appear before [2,1]
 

optional .onnx.TensorProto indices = 2;

Returns:

The indices.

getIndicesOrBuilder

OnnxMl.TensorProtoOrBuilder getIndicesOrBuilder()

 The indices of the non-default values, which may be stored in one of two formats.
 (a) Indices can be a tensor of shape [NNZ, rank] with the [i,j]-th value
 corresponding to the j-th index of the i-th value (in the values tensor).
 (b) Indices can be a tensor of shape [NNZ], in which case the i-th value
 must be the linearized-index of the i-th value (in the values tensor).
 The linearized-index can be converted into an index tuple (k_1,...,k_rank)
 using the shape provided below.
 The indices must appear in ascending order without duplication.
 In the first format, the ordering is lexicographic-ordering:
 e.g., index-value [1,4] must appear before [2,1]
 

optional .onnx.TensorProto indices = 2;

getDimsList

java.util.List<java.lang.Long> getDimsList()

 The shape of the underlying dense-tensor: [dim_1, dim_2, ... dim_rank]
 

repeated int64 dims = 3;

Returns:

A list containing the dims.

getDimsCount

int getDimsCount()

 The shape of the underlying dense-tensor: [dim_1, dim_2, ... dim_rank]
 

repeated int64 dims = 3;

Returns:

The count of dims.

getDims

long getDims(int index)

 The shape of the underlying dense-tensor: [dim_1, dim_2, ... dim_rank]
 

repeated int64 dims = 3;

Parameters:

index - The index of the element to return.

Returns:

The dims at the given index.