Class SparseTensorProto
A serialized sparse-tensor value
Inheritance
SparseTensorProto
Namespace: Onnx
Syntax
public sealed class SparseTensorProto : Google.Protobuf.IMessage<SparseTensorProto>
Constructors
SparseTensorProto()
Declaration
public SparseTensorProto()
SparseTensorProto(SparseTensorProto)
Declaration
public SparseTensorProto(SparseTensorProto other)
Parameters
Fields
DimsFieldNumber
Field number for the "dims" field.
Declaration
public const int DimsFieldNumber = 3
Field Value
IndicesFieldNumber
Field number for the "indices" field.
Declaration
public const int IndicesFieldNumber = 2
Field Value
ValuesFieldNumber
Field number for the "values" field.
Declaration
public const int ValuesFieldNumber = 1
Field Value
Properties
Descriptor
Declaration
public static Google.Protobuf.Reflection.MessageDescriptor Descriptor { get; }
Property Value
| Type |
Description |
| Google.Protobuf.Reflection.MessageDescriptor |
|
Dims
The shape of the underlying dense-tensor: [dim_1, dim_2, ... dim_rank]
Declaration
public Google.Protobuf.Collections.RepeatedField<long> Dims { get; }
Property Value
| Type |
Description |
| Google.Protobuf.Collections.RepeatedField<Int64> |
|
Indices
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]
Declaration
public TensorProto Indices { get; set; }
Property Value
Parser
Declaration
public static Google.Protobuf.MessageParser<SparseTensorProto> Parser { get; }
Property Value
Values
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.
Declaration
public TensorProto Values { get; set; }
Property Value
Methods
CalculateSize()
Declaration
public int CalculateSize()
Returns
Clone()
Declaration
public SparseTensorProto Clone()
Returns
Equals(SparseTensorProto)
Declaration
public bool Equals(SparseTensorProto other)
Parameters
Returns
Equals(Object)
Declaration
public override bool Equals(object other)
Parameters
| Type |
Name |
Description |
| Object |
other |
|
Returns
GetHashCode()
Declaration
public override int GetHashCode()
Returns
Declaration
public void MergeFrom(Google.Protobuf.CodedInputStream input)
Parameters
| Type |
Name |
Description |
| Google.Protobuf.CodedInputStream |
input |
|
MergeFrom(SparseTensorProto)
Declaration
public void MergeFrom(SparseTensorProto other)
Parameters
ToString()
Declaration
public override string ToString()
Returns
WriteTo(Google.Protobuf.CodedOutputStream)
Declaration
public void WriteTo(Google.Protobuf.CodedOutputStream output)
Parameters
| Type |
Name |
Description |
| Google.Protobuf.CodedOutputStream |
output |
|