Tensor {Microsoft.VisualBasic.MachineLearning.TensorFlow} .NET clr documentation

Tensor

Description

张量类 - GNN中所有数值计算的基础数据结构 支持多维数组的存储和基本数学运算

Declare

            
# namespace Microsoft.VisualBasic.MachineLearning.TensorFlow
export class Tensor {
   # 底层数据数组 Underlying data array
   Data: double;
   # 张量的维度数组(兼容旧版本)
   Dimensions: integer;
   # 梯度(用于反向传播) Gradient for backpropagation
   Gradient: Tensor;
   # 是否为变量(可训练) Whether this is a variable (trainable)
   IsVariable: boolean;
   # 张量中元素的总数
   Length: integer;
   # 张量的维度数
   Rank: integer;
   # 张量的形状(各维度大小)
   Shape: integer;
   # 张量中元素的总数(兼容旧版本)
   TotalLength: integer;
}

        

.NET clr type reference tree

  1. use by property member Gradient: Tensor

[Package {$package} version {$version} Index]