ReduceOperation

功能

在指定维度上求和、取最大值或最小值，并消除这个维度。

计算公式

• REDUCE_MAX：

  相当于pytorch中

  intensor.amax(axis)

  • 示例1

    x shape: [2,3], axis: [0]

    x:
    tensor([[ 1, 18, 17],
            [16, 10,  1]])
    output:
    tensor([16, 18, 17])

  • 示例2

    x shape: [2,3,2], axis: [0,1]

    x:
    tensor([[[17,  3],
             [19,  6],
             [ 1, 18]],
    
            [[ 4,  5],
             [ 8,  1],
             [14, 18]]])
    output:
    tensor([19, 18])

• REDUCE_MIN：

  相当于pytorch中

  intensor.amin(axis)

  • 示例1

    x shape: [2,3], axis: [0]

    x:
    tensor([[16,  2,  7],
            [18, 16, 17]])
    output:
    tensor([16,  2,  7])

  • 示例2

    x shape: [2,3,2], axis: [0,1]

    x:
    tensor([[[ 9,  4],
             [11,  0],
             [ 2,  6]],
    
            [[ 2,  7],
             [ 8, 16],
             [ 5,  3]]])
    output:
    tensor([2, 0])

• REDUCE_SUM：

  相当于pytorch中

  torch.sum(intensor, axis)

  • 示例1

    x shape: [2,3], axis: [0]

    x:
    tensor([[-0.9701, -0.8059,  0.2919],
            [-0.1444, -2.3023,  1.2257]])
    output:
    tensor([-1.1145, -3.1082,  1.5176])

  • 示例2

    x shape: [2,3,2], axis: [0,1]

    x:
    tensor([[[ 1.4630, -0.3619],
             [-0.4526, -1.0142],
             [-0.2883,  0.9334]],
    
            [[ 0.7801, -0.1580],
             [ 0.4843,  1.8145],
             [ 0.9706, -1.8114]]])
    output:
    tensor([ 2.9571, -0.5976])

定义

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

struct ReduceParam {
    enum ReduceType {
        REDUCE_UNDEFINED = 0,
        REDUCE_MAX,
        REDUCE_MIN,
        REDUCE_SUM,
    };
    ReduceType reduceType = REDUCE_UNDEFINED;
    SVector<int64_t> axis;
    uint8_t rsv[8] = {0};
};

参数列表

输入

输出

规格约束

• axis不能为空且长度要求小于等于输入x的维度。
• axis中各元素要求小于x的维度且大于等于0。
• reduceType必须是REDUCE_MAX、REDUCE_MIN或REDUCE_SUM。