reduce_max

paddle.fluid.layers. reduce_max ( input, dim=None, keep_dim=False, name=None ) [源代码]

该OP是对指定维度上的Tensor元素求最大值运算,并输出相应的计算结果。

参数

  • input (Variable)- 输入变量为多维Tensor或LoDTensor,支持数据类型为float32,float64,int32,int64。

  • dim (list | int,可选)- 求最大值运算的维度。如果为None,则计算所有元素的最大值并返回包含单个元素的Tensor变量,否则必须在 \([−rank(input),rank(input)]\) 范围内。如果 \(dim [i] <0\),则维度将变为 \(rank+dim[i]\),默认值为None。

  • keep_dim (bool)- 是否在输出Tensor中保留减小的维度。如 keep_dim 为true,否则结果张量的维度将比输入张量小,默认值为False。

  • name (str,可选) - 具体用法请参见 Name,一般无需设置,默认值为 None。

返回

在指定dim上进行求最大值运算的Tensor,数据类型和输入数据类型一致。

返回类型

变量(Variable)

代码示例

import paddle.fluid as fluid
import paddle
paddle.enable_static()
# x is a Tensor variable with following elements:
#    [[0.2, 0.3, 0.5, 0.9]
#     [0.1, 0.2, 0.6, 0.7]]
# Each example is followed by the corresponding output tensor.
x = fluid.data(name='x', shape=[2, 4], dtype='float32')
fluid.layers.reduce_max(x)  # [0.9]
fluid.layers.reduce_max(x, dim=0)  # [0.2, 0.3, 0.6, 0.9]
fluid.layers.reduce_max(x, dim=-1)  # [0.9, 0.7]
fluid.layers.reduce_max(x, dim=1, keep_dim=True)  # [[0.9], [0.7]]

# y is a Tensor variable with shape [2, 2, 2] and elements as below:
#      [[[1.0, 2.0], [3.0, 4.0]],
#      [[5.0, 6.0], [7.0, 8.0]]]
# Each example is followed by the corresponding output tensor.
y = fluid.data(name='y', shape=[2, 2, 2], dtype='float32')
fluid.layers.reduce_max(y, dim=[1, 2]) # [4.0, 8.0]
fluid.layers.reduce_max(y, dim=[0, 1]) # [7.0, 8.0]