Pytorch学习笔记(五):nn.AdaptiveAvgPool2d()函数详解

1.函数语法格式和作用

作用:
自适应平均池化，指定输出（H，W）
函数语言格式:

nn.AdaptiveAvgPool2d(output_size)

2.参数解释

• output_size：指定输出固定尺寸

3.具体代码

import torch
import torch.nn as nn
m = nn.AdaptiveAvgPool2d((5,1))
m1 = nn.AdaptiveAvgPool2d((None,5))
m2 = nn.AdaptiveAvgPool2d(1)
input = torch.randn(2, 64, 8, 9)
output = m(input)
output1 = m1(input)
output2 = m2(input)
print('nn.AdaptiveAvgPool2d((5,1)):',output.shape)
print('nn.AdaptiveAvgPool2d((None,5)):',output1.shape)
print('nn.AdaptiveAvgPool2d(1):',output2.shape)

结果：