1.应用
import torch
import torch.nn as nn
m = nn.MaxPool2d(2)
input = torch.randn(1, 1, 4, 4)
output = m(input)
API
1.MaxPool2d类
CLASS torch.nn.MaxPool2d(kernel_size: Union[T, Tuple[T, ...]], stride: Optional[Union[T, Tuple[T, ...]]] = None, padding: Union[T, Tuple[T, ...]] = 0, dilation: Union[T, Tuple[T, ...]] = 1, return_indices: bool = False, ceil_mode: bool = False)
参数 | 描述 |
---|
kernel_size | |
stride | |
padding | |
dilation | |
return_indices | |
ceil_mode | |
2.MaxPool2d对象
参数 | 描述 |
---|
input | (N,C,H,W) |
output | (N,C,HW) |
参考:
https://pytorch.org/docs/stable/generated/torch.nn.MaxPool2d.html#torch.nn.MaxPool2d