class torch.nn.MaxPool1d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)
kernel_size(int or tuple) - max pooling的窗口大小
stride(int or tuple, optional) - max pooling的窗口移动的步长。默认值是kernel_size
padding(int or tuple, optional) - 输入的每一条边补充0的层数
dilation(int or tuple, optional) – 一个控制窗口中元素步幅的参数
return_indices - 如果等于True,会返回输出最大值的序号,对于上采样操作会有帮助
ceil_mode - 如果等于True,计算输出信号大小的时候,会使用向上取整,代替默认的向下取整的操作
举个例子,构建一个卷积核大小为1x3,步长为2的池化层
import torch
import torch.nn as nn
from torch.autograd import Variable
m = nn.MaxPool1d(3, stride=2)
input = Variable(torch.randn(2, 4, 5))
output = m(input)
print(input)
print(output)
tensor([[[ 1.0000, -0.2401, -1.1694, 0.3162, 0.5495],
[-0.0668, -0.1455, -0.6538, 0.7396, -1.2040],
[ 1.9750, 0.9449, 0.6117, 0.9990, -0.8750],
[ 0.5644, -0.2105, 0.1103, 1.2369, 0.3041]],
[[-0.6587, 0.5686, -0.4883, 1.4393, 2.0761],
[ 0.7883, 0.9219, 3.0924, 0.0957, 0.3198],
[ 1.3996, 0.7220, 0.8044, 1.4365, -0.9084],
[ 0.8209, 0.6308, 1.7780, -0.2451, -0.7157]]])
tensor([[[ 1.0000, 0.5495],
[-0.0668, 0.7396],
[ 1.9750, 0.9990],
[ 0.5644, 1.2369]],
[[ 0.5686, 2.0761],
[ 3.0924, 3.0924],
[ 1.3996, 1.4365],
[ 1.7780, 1.7780]]])
1x3的池化层首先在图中红色区域的3个数中,选出最大的数字1,然后移动2个步长,在图中绿色区域的3个数中选择处最大的数字0.549。接着下移1行,用同样的方式操作
class torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)
参数:
kernel_size(int or tuple) - max pooling的窗口大小
stride(int or tuple, optional) - max pooling的窗口移动的步长。默认值是kernel_size
padding(int or tuple, optional) - 输入的每一条边补充0的层数
dilation(int or tuple, optional) – 一个控制窗口中元素步幅的参数
return_indices - 如果等于True,会返回输出最大值的序号,对于上采样操作会有帮助
ceil_mode - 如果等于True,计算输出信号大小的时候,会使用向上取整,代替默认的向下取整的操作
举个例子,构建一个卷积核大小为1x3,步长为2的池化层
import torch
import torch.nn as nn
from torch.autograd import Variable
m = nn.MaxPool2d(3, stride=2)
input = Variable(torch.randn(2, 4, 5))
output = m(input)
print(input)
print(output)
tensor([[[ 1.0000, -0.2401, -1.1694, 0.3162, 0.5495],
[-0.0668, -0.1455, -0.6538, 0.7396, -1.2040],
[ 1.9750, 0.9449, 0.6117, 0.9990, -0.8750],
[ 0.5644, -0.2105, 0.1103, 1.2369, 0.3041]],
[[-0.6587, 0.5686, -0.4883, 1.4393, 2.0761],
[ 0.7883, 0.9219, 3.0924, 0.0957, 0.3198],
[ 1.3996, 0.7220, 0.8044, 1.4365, -0.9084],
[ 0.8209, 0.6308, 1.7780, -0.2451, -0.7157]]])
tensor([[[1.9750, 0.9990]],
[[3.0924, 3.0924]]])
3x3的池化层首先在图中红色区域的9个数中,选出最大的数字1.9750, 然后移动2个步长,在图中绿色区域的9个数中选择处最大的数字0.9990。接着下移2行,发现3x3的池化层超出边界,那就跳到下一个4x5的输入层,接着重复上一个4x5的输入层操作