[土堆]深度学习快速入门教程笔记——池化层——009

1. 池化层原理

---

1. 最大池化层有时也被称为下采样。
2. dilation为空洞卷积，如下图所示。
3. Ceil_model为当超出区域时，只取最左上角的值。
4. 池化使得数据由5 * 5 变为3 * 3,甚至1 * 1的，这样导致计算的参数会大大减小。例如1080P的电影经过池化的转为720P的电影、或360P的电影后，同样的网速下，视频更为不卡。

---

2.torch.nn.MaxPool2d

---

torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1,

 return_indices=False, ceil_mode=False)

• kernel_size (Union[int, Tuple[int, int]]) – the size of the window to take a max over

• stride (Union[int, Tuple[int, int]]) – the stride of the window. Default value is kernel_size

• padding (Union[int, Tuple[int, int]]) – Implicit negative infinity padding to be added on both sides

• dilation (Union[int, Tuple[int, int]]) – a parameter that controls the stride of elements in the window

• return_indices (bool) – if True, will return the max indices along with the outputs. Useful for torch.nn.MaxUnpool2d later

• ceil_mode (bool) – when True, will use ceil instead of floor to compute the output shape

• 当 ceil_mode=True 时，如果滑动窗口在左填充内边距内启动，则允许它们越界或输入。将在右侧填充区域开始的滑动窗口将被忽略。

---

3. 池化层处理图片

---

import torch
import torchvision
from torch import nn 
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)       
dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool = MaxPool2d(kernel_size=3, ceil_mode=True)
        
    def forward(self, input):
        output = self.maxpool(input)
        return output

tudui = Tudui()
writer = SummaryWriter("logs")
step = 0

for data in dataloader:
    imgs, targets = data
    writer.add_images("input", imgs, step)
    output = tudui(imgs)
    writer.add_images("output", output, step)
    step = step + 1