PyTorch⑥---卷积神经网络_池化层

最大池化（下采样）

目的：保留输入的特征，同时减少数据量。参数更少了，使得训练的更快。

参数：
kernel_size:卷积核大小
ceil_mode:Ture保留、False不保留
注意输入输出都是四个参数或三个

import torch
from torch import nn
from torch.nn import MaxPool2d

input=torch.tensor([[1,2,0,3,1],
                    [0,1,2,3,1],
                    [1,2,1,0,0],
                    [5,2,3,1,1],
                    [2,1,0,1,1]
                    ],dtype=torch.float32)
input=torch.reshape(input,(-1,1,5,5))
print(input.shape)
class Demo(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.maxpool1=MaxPool2d(kernel_size=3,ceil_mode=True)
    def forward(self,input):
        output=self.maxpool1(input)
        return output

demo=Demo()
output=demo(input)
print(output)

结果：

import torch
import torchvision.datasets
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_CIFAR10",train=False,
                                     download=True,
                                     transform=torchvision.transforms.ToTensor())
dataloader=DataLoader(dataset,batch_size=64)




class Demo(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.maxpool1=MaxPool2d(kernel_size=3,ceil_mode=True)

    def forward(self,input):
        output=self.maxpool1(input)
        return output

demo=Demo()

writer=SummaryWriter("logs_maxpool")
step=0
for data in dataloader:
    imgs,targets=data
    writer.add_images("input",imgs,step)
    output=demo(imgs)
    writer.add_images("output",output,step)
    step=step+1
writer.close()

池化的通道数不会改变哦~池化后参数量大大减少，所以经常在卷积层后加一层池化层，再加一层非线性激活。