最大池化层

# 1.池化层原理
# 最大池化层有时也被称为下采样
# dilation为空洞卷积
# Ceil_model为当超出区域时，只取最左上角的值
# 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。
# 最大池化（Max Pooling）:它通过选择每个局部区域内的最大值作为该区域的代表值。
# 平均池化（Average Pooling）:平均池化则是计算每个局部区域的平均值作为该区域的代表值。
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

# 2.池化层处理数据
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 MyModule(nn.Module):
    def __init__(self):
        super(MyModule, self).__init__()
        self.maxpool = MaxPool2d(kernel_size=3, ceil_mode=True)

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


model = MyModule()
output = model(input)
print(output)

# 3.池化层处理图片
dataset = torchvision.datasets.CIFAR10(root='D:\PyCharm\CIFAR10', train=False,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)


class MyModule1(nn.Module):
    def __init__(self):
        super(MyModule1, self).__init__()
        self.maxpool = nn.MaxPool2d(kernel_size=3, ceil_mode=True)

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


model = MyModule1()
writer = SummaryWriter("logs10")
step = 0
for data in dataloader:
    imgs, targets = data
    for i, img in enumerate(imgs):
        img_input_hwc = img.permute(1, 2, 0)
        writer.add_image('input', img_input_hwc, step, dataformats="HWC")
    output = model(input)
    for i, img in enumerate(imgs):
        img_output_hwc = img.permute(1, 2, 0)
        writer.add_image('output', img_output_hwc, step, dataformats="HWC")
    step = step + 1
writer.close()