深度学习——05pytorch最大池化的效果（CIFAR10数据集）

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

dataset_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])
test_data = torchvision.datasets.CIFAR10(root="./test10_dataset", train=False, transform=dataset_transform)
test_loader = DataLoader(dataset=test_data, batch_size=64)

class MyNet(nn.Module):
    def __init__(self):
        super(MyNet, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=2)

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

MyNet = MyNet()
writer = SummaryWriter("CIFAR10")
step = 0
for data in test_loader:
    imgs, target = data
    output = MyNet(imgs)
    writer.add_images("input", imgs, step)
    writer.add_images("output", output, step)
    step = step + 1
writer.close()

池化层
MaxPool2d(kernel_size=2)
卷积核大小为2

在terminal中使用：
tensorboard --logdir=CIFAR10
tensorboard ：
输入：

输出：