pytorch神经网络最大池化的的使用

pytorch神经网络最大池化的的使用
池化=下采样
stride=kernel_size
nn.MaxPool2d

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

dataset = torchvision.datasets.CIFAR10("../data", train = False, download = Ture, transform = torchvision.transforms.ToTensor())
dataloader =  DataLoader(dataset, batch_size = 64)
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 Model_test(nn.Module)：
		def __init__(self):
			super(Model_test, self).__init__()
			self.maxpool1 = MaxPool2d(kernel_size = 3, ceil_mode = Ture)
		
		def forward(self, input):
			output = self.maxpool1(input)
			return output


model_test = Model_test()	


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


#terminal :tensorboard --logdir=logs_maxpool