MaxPool2dMaxPool2d:在由多个输入平面组成的输入信号上应用 2D 最大池化
最大池化后数据量大大减少,训练速度增加
代码实战:
import torch
from torch import nn
from torch.nn import MaxPool2d
#将列表数据转换为浮点型
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))
class Test(nn.Module):
def __init__(self):
super(Test, self).__init__()
#kernel_size:最大的窗口大小 3:3×3
#ceil_mode:如果为 True,将使用ceil而不是floor来计算输出形状
#ceil是向上取整(保留),floor是向下取整(舍去),默认为ceil_mode=False
#当 ceil_mode=True 时,如果滑动窗口从左侧填充或输入中开始,则允许它们越界。将在右侧填充区域开始的滑动窗口将被忽略
self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)
def forward(self, input):
output = self.maxpool1(input)
return output
test1 = Test()
output = test1(input)
print(output)
当ceil_mode=True时,结果:
tensor([[[[2., 3.],
[5., 1.]]]])
当ceil_mode=False时,结果:
tensor([[[[2.]]]])
CIFAR10数据集的操作:
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("../data", train=False, download=True, transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)
#将列表数据转换为浮点型
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))
class Test(nn.Module):
def __init__(self):
super(Test, self).__init__()
#MaxPool2dMaxPool2d:在由多个输入平面组成的输入信号上应用 2D 最大池化
#kernel_size:最大的窗口大小 3:3×3
#ceil_mode:如果为 True,将使用ceil而不是floor来计算输出形状
#ceil是向上取整(保留),floor是向下取整(舍去),默认为ceil_mode=False
#当 ceil_mode=True 时,如果滑动窗口从左侧填充或输入中开始,则允许它们越界。将在右侧填充区域开始的滑动窗口将被忽略
self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False)
def forward(self, input):
output = self.maxpool1(input)
return output
test1 = Test()
writer = SummaryWriter("logs_maxpool")
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images("input", imgs, step)
output = test1(imgs)
writer.add_images("output", output, step)
step = step + 1
writer.close()
Terminal中开启端口:
tensorboard --logdir="logs_maxpool" --port=6007