P19.神经网络-最大池化的使用

Pytorch官网 -> Docs -> Pytorch -> torch.nn -> Pooling Layers -> MaxPool2d最大池化（下采样）

class torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)

Parameters

• kernel_size – the size of the window to take a max over

• stride – the stride of the window. Default value is kernel_size

• padding – implicit zero padding to be added on both sides

• dilation – a parameter that controls the stride of elements in the window

• return_indices – if True, will return the max indices along with the outputs. Useful for torch.nn.MaxUnpool2d later

• ceil_mode – when True, will use ceil instead of floor to compute the output shape

import torch
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]])

input = torch.reshape(input, (-1, 1, 5, 5)) # -1 means compute batch_size automatically
print(input.shape)

 torch.Size([1, 1, 5, 5])

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) # 1 -> 1.0, 2 -> 2.0

input = torch.reshape(input, (-1, 1, 5, 5)) # -1 means compute batch_size automatically
print(input.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)

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

tudui = Tudui()
output = tudui(input)
print(output)

torch.Size([1, 1, 5, 5])
tensor([[[[2., 3.],
          [5., 1.]]]]) 

 RuntimeError: "max_pool2d_with_indices_cpu" not implemented for 'Long'

解决方法：

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)

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) # 1 -> 1.0, 2 -> 2.0

input = torch.reshape(input, (-1, 1, 5, 5)) # -1 means compute batch_size automatically
print(input.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False)

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

tudui = Tudui()
output = tudui(input)
print(output)

 torch.Size([1, 1, 5, 5])
tensor([[[[2.]]]])

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("dataset", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())

dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False)

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

tudui = Tudui()

writer = SummaryWriter("P19")
step = 0
for data in dataloader:
    imgs, targets = data
    writer.add_images("input", imgs, step)
    output = tudui(imgs)
    writer.add_images("output", output, step)
    step = step + 1

writer.close()

tensorboard --logdir=P19