神经网络：池化层

7. 神经网络 池化操作

   下采样：减少特征数量

   先看池化操作：

   其中ceil_mode设置成True和False池化区别：

   在这个例子当中：ceil_mode=True表示边缘不满3x3的部分也会被池化，False表示边缘不满3x3的部分不会采样

   code：

   import torch
   from torch import nn
   from torch.nn import MaxPool2dinput = 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)
   #这里dtype为float是因为maxpool2d只能处理float类型的数据input = torch.reshape(input,(-1,1,5,5))
   print(input.shape)class Net(nn.Module):def __init__(self):super(Net,self).__init__()#ceil_mode=True表示边缘不满3x3的部分也会被池化#kernel_size=3 默认是卷积核的大小self.maxpool1 = MaxPool2d(kernel_size=3,ceil_mode=True)self.maxpool2 = MaxPool2d(kernel_size=3,ceil_mode=False)def forward(self,input):#output = self.maxpool1(input)output = self.maxpool2(input)return outputnet = Net()
   output = net(input)
   print(output)
   

   ceil_mode=True:

   

   ceil_mode=False:

   

8. 神经网络 池化层
   这里需要先看这篇博客：

https://blog.csdn.net/whdehcy/article/details/149486555?fromshare=blogdetail&sharetype=blogdetail&sharerId=149486555&sharerefer=PC&sharesource=whdehcy&sharefrom=from_link

是讲卷积层的

现在将上一步的卷积得到的特征图作为池化的输入

    pool_output = poolnet(conv_output)writer.add_images('pool_output',pool_output,cnt)

只需要添加一下池化的操作

class poolNet(nn.Module):def __init__(self):super(poolNet,self).__init__()#ceil_mode=True表示边缘不满3x3的部分也会被池化#kernel_size=3 默认是卷积核的大小self.maxpool1 = MaxPool2d(kernel_size=3,ceil_mode=True)self.maxpool2 = MaxPool2d(kernel_size=3,ceil_mode=False)def forward(self,input):output = self.maxpool1(input)#output = self.maxpool2(input)return outputpoolnet = poolNet()

完整版代码：

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from torchvision.datasets import ImageFolder
from torchvision import transforms#数据预处理
transform = transforms.Compose([transforms.Resize((224,224)),transforms.ToTensor(),transforms.Normalize(mean = [0.5,0.5,0.5],std = [0.5,0.5,0.5])
])#加载数据集
folder_path = '../images'
dataset = ImageFolder(folder_path,transform=transform)
dataloader = DataLoader(dataset,batch_size=1)#卷积
class convNet(nn.Module):def __init__(self):#调用父类nn.Module的构造函数super(convNet,self).__init__()self.conv1 = Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0)def forward(self,x):x = self.conv1(x)return xconvnet = convNet()#池化
class poolNet(nn.Module):def __init__(self):super(poolNet,self).__init__()#ceil_mode=True表示边缘不满3x3的部分也会被池化#kernel_size=3 默认是卷积核的大小self.maxpool1 = MaxPool2d(kernel_size=3,ceil_mode=True)self.maxpool2 = MaxPool2d(kernel_size=3,ceil_mode=False)def forward(self,input):output = self.maxpool1(input)#output = self.maxpool2(input)return outputpoolnet = poolNet()writer = SummaryWriter('../logs')cnt = 0
for data in dataloader:img,label = dataprint(img.shape)conv_output = convnet(img)print(conv_output.shape)writer.add_images('input',img,cnt)conv_output = torch.reshape(conv_output,(-1,3,222,222))writer.add_images('conv_output',conv_output,cnt)pool_output = poolnet(conv_output)writer.add_images('pool_output',pool_output,cnt)cnt = cnt + 1writer.close()

卷积：

池化：