pytorch -- torch.nn网络结构

1. 官网描述

官���

使用 torch.nn 模块，我们可以创建自定义的神经网络模型，并使用 PyTorch 提供的优化器（如 torch.optim）和损失函数来训练和优化模型。

2. 常见结构

1.卷积操作

定义：

二维卷积

1.1版本 nn.functional.conv2d

torch.nn.functional.conv2d(input,weight,bias=None,stride=1,padding=0,dilation=1, groups=1)

例子：

代码：

import torchimport torch.nn.functional as Finput = 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]])kernel = torch.tensor([[1,2,1],                       [0,1,0],                       [2,1,0]])print(input.shape,kernel.shape)#5,5 3,3input = torch.reshape(input,(1,1,5,5))kernel = torch.reshape(kernel,(1,1,3,3))output = F.conv2d(input,kernel,stride=1)print(output)output2 = F.conv2d(input,kernel,stride=2)print(output2)# padding=1 上下左右加一圈0output3 = F.conv2d(input,kernel,stride=1,padding=1)print(output3)

运行：

1.2版本 torch.nn.Conv2d

torch.nn.Conv2d(in_channels,    输入通道数out_channels,   输出通道数kernel_size,    卷积核大小（int or turple）3 (1,2)stride=1,       卷积核移动的步长padding=0,      边界填充（加几圈0）dilation=1,groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)

代码

import torchimport torchvisionfrom torch import nnfrom torch.utils.data import DataLoaderfrom torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10('data',train=False,                                       transform=torchvision.transforms.ToTensor(),                                       download=True)dataloader = DataLoader(dataset,batch_size=64)class Tudui(nn.Module):    def __init__(self):        super(Tudui,self).__init__()        self.conv1 = nn.Conv2d(3,6,3,stride=1,padding=0)    def forward(self,x):        x = self.conv1(x)        return xtudui = Tudui()writer = SummaryWriter('logs')step = 0for data in dataloader:    imgs,targets = data    output = tudui(imgs)    print(output.shape)    # 输入大小    writer.add_images('input',imgs,step)    # 输出大小    output = torch.reshape(output,(-1,3,30,30))    writer.add_images('output', output, step)    step+=1

输出：

2.池化操作

目的：保留输入特征，减小数据量

最大池化MaxPool2d：下采样

torch.nn.MaxPool2d(

kernel_size, int/tuple 窗口

stride=None, 步长（默认值是Kernel_size）

padding=0, 在外面加一圈

dilation=1, （空洞卷积）

return_indices=False,

ceil_mode=False ceil模式：向上取整

)

例子：

import torchimport torchvision.datasetsfrom torch import nninput = 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]])# (N,C,Hin,Win) (C,Hin,Win)  -1表示自己计算batchsize,input = torch.reshape(input,(-1,1,5,5))print(input.shape)class Tudui(nn.Module):    def __init__(self):        super(Tudui,self).__init__()        self.maxpool1 = nn.MaxPool2d(kernel_size=3,ceil_mode=True)# 模板创建自己的    def forward(self,input):        output = self.maxpool1(input)#输入        return outputtudui = Tudui()output = tudui(input)print(output)

输出

例子2

代码

import torchimport torchvision.datasetsfrom torch import nnfrom torch.utils.data import DataLoaderfrom torch.utils.tensorboard import SummaryWriterclass Tudui(nn.Module):    def __init__(self):        super(Tudui,self).__init__()        self.maxpool1 = nn.MaxPool2d(kernel_size=3,ceil_mode=True)# 模板创建自己的    def forward(self,input):        output = self.maxpool1(input)#输入        return outputtudui = Tudui()dataset = torchvision.datasets.CIFAR10('data',train=False,download=True,transform=torchvision.transforms.ToTensor())dataloader = DataLoader(dataset,batch_size=64)writer = SummaryWriter('logs_maxpool')step = 0for data in dataloader:    imgs,targets = data    writer.add_images('input', imgs, step)    output = tudui(imgs)    writer.add_images('maxpool',output,step)    step+=1writer.close()

输出

3.非线性激活

torch.nn.ReLU(inplace=False)torch.nn.Sigmoid(*args, **kwargs)

代码：

import torchfrom torch import nninput = torch.tensor([[1,-0.5],                      [-1,3]])input = torch.reshape(input,(-1,1,2,2))class Tudui(nn.Module):    def __init__(self):        super().__init__()        self.relu1 = nn.ReLU()    def forward(self,input):        output = self.relu1(input)        return outputtudui = Tudui()output = tudui(input)print(output)

运行

例子2：

代码：

import torchimport torchvision.datasetsfrom torch import nnfrom torch.utils.data import DataLoaderfrom torch.utils.tensorboard import SummaryWriter# sigmoiddataset = torchvision.datasets.CIFAR10('data',train=False,download=True,transform=torchvision.transforms.ToTensor())dataloader = DataLoader(dataset,batch_size=64)class Tudui(nn.Module):    def __init__(self):        super().__init__()        self.sigmoid1 = nn.Sigmoid()    def forward(self,input):        output = self.sigmoid1(input)        return outputtudui = Tudui()writer = SummaryWriter('logs_sigmoid')step = 0for data in dataloader:    imgs,targets = data    writer.add_images('input',imgs,step)    output = tudui(imgs)    writer.add_images('output', output, step)    print(output.shape)    step+=1writer.close()

输出

4.线性层

torch.nn.Linear(

in_features,

out_features,

bias=True,

device=None, dtype=None)

代码：

import torchimport torchvisionfrom torch import nnfrom torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10('data',train=False,transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset,64,drop_last=True)class Tudui(nn.Module):    def __init__(self):        super(Tudui,self).__init__()        self.linear1 = nn.Linear(in_features=196608,out_features=10)    def forward(self,input):        return self.linear1(input)tudui = Tudui()for data in dataloader:    imgs, targets = data    # output = torch.flatten(imgs)    #torch.Size([196608])    # 替换展平    output = torch.reshape(imgs,(1,1,1,-1)) #torch.Size([1, 1, 1, 196608])    print(output.shape)    output = tudui(output)            #torch.Size([10]) torch.Size([1, 1, 1, 10])    print(output.shape)

4.序列化层（sequential）

例子：

代码：

import torchfrom torch import nnfrom torch.utils.tensorboard import SummaryWriterclass Tudui(nn.Module):    def __init__(self):        super().__init__()        # 草稿中计算 stride padding        self.conv1 = nn.Conv2d(in_channels=3,out_channels=32,kernel_size=5,stride=1,padding=2)        self.maxpool1 = nn.MaxPool2d(2)        self.conv2 = nn.Conv2d(in_channels=32,out_channels=32,kernel_size=5,padding=2)        self.maxpool2 = nn.MaxPool2d(2)        self.conv3 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size=5,padding=2)        self.maxpool3 = nn.MaxPool2d(2)        self.flatten = nn.Flatten()        #64是隐藏单元数        self.linear1 = nn.Linear(in_features=1024,out_features=64)        #10是输出类别        self.linear2 = nn.Linear(in_features=64, out_features=10)        # 另一种写法        self.model1 = nn.Sequential(            nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),            nn.MaxPool2d(2),            nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),            nn.MaxPool2d(2),            nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),            nn.MaxPool2d(2),            nn.Flatten(),            nn.Linear(in_features=1024, out_features=64),            nn.Linear(in_features=64, out_features=10)        )    def forward(self,x):        # x = self.conv1(x)        # x = self.maxpool1(x)        # x = self.conv2(x)        # x = self.maxpool2(x)        # x = self.conv3(x)        # x = self.maxpool3(x)        # x = self.flatten(x)        # x = self.linear1(x)        # x = self.linear2(x)        # sequential方式        x = self.model1(x)        return xtudui = Tudui()print(tudui)# 用来检验网络结构参数input = torch.ones((64,3,32,32))# 64 batchsize（64张）output = tudui(input)writer= SummaryWriter('logs_s')writer.add_graph(tudui,input)writer.close()

输出