pytorch学习2

卍郝凝卍

已于 2024-09-01 14:20:38 修改

阅读量822

点赞数 12

分类专栏： pytorch 文章标签： pytorch 学习 python

于 2024-05-10 15:13:55 首次发布

本文链接：https://blog.csdn.net/qq_52057773/article/details/138653669

版权

pytorch 专栏收录该内容

6 篇文章

订阅专栏

nn.module的使用

1. nn.module模块使用

nn.Module是对所有神经网络提供一个基本的类。
我们的神经网络是继承nn.Module这个类，即nn.Module为父类，nn.Module为所有神经网络提供一个模板，对其中一些我们不满意的部分进行修改。

import torch
from torch import nn

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()  # 继承父类的初始化
        
    def forward(self, input):          # 将forward函数进行重写
        output = input + 1
        return output
    
tudui = Tudui()
x = torch.tensor(1.0)  # 创建一个值为 1.0 的tensor
output = tudui(x)
print(output)

#tensor(2.)

2. super(Myclass, self).init()

简单理解就是子类把父类的__init__()放到自己的__init__()当中，这样子类就有了父类的__init__()的那些东西。
Myclass类继承nn.Module，super(Myclass, self).__init__()就是对继承自父类nn.Module的属性进行初始化。而且是用nn.Module的初始化方法来初始化继承的属性。
super().__init()__()来通过初始化父类属性以初始化自身继承了父类的那部分属性；这样一来，作为nn.Module的子类就无需再初始化那一部分属性了，只需初始化新加的元素。
子类继承了父类的所有属性和方法，父类属性自然会用父类方法来进行初始化。

3. forward函数

使用pytorch的时候，不需要手动调用forward函数，只要在实例化一个对象中传入对应的参数就可以自动调用 forward 函数。

因为 PyTorch 中的大部分方法都继承自 torch.nn.Module，而 torch.nn.Module 的__call__(self)函数中会返回 forward()函数的结果，因此PyTroch中的 forward()函数等于是被嵌套在了__call__(self)函数中；因此forward()函数可以直接通过类名被调用，而不用实例化对象。

class A():
    def __call__(self, param):
        print('i can called like a function')
        print('传入参数的类型是：{}   值为： {}'.format(type(param), param))
        res = self.forward(param)
        return res
    
    def forward(self, input_):
        print('forward 函数被调用了')
        print('in  forward, 传入参数类型是：{}  值为: {}'.format( type(input_), input_))
        return input_

a = A()
input_param = a('i')
print("对象a传入的参数是：", input_param)

#i can called like a function
#传入参数的类型是：<class 'str'>   值为： i
#forward 函数被调用了
#in  forward, 传入参数类型是：<class 'str'>  值为: i
#对象a传入的参数是： i

卷积

1.卷积原理

卷积核不停的在原图上进行滑动，对应元素相乘再相加。、
下图为每次滑动移动1格，然后再利用原图与卷积核上的数值进行计算得到缩略图矩阵的数据，如下图右所示。

import torch
import torch.nn.functional as F

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]])

kernel = torch.tensor([[1, 2, 1],
                       [0, 1, 0],
                       [2, 1, 0]])

print(input.shape)
print(kernel.shape)
input = torch.reshape(input, (1,1,5,5))
kernel = torch.reshape(kernel, (1,1,3,3))
print(input.shape)
print(kernel.shape)

output = F.conv2d(input, kernel, stride=1)
print(output)

#torch.Size([5, 5])
#torch.Size([3, 3])
#torch.Size([1, 1, 5, 5])
#torch.Size([1, 1, 3, 3])
#tensor([[[[10, 12, 12],
#          [18, 16, 16],
#          [13,  9,  3]]]])

2. 步幅、填充原理

步幅：卷积核经过输入特征图的采样间隔。设置步幅的目的：希望减小输入参数的数目，减少计算量。
填充：在输入特征图的每一边添加一定数目的行列。设置填充的目的：希望每个输入方块都能作为卷积窗口的中心，或使得输出的特征图的长、宽 = 输入的特征图的长、宽。
一个尺寸 a * a 的特征图，经过 b * b 的卷积层，步幅（stride）= c，填充（padding）= d，若d等于0，也就是不填充，输出的特征图的尺寸 =（a-b）/ c+1；若d不等于0，也就是填充，输出的特征图的尺寸 ={（a+2d-b）/ c}+1。

3.卷积层

Conv1d代表一维卷积，Conv2d代表二维卷积，Conv3d代表三维卷积。
kernel_size在训练过程中不断调整，定义为3就是3 * 3的卷积核，实际我们在训练神经网络过程中其实就是对kernel_size不断调整。
可以根据输入的参数获得输出的情况，如下图所示。

4. 搭建卷积层

import torch
from torch import nn
import torchvision
from torch.nn import Conv2d
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10("./dataset",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 = Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0) # 彩色图像输入为3层，我们想让它的输出为6层，选3 * 3 的卷积                
    
    def forward(self,x):
        x = self.conv1(x)
        return x
    
tudui = Tudui()
print(tudui)

#Files already downloaded and verified
#Tudui(
#  (conv1): Conv2d(3, 6, kernel_size=(3, 3), stride=(1, 1))
#)

4. 卷积层处理图片

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10("./dataset",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 = Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0) # 彩色图像输入为3层，我们想让它的输出为6层，选3 * 3 的卷积                
    
    def forward(self,x):
        x = self.conv1(x)
        return x
    
tudui = Tudui()
for data in dataloader:
    imgs, targets = data
    output = tudui(imgs)
    print(imgs.shape)   # 输入为3通道32×32的64张图片
    print(output.shape) # 输出为6通道30×30的64张图片

5. Tensorboard显示

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("./dataset",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 = Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0) # 彩色图像输入为3层，我们想让它的输出为6层，选3 * 3 的卷积                
    
    def forward(self,x):
        x = self.conv1(x)
        return x
    
tudui = Tudui()
writer = SummaryWriter("logs")
step = 0
for data in dataloader:
    imgs, targets = data
    output = tudui(imgs)
    print(imgs.shape)   
    print(output.shape)    
    writer.add_images("input", imgs, step)
    output = torch.reshape(output,(-1,3,30,30)) # 把原来6个通道拉为3个通道，为了保证所有维度总数不变，其余的分量分到第一个维度中
    writer.add_images("output", output, step)
    step = step + 1

池化

1.池化层原理

最大池化层有时也被称为下采样。
dilation为空洞卷积，如下图所示。
Ceil_model为当超出区域时，只取最左上角的值。
池化使得数据由5 * 5 变为3 * 3,甚至1 * 1的，这样导致计算的参数会大大减小。例如1080P的电影经过池化的转为720P的电影、或360P的电影后，同样的网速下，视频更为不卡。

卷积的作用就是为了提取某些指定的特征，而池化就是为了进一步抽取更高阶的特征。通过池化操作忽略一些细节信息，强行让CNN学到的更多我们想要的高阶信息。

2. 池化层处理数据

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)
input = torch.reshape(input,(-1,1,5,5)) 
print(input.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool = MaxPool2d(kernel_size=3, ceil_mode=True)
        
    def forward(self, input):
        output = self.maxpool(input)
        return output
        
tudui = Tudui()
output = tudui(input)
print(output)

3. 池化层处理图片

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,transform=torchvision.transforms.ToTensor(),download=True)       
dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool = MaxPool2d(kernel_size=3, ceil_mode=True)
        
    def forward(self, input):
        output = self.maxpool(input)
        return output

tudui = Tudui()
writer = SummaryWriter("logs")
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

非线性激活

1. 非线性激活

import torch
from torch import nn
from torch.nn import ReLU

input = torch.tensor([[1, -0.5],
                      [-1,3]])
input = toech.reshape(input,(-1,1,2,2))
print(input.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init)__()
        self.relu = ReLU()

    sef forward(self, input):
        output = self.ReLU(input)
        return output

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

#torch.Size([1, 1, 2, 2])
#tensor([[[[1., 0.],
#          [0., 3.]]]])

2. Tensorboard显示

import torch
import torchvision
from torch import nn 
from torch.nn import ReLU
from torch.nn import Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("./dataset",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.relu1 = ReLU()
        self.sigmoid1 = Sigmoid()
        
    def forward(self, input):
        output = self.sigmoid1(input)
        return output

tudui = Tudui()
writer = SummaryWriter("logs")
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

线性层与其它层

1. 神经网络

2. 线性拉平

import torch
import torchvision
from torch import nn 
from torch.nn import ReLU
from torch.nn import Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)       
dataloader = DataLoader(dataset, batch_size=64)

for data in dataloader:
    imgs, targets = data
    print(imgs.shape)
    output = torch.reshape(imgs,(1,1,1,-1))
    print(output.shape)

3. 线性层

import torch
import torchvision
from torch import nn 
from torch.nn import Linear
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)       
dataloader = DataLoader(dataset, batch_size=64,drop_last=True)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.linear1 = Linear(196608,10)
        
    def forward(self, input):
        output = self.linear1(input)
        return output

tudui = Tudui()
writer = SummaryWriter("logs")
step = 0

for data in dataloader:
    imgs, targets = data
    print(imgs.shape)
    writer.add_images("input", imgs, step)
    output = torch.reshape(imgs,(1,1,1,-1)) # 方法一：拉平
    print(output.shape)
    output = tudui(output)
    print(output.shape)
    writer.add_images("output", output, step)
    step = step + 1

import torch
import torchvision
from torch import nn 
from torch.nn import Linear
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)       
dataloader = DataLoader(dataset, batch_size=64,drop_last=True)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.linear1 = Linear(196608,10)
        
    def forward(self, input):
        output = self.linear1(input)
        return output

tudui = Tudui()
writer = SummaryWriter("logs")
step = 0

for data in dataloader:
    imgs, targets = data
    print(imgs.shape)
    writer.add_images("input", imgs, step)
    output = torch.flatten(imgs)  # 方法二：拉平。展开为一维
    print(output.shape)
    output = tudui(output)
    print(output.shape)
    step = step + 1

搭建小实战与Sequential使用

1. 神经网络

把网络结构放在Sequential里面，好处就是代码写起来比较简介、易懂。

可以根据神经网络每层的尺寸，根据下图的公式计算出神经网络中的参数。

2. 搭建神经网络

import torch
import torchvision
from torch import nn 
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.conv1 = Conv2d(3,32,5,padding=2)
        self.maxpool1 = MaxPool2d(2)
        self.cov2 = Conv2d(32,32,5,padding=2)
        self.maxpool2 = MaxPool2d(2)
        self.conv3 = Conv2d(32,64,5,padding=2)
        self.maxpool3 = MaxPool2d(2)
        self.flatten = Flatten()
        self.linear1 = Linear(1024,64)
        self.Linear2 = Linear(64,10)
        
    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)
        return x

tudui = Tudui()
print(tudui)

打印结果

3. 神经网络输入数据

import torch
import torchvision
from torch import nn 
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.conv1 = Conv2d(3,32,5,padding=2)
        self.maxpool1 = MaxPool2d(2)
        self.conv2 = Conv2d(32,32,5,padding=2)
        self.maxpool2 = MaxPool2d(2)
        self.conv3 = Conv2d(32,64,5,padding=2)
        self.maxpool3 = MaxPool2d(2)
        self.flatten = Flatten()
        self.linear1 = Linear(1024,64)
        self.Linear2 = Linear(64,10)
        
    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)
        return x

tudui = Tudui()
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)

打印结果

4. Sequential神经网络

import torch
import torchvision
from torch import nn 
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()        
        self.model1 = Sequential(
            Conv2d(3,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,64,5,padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024,64),
            Linear(64,10)
        )
        
    def forward(self, x):
        x = self.model1(x)
        return x

tudui = Tudui()
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)

打印结果

4. Tensorboard可视化网络

import torch
import torchvision
from torch import nn 
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)       
dataloader = DataLoader(dataset, batch_size=64,drop_last=True)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()        
        self.model1 = Sequential(
            Conv2d(3,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,64,5,padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024,64),
            Linear(64,10)
        )
        
    def forward(self, x):
        x = self.model1(x)
        return x

tudui = Tudui()
writer = SummaryWriter("logs")

tudui = Tudui()
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)

writer.add_graph(tudui, input)
writer.close()