学习笔记(b站小土堆)

标签：input nn output self torch 笔记 学习 import 土堆

一、torchvision中的数据集使用

CIFAR10

结果，图片展示为一只猫

二、DataLoader的使用

结果

测试集当中的第一个数据是一个三通道（RGB），是个彩色的图片，尺寸为32*32 ，对应的target是3

batch_size=4就是从当中去取test_data[0]、test_data[1]、test_data[2]、test_data[3]，把对应的img打包

结果

由于batch_size=4，所以将四个进行打包，torch.Size([4,3,32,32])表示从dataset当中取了4张图片，三通道，32*32，同时还把4个target进行打包，每张图片对应的5、9、0、0

用img.add()查看图片

结果可以发现图片被四个四个打包在一起

当改变batch_size=64时，也许改变tag

发现最后一张图不够64，这是因为drop_last=False的缘故将drop_last=True（注意也要修改tag）则可得到最后一步step155为64张，把step=156舍去 

shuffle=False表示每次抓取的数据是一样的

shuffle=True 【 test_loader = DataLoader(dataset=test_data,batch_size=64,shuffle=True , num_workers=0,drop_last=True) 】时

相同的步骤但图片顺序不同

三、神经网络骨架的基本搭建（torch.nn中containers中module）

定义一个类Model,继承父类nn.Module,在__init__()函数与forward()函数中写必要的条件

神经网络前向传播

自己搭建

调用

四、卷积操作

Conv2d — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html#torch.nn.Conv2d

1、理解stride

代码

import torch
import torch.nn.functional as F

input = torch.tensor([[1,2,0,3,1],   #连续中括号数，几个就是几维矩阵
                      [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]])

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)

output2 = F.conv2d(input,kernel,stride=2)
print(output2)

结果

2、理解padding

output3 = F.conv2d(input,kernel,stride=1,padding=1 )
print(output3)

结果

五、神经网络-卷积层

Conv2d — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html#conv2d

• in_channels (int) – Number of channels in the input image

• out_channels (int) – Number of channels produced by the convolution

• kernel_size (int or tuple) – Size of the convolving kernel

• stride (int or tuple, optional) – Stride of the convolution. Default: 1

• padding (int, tuple or str, optional) – Padding added to all four sides of the input. Default: 0

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

dataset = torchvision.datasets.CIFAR10("./data",train=False ,transform=torchvision.transforms.ToTensor(),
                                       download=True  )#需要测试数据集,把数据类型转换成tensor数据类型
dataloader = DataLoader(dataset,batch_size=64) #把数据集放在dataloader中加载

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui,self).__init__()
        self.conv1 = Conv2d(3,6,3,1,0)

    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)
    print(output.shape)

dataloader加载 batch_size=64，in_channels=3(3层彩色图像)，32*32大小，经过卷积之后in_channels=6,30*30大小

通过tensorboard查看

tudui = Tudui()

writer = SummaryWriter("./llogs")
step=0
for data in dataloader:
    imgs,targets = data
    output = tudui(imgs)
    print(imgs.shape)
    print(output.shape)
    # torch.Size([64, 3, 32, 32])
    writer.add_images("input",imgs,step)
    # torch.Size([64, 6, 30, 30]) ->[xxx,3,30,30]
    output = torch.reshape(output,(-1,3,30,30))
    writer.add_images("output",output,step)
    step = step+1

由于卷积过后图像变为6通道，无法显示，这里将输出图像从6 通道变为3通道，多余的像素点也显示，故输出有64*2张图

六、神经网络-最大池化的使用

MaxPool2d — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.MaxPool2d.html#maxpool2d

默认padding为kernel_size的大小，即为3

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) #变为浮点数据类型
input = torch.reshape(input,(-1,1,5,5))
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)

当ceil_mode= False时

用tensorboard查看

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)

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("logs_maxpool")
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()

七、神经网络-非线性激活

ReLU — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.ReLU.html#relu

参数inplace的作用

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

input = torch.tensor([[1,-0.5],
                      [-1,3]])

input = torch.reshape(input,(-1,1,2,2))
print(input.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui ,self).__init__()
        self.relu1 = ReLU()

    def forward(self,input):
        output = self.relu1(input)
        return output

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

可以看出来-0.5 -1都变为0

nn.ReLU在图像显示上不明显，换为nn.LogSigmoid

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

input = torch.tensor([[1,-0.5],
                      [-1,3]])

input = torch.reshape(input,(-1,1,2,2))
print(input.shape)

dataset = 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(Tudui ,self).__init__()
        self.relu1 = ReLU()
        self.sigmoid1 = Sigmoid()

    def forward(self,input):
        output = self.sigmoid1(input)
        return output

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

writer.close()

八、神经网络-线性层及其它层介绍

Linear — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.Linear.html#linear

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

dataset = 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.linear1 = Linear(196608,10)

    def forward(self,input):
        output = self.linear1(input)
        return output

tudui = Tudui()

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

可用   output = torch.flatten(imgs)   展平

九、神经网络-搭建小实战和sequential的使用

Sequential — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#sequentialCIFAR10的 网络结构

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


class Yebi(nn.Module):
    def __init__(self):
        super(Yebi, 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 = Yebi()
print(tudui)

sequential的使用

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


class Yebi(nn.Module):
    def __init__(self):
        super(Yebi, 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 = Yebi()
print(tudui)

十、损失函数与反向传播

L1Loss

L1Loss — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.L1Loss.html#l1loss

import torch
from torch.nn import L1Loss

inputs = torch.tensor([1,2,3],dtype=torch.float32)
targets = torch.tensor([1,2,5],dtype=torch.float32)

inputs = torch.reshape(inputs,(1,1,1,3))  #batch_size=1,1通道,1行3列
targets = torch.reshape(targets,(1,1,1,3))

loss = L1Loss()
result = loss(inputs, targets)

print(result)

 [（1-1）+（2-2）+（5-3）] /3

L1Loss()可以指定计算方法，如  loss = L1Loss(reduction='sum')

（1-1）+（2-2）+（5-3）

则结果为

MSELoss 

MSELoss — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.MSELoss.html#mseloss

import torch
from torch import nn
from torch.nn import L1Loss

inputs = torch.tensor([1,2,3],dtype=torch.float32)
targets = torch.tensor([1,2,5],dtype=torch.float32)

inputs = torch.reshape(inputs,(1,1,1,3))  #batch_size=1,1通道,1行3列
targets = torch.reshape(targets,(1,1,1,3))

loss = L1Loss(reduction='sum')
result = loss(inputs, targets)

loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs,targets)

print(result)
print(result_mse)

结果

 CrossEntropyLoss

CrossEntropyLoss — PyTorch 2.4 documentationhttps://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html#crossentropyloss

 

import torch
from torch import nn
from torch.nn import L1Loss

inputs = torch.tensor([1,2,3],dtype=torch.float32)
targets = torch.tensor([1,2,5],dtype=torch.float32)

inputs = torch.reshape(inputs,(1,1,1,3))  #batch_size=1,1通道,1行3列
targets = torch.reshape(targets,(1,1,1,3))

loss = L1Loss(reduction='sum')
result = loss(inputs, targets)

loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs,targets)

print(result)
print(result_mse)

x = torch.tensor([0.1,0.2,0.3])
y = torch.tensor([1])
x = torch.reshape(x,(1,3))
loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x,y)
print(result_cross)

 根据一个网络模型，用CrossEntropyLoss计算实际输出和目标之间的差距

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("../data",train=False,transform=torchvision.transforms.ToTensor(),
                                       download=True)
dataloader = DataLoader(dataset, batch_size=1)

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

loss = nn.CrossEntropyLoss ()
tudui = Tudui()
for data in dataloader:
    imgs,targets = data
    outputs = tudui(imgs)
    result_loss = loss(outputs,targets)
    print(result_loss)

 计算的结果就是神经网络输出 与真实输出之间的误差

调用损失函数的backwards，会得到反向传播，可以求出每个需要调节的参数，以及每个参数对应的梯度，然后利用优化器，优化器根据梯度，对参数进行调整，达到误差整体降低的目的。

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


dataset = torchvision.datasets.CIFAR10("../data",train=False,transform=torchvision.transforms.ToTensor(),
                                       download=True)
dataloader = DataLoader(dataset, batch_size=1)

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

loss = nn.CrossEntropyLoss ()
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters() ,0.01)
for data in dataloader:
    imgs,targets = data
    outputs = tudui(imgs)
    result_loss = loss(outputs,targets) #计算网络和目标的差距
    optim.zero_grad()         #把网络中每个可调节的参数设为0
    result_loss.backward()     #得到每一个可调节参数对应的梯度
    optim.step()             #调用优化器 对每个参数进行调优

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


dataset = torchvision.datasets.CIFAR10("../data",train=False,transform=torchvision.transforms.ToTensor(),
                                       download=True)
dataloader = DataLoader(dataset, batch_size=1)

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

loss = nn.CrossEntropyLoss ()
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters() ,0.01)
for epoch in range(20):
    running_loss = 0.0
    for data in dataloader:
        imgs,targets = data
        outputs = tudui(imgs)
        result_loss = loss(outputs,targets) #计算网络和目标的差距
        optim.zero_grad()         #把网络中每个可调节的参数设为0
        result_loss.backward()     #得到每一个可调节参数对应的梯度
        optim.step()             #调用优化器 对每个参数进行调优
        running_loss = running_loss + result_loss  #每一轮误差的总和
    print(running_loss)

可以看到每一轮的误差总和在减小

标签：input,nn,output,self,torch,笔记,学习,import,土堆
From： https://blog.csdn.net/weixin_57736375/article/details/140668851