【Pytorch深度学习框架入门】

1.pytorch加载数据

两个有用的工具箱：

help(torch.cuda.is_available) # 对函数进行操作

唤醒指定的python运行环境的命令：

conda activate 环境的名称

Dataset 和 Dataloader 

Dataset：提供一种方式去获取数据及其label

• 如何获取每一个数据及其label
• 告诉我们总共有多少数据

Dataloader ：为后面的网络提供不同的数据形式

from torch.utils.data import Dataset #Dataset数据处理的包
from PIL import Image
import os

#定义数据处理的类
class MyData(Dataset):
    
    #数据地址处理方法
    def __init__(self,root_dir,label_dir):
        self.root_dir = root_dir #读取数据文件的根地址
        self.label_dir = label_dir #读取数据文件的字地址
        self.path = os.path.join(self.root_dir,self.label_dir)# 将根地址和子地址进行拼接
        self.img_path = os.listdir(self.path) #将图片的地址提取出来，并一个个存入到列表中去

    
    #提取每一个图片的信息
    def __getitem__(self, idx):
        img_name = self.img_path[idx] #根据序号从列表中找到相应的图片地址
        img_item_path = os.path.join(self.root_dir,self.label_dir,img_name)# 将根地址与图片地址进行拼接
        img = Image.open(img_item_path) #将地址转换为图片的形式
        label = self.label_dir# 读取标签的地址
        return img,label #返回图片和标签

    #计算数据集的长度
    def __len__(self):
        return len(self.img_path)

root_dir = "dataset/train"
ants_label_dir = "ants"
bees_label_dir = "bees"
ants_dataset = MyData(root_dir,ants_label_dir)
bees_dataset = MyData(root_dir,bees_label_dir)
train_dataset = ants_dataset + bees_dataset

2.TensorBoard的使用

from torch.utils.tensorboard import SummaryWriter
from PIL import  Image
import numpy as np

writer = SummaryWriter("logs")
image_path = "dataset/train/ants/0013035.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)
# writer.add_image("test",img_array,1,dataformats='HWC')# 其中1的作用主要是为了进行步数的设置
# y = x
for i in range(100):
    writer.add_scalar("y=2x",3*i,i)
writer.close()

启动日志的相关命令

tensorboard --logdir=logs --port=6007

3. transfrom的使用

下面图片是transform的图解：

"""
transform的讲解
"""
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms


#python的用法 -》 tensor数据类型
#通过 transform.Totensor去看两个问题
# 1、transform该如何去使用（python）
# 2、为什么我们需要tensor数据类型

# 绝对路径："F:\learn_pytorch\p9_transform.py"
# 相对路径："dataset/train/ants/0013035.jpg"
#为什么不选择使用绝对路径，因为在window系统下，\会被认为是转移字符

img_path = "dataset/train/ants/0013035.jpg"# 读取图片的相对地址
img_path_abs = "F:\learn_pytorch\p9_transform.py"# 读取图片的绝对地址
img = Image.open(img_path)# 打开图片
#print(img)

writer = SummaryWriter("logs") # 创建TensorBoard对象

# 1、transform该如何去使用（python）
tensor_trans = transforms.ToTensor()# 创建一个tensor_trans的图片类型转换工具的对象
tensor_img = tensor_trans(img)# 将img转化成tensor的形式
#print(tensor_img)

writer.add_image("Tensor_img",tensor_img)# 利用TensorBoard展示数据

4.常见的transform

 Python中__call__的用法

class Person:
    def __call__(self,name):
        print("__call__"+"Hello"+name)
    def hello(self,name):
        print("hello"+name)

person = Person()

person("张三")

person.hello("lisi")

Totensor()的使用

#Totensor()的使用
trans_Totensor = transforms.ToTensor()
img_tensor = trans_Totensor(img)
writer.add_image('ToTensor',img_tensor)

Normalize()的使用

print(img_tensor[0][0][0])
trans_norm = transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
img_norm = trans_norm(img_tensor)
print(img_norm[0][0][0])

Resize()的使用

#Resize()
print(img.size)
trans_size = transforms.Resize((512,512))
# img PIL -> resize ->img_resize PIL
img_resize = trans_size(img)
# img_resize PIL -> totensor ->img_resize tensor
img_resize = trans_Totensor(img_resize)
writer.add_image('Resize',img_resize,0)
print(img_resize)

Compose()的使用

#Compose() -resize -2
trans_resize_2 = transforms.Resize(512)
# PIL -> PIL -> tensor
trans_compose = transforms.Compose([trans_resize_2,trans_Totensor])
img_resize_2 = trans_compose(img)
writer.add_image('Compose',img_resize_2)

RandomCrop()的使用

#RandomCrop()
trans_random = transforms.RandomCrop((500,20))

trans_compose_2 = transforms.Compose([trans_random,trans_Totensor])

for i in range(10):
    img_crop = trans_compose_2(img)
    writer.add_image('RandomCrop',img_crop,i)

 4.torchvision中数据集的使用

进入pytorch的官网

依次进入到Docs->torchvision->dataset

 相关代码：

import torchvision
from torch.utils.tensorboard import SummaryWriter

dataset_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])
train_set = torchvision.datasets.(root="./dataset1",train=True,download=True,transform=dataset_transform)#构建训练集
test_set = torchvision.datasets.CIFAR10(root="./dataset1",train=False,download=True,transform=dataset_transform)#构建测试集

'''
print(test_set[0])
print(test_set.classes)
img,target = test_set[0]
print(img)
print(target)
img.show()
'''
# print(test_set[0])
writer = SummaryWriter('p10')
# writer.add_image()
for i in range(10):
    img,target = test_set[i]
    writer.add_image('test_set',img,i)
writer.close()

5.dataloader的使用

 

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

test_data = torchvision.datasets.CIFAR10(root="./dataset1",train=True,transform=torchvision.transforms.ToTensor(),download=True)

test_loader = DataLoader(dataset=test_data,batch_size=64,shuffle=False,num_workers=0,drop_last=False)

#测试数据集里面的第一章图片及target
img,target = test_data[0]
print(img.shape)
print(target)

writer = SummaryWriter('dataloader')
for epoch in range(2):#进行两轮
    step = 0
    for data in test_loader:
        imgs,targets = data
        writer.add_images(f"Epoch{epoch}",imgs,step)
        step = step + 1
        # print(imgs.shape)
        # print(target)
print("读取结束")
writer.close()

 6.神经网络的基本骨架-nn.Mouble的使用

 

import torch
from torch import nn


class Tudui(nn.Module):

    def __init__(self) -> None:
        super().__init__()

    def forward(self,input):
        output = input + 1
        return output

tutui = Tudui()
x = torch.tensor(1.0)
output = tutui(x)
print(output)

 7.卷积操作

需要重点学会的是：Conv2d

对应位置相乘，然后加在一起

 

 注意padding填充的全部为0。

 需要注意以上的参数的要求：

import torch
import torch.nn.functional as F
#输入
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]])
#卷积核
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)

output1= F.conv2d(input,kernel,stride=1)
print(output1)
output2 = F.conv2d(input,kernel,stride=2)
print(output2)
output3 = F.conv2d(input,kernel,stride=1,padding=1)
print(output3)

 8.神经网络-卷积层

 

 当out_channel = 2的时候，此时会设置2个卷积核

import torch
import torchvision

#加载测试集
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(root="./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)

dataloader = DataLoader(dataset,batch_size=64,num_workers=0)

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)

    def forward(self,x):
        x = self.conv1(x)
        return x
tudui = Tudui()
print(tudui)

writer = SummaryWriter('./logs')
step = 0
for data in dataloader:
    imgs,targets = data
    ouput = tudui(imgs)
    print(imgs.shape)
    print(ouput.shape)
    writer.add_images("input",imgs,step)
    ouput = torch.reshape(ouput, (-1, 3, 30, 30))  # ->[xxx,3,30,30],3是通道数减少，使得xxx的batchsize变大
    writer.add_images("ouput",ouput,step)
    step = step + 1
print("over")

  9.神经网络-最大池化的使用

 

 

 

 

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.float)

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

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



    def forward(self,input):
        output = self.maxpool(input)
        return output
tudui = Tudui()
output = tudui(input)
print(output)

 最大池化的作用：就是压缩。

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

dataloader = DataLoader(dataset,batch_size=64,shuffle=True)
'''
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.float)

input = torch.reshape(input,(-1,1,5,5))
'''
class Tudui(nn.Module) :
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool = MaxPool2d(kernel_size=3,ceil_mode=False)



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

tudui = Tudui()
writer = SummaryWriter("logs")
step = 0
for data in dataloader:
    imgs,target = data
    writer.add_images("imgs",imgs,step)
    print(imgs.shape)
    output = tudui(imgs)
    writer.add_images("maxpool",output,step)
    print(output.shape)
    step = step + 1

writer.close()
print("over")

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

10.神经网络-非线性激活

inplace参数的讲解

'''
ReLU
'''
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)

'''
Sigmoid
'''
import torch
import torchvision.datasets
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(root="./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.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
    print(imgs.shape)
    writer.add_images("imgs",imgs,step)
    output = tudui(imgs)
    print(output.shape)
    writer.add_images("Sigmod",output,step)

writer.close()

11.神经网络-线性层及其它层的介绍 

 线性层

"""
vgg16
"""
import torch
import torchvision.datasets
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)

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,tragets = data
    print(imgs.shape)
    #writer.add_images("imgs",imgs,step)
    #output = torch.reshape(imgs,(1,1,1,-1))
    output = torch.flatten(imgs)
    print(output.shape)
    output = tudui(output)
    print(output.shape)
    #writer.add_images("linear",output,step)
    #step += 1

#writer.close()

12.神经网络-搭建小实战和Sequential的使用

 CIFAR 10 model结构

 

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


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)

        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.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)
        x = self.model1(x)
        return x

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


writer = SummaryWriter("logs_seq")
writer.add_graph(tudui,input)
writer.close()

13.损失函数

 

'''
nn.loss
'''

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))
targets = torch.reshape(targets,(1,1,1,3))

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

print(result)

'''
nn.MSEloss
'''

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

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))
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)

'''
nn.CrossEntropyLoss
'''

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

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))
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)

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.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)

        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.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)
        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)
    result_loss.backward()
    print("ok")
    print(result_loss)
    print(outputs)
    print(targets)

14.优化器

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.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)

        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.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)
        x = self.model1(x)
        return x
loss = nn.CrossEntropyLoss()
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters(),lr = 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)# 计算损失
        optim.zero_grad()# 梯度清零
        result_loss.backward()# 反向传播，求出每个参数的梯度
        optim.step() #对权重进行更新
        running_loss = running_loss + result_loss
    print(running_loss)

15.现有模型的使用和修改

import torchvision

# train_data = torchvision.datasets.ImageNet("./dataset",split='train',download=True,
#                                            transform=torchvision.transforms.ToTensor())
from torch import nn

vgg16_false = torchvision.models.vgg16(pretrained=False)
vgg16_true = torchvision.models.vgg16(pretrained=True)
print("ok")
print(vgg16_true)


train_data = torchvision.datasets.CIFAR10('./data',train=True,transform=torchvision.transforms.ToTensor(),
                                          download=True)
# 修改vgg16网络模型的结构
vgg16_true.classifier.add_module('add_liner',nn.Linear(1000,10))
print(vgg16_true)
print(vgg16_false)
vgg16_false.classifier[6] = nn.Linear(4096,10)
print(vgg16_false)

16.网络模型的保存与读取

 

自己定义模型

from torch import nn


class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.conv1 = nn.Conv2d(3,64,kernel_size=3)

    def forward(self,x):
        x = self.conv1(x)
        return x

保存模型

import torch
import torchvision

vgg16 = torchvision.models.vgg16(pretrained=False) #加载vgg16初始的模型

#保存方式1
torch.save(vgg16,"vgg16_method1.pth")

import torch
import torchvision
from torch import nn
from Tudui import Tudui
# vgg16 = torchvision.models.vgg16(pretrained=False) #加载vgg16初始的模型
#
# #保存方式1 模型的结构+模型的参数
# torch.save(vgg16,"vgg16_method1.pth")
#
# #保存方式2 模型的参数（官方的推荐）保存为字典的形式
# torch.save(vgg16.state_dict(),"vgg16_method2.pth")

#陷阱

# class Tudui(nn.Module):
#     def __init__(self):
#         super(Tudui, self).__init__()
#         self.conv1 = nn.Conv2d(3,64,kernel_size=3)
#
#     def forward(self,x):
#         x = self.conv1(x)
#         return x
tudui = Tudui()

torch.save(tudui,"tudui_method1.pth")
print("over")

加载模型

import torch
import torchvision

vgg16 = torchvision.models.vgg16(pretrained=False) #加载vgg16初始的模型

#保存方式1
torch.save(vgg16,"vgg16_method1.pth")

"""
加载模型
"""
import torch
#保存方式1的加载模型的方法
import torchvision

# model = torch.load("vgg16_method1.pth")
#print(model)

#方式2的加载模型的方法
# # model = torch.load("vgg16_method2.pth")
# print(model)



vgg16 = torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict((torch.load("vgg16_method2.pth")))
# print(vgg16)
#陷阱
model = torch.load("tudui_method1.pth")
print(model)

17.完整的模型训练的套路

 定义网络模型Model.py

#搭建神经网络
from torch import nn


class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        #使用序列化的方法更新神经网络的各个层
        self.model = nn.Sequential(
            nn.Conv2d(3,32,kernel_size=5,stride=1,padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Conv2d(32,32,kernel_size=5,stride=1,padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32,64,kernel_size=5,stride=1,padding=2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn. Linear(64*4*4,64),
            nn.Linear(64,10)
        )

#定义前向传播
    def forward(self,x):
        x = self.model(x)
        return x

完整的模型训练套路train.py

"""
完整的模型训练的套路
"""

#准备数据集
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from Model import Tudui

train_data = torchvision.datasets.CIFAR10("./data",
                                          train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("./data",
                                          train=False,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)

#查看训练集和测试集有多少张
#length 长度
train_data_size = len(train_data) #训练集的长度
test_data_size = len(test_data) #测试集的长度
print(f"训练集的长度为{train_data_size}\n")
print(f"测试集的长度为{test_data_size}\n")

# 利用DataLoader 来加载数据集
train_dataloader = DataLoader(train_data,batch_size=64)
test_dataloader = DataLoader(test_data,batch_size=64)

#主函数
if __name__ == '__main__':
    # 创建网络模型
    tudui = Tudui()

    #小测试
    input = torch.ones((64,3,32,32))
    output = tudui(input)
    print(output.shape)
    """
    torch.Size([64, 10])
    64是代表64张照片
    10是代表10个类别，每张图片10各类别上分别的概率
    """

    # 损失函数
    loss_fn = nn.CrossEntropyLoss()

    #学习速率
    #1e-2=1x10^(-2)
    learning_rate = 1e-2

    # 优化器
    optimizer = torch.optim.SGD(tudui.parameters(),lr = learning_rate,)

    #设置训练网络的一些参数
    total_train_step = 0 #记录训练的次数
    total_test_step = 0 #记录测试的次数
    #训练的次数
    epoch = 10
    #添加tensorboard
    writer = SummaryWriter("logs_train")

    for i  in range(epoch):
        print(f"------第{i+1}轮训练开始------")

        # 训练步骤开始
        tudui.train()
        for data in train_dataloader:
            imgs,targets = data
            outputs = tudui(imgs)
            loss = loss_fn(outputs,targets)

            #优化器的调优
            optimizer.zero_grad()# 梯度清零
            loss.backward()# 反向传播
            optimizer.step()# 更新优化参数

            total_train_step = total_train_step + 1 #训练次数加1
            if total_train_step % 100 == 0:# 每个一百次输出一次训练的结果
                print(f"训练次数：{total_train_step},Loss：{loss.item()}") #记录每次训练的损失结果,item()主要就是把loss转化为真实的数，其实转化不转化都行的
                writer.add_scalar("train_loss",loss.item(),total_train_step)

        #测试步骤开始
        tudui.eval()
        total_test_loss = 0
        total_accuracy = 0
        with torch.no_grad():#防止调优，测试时不需要进行调优
            for data in test_dataloader:
                imgs , targets = data
                outputs = tudui(imgs)
                loss = loss_fn(outputs,targets)
                total_test_loss = total_test_loss + loss

                #计算整体的正确率
                accuracy = (outputs.argmax(1) == targets).sum()
                total_accuracy = total_accuracy + accuracy
            print(f"整体测试集上的正确率{total_accuracy/test_data_size}")
            print(f"整体测试集上的Loss：{total_test_loss}")
            writer.add_scalar("test_loss",total_test_loss,total_test_step)
            writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step)
            total_test_step = total_test_step + 1

        #保存模型
        torch.save(tudui,f"tudui_{i}.ph")
        #torch.save(tudui.state_dict(),f"tudui_{i}.ph")
        print("模型已保存")

    writer.close()

18.利用GPU进行训练

"""
完整的模型训练的套路
"""

#准备数据集
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time

from Model import Tudui

train_data = torchvision.datasets.CIFAR10("./data",
                                          train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("./data",
                                          train=False,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)

#查看训练集和测试集有多少张
#length 长度
train_data_size = len(train_data) #训练集的长度
test_data_size = len(test_data) #测试集的长度
print(f"训练集的长度为{train_data_size}\n")
print(f"测试集的长度为{test_data_size}\n")

# 利用DataLoader 来加载数据集
train_dataloader = DataLoader(train_data,batch_size=64)
test_dataloader = DataLoader(test_data,batch_size=64)

#主函数
if __name__ == '__main__':
    # 创建网络模型
    tudui = Tudui()
    if torch.cuda.is_available():
        tudui = tudui.cuda()

    #小测试

    input = torch.ones((64,3,32,32))
    device = torch.device('cuda:0') #将tensor.cpu类型的数据转化为tensor.gpu类型的数据
    input = input.to(device)
    output = tudui(input)
    print(output.shape)
    """
    torch.Size([64, 10])
    64是代表64张照片
    10是代表10个类别，每张图片10各类别上分别的概率
    """

    # 损失函数
    loss_fn = nn.CrossEntropyLoss()
    if torch.cuda.is_available():
        loss_fn = loss_fn.cuda()

    #学习速率
    #1e-2=1x10^(-2)
    learning_rate = 1e-2

    # 优化器
    optimizer = torch.optim.SGD(tudui.parameters(),lr = learning_rate,)

    #设置训练网络的一些参数
    total_train_step = 0 #记录训练的次数
    total_test_step = 0 #记录测试的次数
    #训练的次数
    epoch = 10
    #添加tensorboard
    writer = SummaryWriter("logs_train")

    start_time = time.time() #开始训练的时间
    for i  in range(epoch):
        print(f"------第{i+1}轮训练开始------")

        # 训练步骤开始
        tudui.train()
        for data in train_dataloader:
            imgs,targets = data
            if torch.cuda.is_available():
                imgs = imgs.cuda()
                targets = targets.cuda()
            outputs = tudui(imgs)
            loss = loss_fn(outputs,targets)

            #优化器的调优
            optimizer.zero_grad()# 梯度清零
            loss.backward()# 反向传播
            optimizer.step()# 更新优化参数

            total_train_step = total_train_step + 1 #训练次数加1
            if total_train_step % 100 == 0:# 每个一百次输出一次训练的结果
                end_time = time.time() #结束时间
                print(end_time - start_time) #计算100次训练的间隔的时间
                print(f"训练次数：{total_train_step},Loss：{loss.item()}") #记录每次训练的损失结果,item()主要就是把loss转化为真实的数，其实转化不转化都行的
                writer.add_scalar("train_loss",loss.item(),total_train_step)

        #测试步骤开始
        tudui.eval()
        total_test_loss = 0
        total_accuracy = 0
        with torch.no_grad():#防止调优，测试时不需要进行调优
            for data in test_dataloader:
                imgs , targets = data
                if torch.cuda.is_available():
                    imgs = imgs.cuda()
                    targets = targets.cuda()
                outputs = tudui(imgs)
                loss = loss_fn(outputs,targets)
                total_test_loss = total_test_loss + loss

                #计算整体的正确率
                accuracy = (outputs.argmax(1) == targets).sum()
                total_accuracy = total_accuracy + accuracy
            print(f"整体测试集上的正确率{total_accuracy/test_data_size}")
            print(f"整体测试集上的Loss：{total_test_loss}")
            writer.add_scalar("test_loss",total_test_loss,total_test_step)
            writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step)
            total_test_step = total_test_step + 1

        #保存模型
        torch.save(tudui,f"tudui_{i}.ph")
        #torch.save(tudui.state_dict(),f"tudui_{i}.ph")
        print("模型已保存")

    writer.close()

"""
完整的模型训练的套路
"""

#准备数据集
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time

from Model import Tudui

#定义训练的设备
# device = torch.device("cuda:0")
device =  torch.device("cuda" if torch.cuda.is_available() else "cpu")

train_data = torchvision.datasets.CIFAR10("./data",
                                          train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("./data",
                                          train=False,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)

#查看训练集和测试集有多少张
#length 长度
train_data_size = len(train_data) #训练集的长度
test_data_size = len(test_data) #测试集的长度
print(f"训练集的长度为{train_data_size}\n")
print(f"测试集的长度为{test_data_size}\n")

# 利用DataLoader 来加载数据集
train_dataloader = DataLoader(train_data,batch_size=64)
test_dataloader = DataLoader(test_data,batch_size=64)

#主函数
if __name__ == '__main__':
    # 创建网络模型
    tudui = Tudui()
    tudui = tudui.to(device)


    #小测试

    input = torch.ones((64,3,32,32))
    input = input.to(device)
    output = tudui(input)
    print(output.shape)
    """
    torch.Size([64, 10])
    64是代表64张照片
    10是代表10个类别，每张图片10各类别上分别的概率
    """

    # 损失函数
    loss_fn = nn.CrossEntropyLoss()
    loss_fn = loss_fn.to(device)

    #学习速率
    #1e-2=1x10^(-2)
    learning_rate = 1e-2

    # 优化器
    optimizer = torch.optim.SGD(tudui.parameters(),lr = learning_rate,)

    #设置训练网络的一些参数
    total_train_step = 0 #记录训练的次数
    total_test_step = 0 #记录测试的次数
    #训练的次数
    epoch = 10
    #添加tensorboard
    writer = SummaryWriter("logs_train")

    start_time = time.time() #开始训练的时间
    for i  in range(epoch):
        print(f"------第{i+1}轮训练开始------")

        # 训练步骤开始
        tudui.train()
        for data in train_dataloader:
            imgs,targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = tudui(imgs)
            loss = loss_fn(outputs,targets)

            #优化器的调优
            optimizer.zero_grad()# 梯度清零
            loss.backward()# 反向传播
            optimizer.step()# 更新优化参数

            total_train_step = total_train_step + 1 #训练次数加1
            if total_train_step % 100 == 0:# 每个一百次输出一次训练的结果
                end_time = time.time() #结束时间
                print(end_time - start_time) #计算100次训练的间隔的时间
                print(f"训练次数：{total_train_step},Loss：{loss.item()}") #记录每次训练的损失结果,item()主要就是把loss转化为真实的数，其实转化不转化都行的
                writer.add_scalar("train_loss",loss.item(),total_train_step)

        #测试步骤开始
        tudui.eval()
        total_test_loss = 0
        total_accuracy = 0
        with torch.no_grad():#防止调优，测试时不需要进行调优
            for data in test_dataloader:
                imgs , targets = data
                imgs = imgs.to(device)
                targets = targets.to(device)
                outputs = tudui(imgs)
                loss = loss_fn(outputs,targets)
                total_test_loss = total_test_loss + loss

                #计算整体的正确率
                accuracy = (outputs.argmax(1) == targets).sum()
                total_accuracy = total_accuracy + accuracy
            print(f"整体测试集上的正确率{total_accuracy/test_data_size}")
            print(f"整体测试集上的Loss：{total_test_loss}")
            writer.add_scalar("test_loss",total_test_loss,total_test_step)
            writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step)
            total_test_step = total_test_step + 1

        #保存模型
        torch.save(tudui,f"tudui_{i}.ph")
        #torch.save(tudui.state_dict(),f"tudui_{i}.ph")
        print("模型已保存")

    writer.close()

如果没有GPU怎么办呢？

没有GPU的话，我们可以使用谷歌提供colab，可能访问这个网站的话需要进行科学上网

 19.完整的模型验证套路

利用已经训练好的模型，然后给它提供测试

# -*- coding: utf-8 -*-
# 作者：小土堆
# 公众号：土堆碎念
import torch
import torchvision
from PIL import Image
from torch import nn

image_path = "../imgs/airplane.png"
image = Image.open(image_path)
print(image)
image = image.convert('RGB')
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)),
                                            torchvision.transforms.ToTensor()])

image = transform(image)
print(image.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64*4*4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        x = self.model(x)
        return x

model = torch.load("tudui_29_gpu.pth", map_location=torch.device('cpu'))
print(model)
image = torch.reshape(image, (1, 3, 32, 32))
model.eval()
with torch.no_grad():
    output = model(image)
print(output)

print(output.argmax(1))