PyTorch深度学习快速入门教程

1、Pytorch加载数据

Dataset主要是提供一种方式去获取数据及其对应的真实label，这个需要我们去写。需要实现的功能是：1）如何获取每一个数据及其label，2）告诉我们总共有多少个数据
Dataloader为后面的网络提供不同的数据形式。

from torch.utils.data import Dataset
from PIL import Image
import os

class MyData(Dataset):

    def __init__(self,root_dir,label_dir):
        # self 相当于指定了一个类当中的全局变量
        self.root_dir = root_dir
        self.label_dir = label_dir
        self.path = os.path.join(self.root_dir,self.label_dir)
        self.img_path = os.listdir(self.path)

    def __getitem__(self, idx):
        img_name = self.img_path[idx]
        img_item_path = os.path.join(self.root_dir,self.label_dir,img_name)
        img = Image.open(img_item_path)
        label = self.label_dir
        return img, label

    def __len__(self):
        return len(self.img_path)


root_dir = "dataset/train"
ants_label_dir = "ants"
ants_dataset = MyData(root_dir,ants_label_dir)

bees_label_dir = "bees"
bees_dataset = MyData(root_dir,bees_label_dir)

train_dataset = ants_dataset+bees_dataset

2、Tensorbord的使用

首先通过指令安装pip install tensorboard。

显示tensorboard界面，有两种方式，默认端口和指定端口。


关于tensorboard的小练习。

from torch.utils.tensorboard import SummaryWriter

writer = SummaryWriter("logs")

for i in range(100):
    writer.add_scalar("y=2x",3*i,i)

writer.close()

当遇到上述问题的时候可以采用下面的方式解决。

采用opencv读入的图像是numpy中的数组的数据类型，安装指令pip install opencv-python 。
也可以采用numpy进行数据的转换，如图所示。


tensorboard显示图片代码。

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

writer = SummaryWriter("logs")
image_path = "data/train/bees_image/16838648_415acd9e3f.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,2,dataformats='HWC')
for i in range(100):
    writer.add_scalar("y=2x",3*i,i)

writer.close()

3、Transforms的使用

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transforms.ToTensor去看两个问题

# 2、为什么我们需要Tensor数据类型

# 绝对路径: D:\shanda_python\2022_pytorch\Learning\dataset\train\ants_image\0013035.jpg
# 相对路径: dataset/train/ants_image/0013035.jpg
img_path = "dataset/train/ants_image/0013035.jpg"
img = Image.open(img_path)
writer = SummaryWriter("logs")

# 1、transforms该如何使用（python）
tensor_trans = transforms.ToTensor() # 这里返回的是一个ToTensor的对象
tensor_img = tensor_trans(img) # 将PIL类型转换成Tensor
print(tensor_img.shape)
writer.add_image("Tensor_img",tensor_img)
writer.close()

4、常见的Transforms

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

writer = SummaryWriter("logs")
img = Image.open("images/img.png")
print(img)

# ToTensor--数据由PIL转换成tensor
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
writer.add_image("ToTensor",img_tensor)

# Normalize--归一化，设置均值方差
# 计算公式： output[channel] = (input[channel] - mean[channel]) / std[channel]
print(img_tensor[0][0][0])
trans_norm = transforms.Normalize([3,2,1,5],[2,3,8,7]) # 我这里读入的图像是四个通道的，RGBA
img_norm = trans_norm(img_tensor)
print(img_norm[0][0][0])
writer.add_image("Normalize",img_norm,2)

# Resize
print(img.size)
trans_resize = transforms.Resize((512,512))
# img PIL->resize->img_resize PIL
img_resize = trans_resize(img)
# img_resize PIL -> totensor -> img_resize tensor
img_resize = trans_totensor(img_resize)
writer.add_image("Resize",img_resize,0)
print(img_resize.shape)

# Compose - resize - 2 将两种变换组合在一起使用
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("Resize",img_resize_2,1)

#
trans_random = transforms.RandomCrop((500,600))
trans_compose2 = transforms.Compose([trans_random,trans_totensor])
for i in range(10):
    img_crop = trans_compose2(img)
    writer.add_image("RandomCrop",img_crop,i)

writer.close()

小结：多从官方文档进行各个函数的学习和使用。

5、torchvision中的数据集使用

import torchvision
from torch.utils.tensorboard import SummaryWriter

# 设置数据的转化，这里只是将PIL-》Tensor
dataset_tranform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])
# 转化成Tensor之前
train_set = torchvision.datasets.CIFAR10(root="./dataset",train=True,download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset",train=False,download=True)

print(test_set[0])
print(test_set.classes)
img, target = test_set[0]
print(img)
print(target)
print(test_set.classes[target])
img.show()

# 转化成Tensor之后
train_set = torchvision.datasets.CIFAR10(root="./dataset",train=True,transform=dataset_tranform,download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset",train=False,transform=dataset_tranform,download=True)

# print(test_set[0])
writer = SummaryWriter("P14")
for i in range(10):
    img, target = test_set[i]
    writer.add_image("test_set",img,i)

writer.close()

6、DataLoader的使用

DataLoader的主要功能是用来加载数据集，加载前面讲过的dataset，分批次送入模型 中。

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

test_set = torchvision.datasets.CIFAR10(root="./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)

# shuffle:是否打乱数据，如果不打乱，设置为False，如果打乱，设置为True
# drop_last: 最后不能成为一个batch的是否丢弃，如果不丢弃，设置为False，如果丢弃，设置为True
test_loader = DataLoader(dataset=test_set,batch_size=64,shuffle=False,num_workers=0,drop_last=False)

# 测试数据集中第一张图片及target
img, target = test_set[0]
print(img.shape)
print(target)

writer = SummaryWriter("P15_dataloader")

for epoch in range(2):
    step = 0
    for data in test_loader:
        imgs, targets = data
        # print(imgs.shape)
        # print(targets)
        writer.add_images("Epoch: {}".format(epoch),imgs,step)
        step = step + 1

writer.close()

7、神经网络的基本骨架—nn.module

自己创建一个简单的网络模型。

import torch
from torch import nn

class Tudui(nn.Module):
    def __init__(self):
        super().__init__()

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

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

8、卷积操作

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]])

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)

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

9、神经网络—卷积层

10、神经网络—池化层的使用

import torch
from torch import nn
from torch.nn import MaxPool2d
import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

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

dataloader = DataLoader(dataset,batch_size=64)

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

# 构建了一个神经网络
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()
# output = tudui(input)
# print(output)
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()

11、神经网络—非线性激活

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

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

dataloader = DataLoader(dataset,batch_size=64)
# 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()
        self.sigmoid1 = Sigmoid()

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

tudui = Tudui()
# output = tudui(input)
# print(output)
writer = SummaryWriter("../logs_relu")
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+=1

writer.close()

12、神经网络—线性层及其他层介绍

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

dataset = torchvision.datasets.CIFAR10(root="../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()

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)

13、神经网络—搭建小实战和Sequential

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

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

引入Sequential之后代码更加简洁了。

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

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui,self).__init__()
        self.mode1 = 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.mode1(x)
        return x

tudui = Tudui()
print(tudui)
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)
# 可视化这个网络模型
writer = SummaryWriter("../logs_seq")
writer.add_graph(tudui,input)
writer.close()

14、损失函数与反向传播

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)
print(result)

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

15、优化器

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

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

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui,self).__init__()
        self.mode1 = 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.mode1(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)
        optim.zero_grad()
        result_loss.backward()
        optim.step()
        running_loss += result_loss
        # print(outputs)
        # print(result_loss)
    print(running_loss)

16、现有网络模型的使用及修改

import torchvision
from torch import nn

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

print(vgg16_true)

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

# 在vgg16网络模型上添加一个线性层
vgg16_true.classifier.add_module('add_linear',nn.Linear(1000,10))
print(vgg16_true)

print(vgg16_false)
vgg16_false.classifier[6] = nn.Linear(4096,10)
print(vgg16_false)

17、网络模型的保存与读取

import torch
import torchvision

vgg16 = torchvision.models.vgg16()
# 保存方式1—保存模型结构和模型参数
torch.save(vgg16,"vgg16_method1.pth")

# 保存方式2—模型参数（官方推荐）
torch.save(vgg16.state_dict(),"vgg16_method2.pth")

import torch
import torchvision

# 方式1-》保存方式1，加载模型
model = torch.load("vgg16_method1.pth")
print(model)

# 方式2-》保存方式2，加载模型
model = torch.load("vgg16_method2.pth")
print(model) # 输出只是参数
vgg16 = torchvision.models.vgg16()
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
print(vgg16) # 将参数送入到模型中

18、完整的模型训练套路

train.py

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

from model import *
from torch import nn
from torch.utils.data import DataLoader
'''
完整的模型训练套路
'''

# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="../dataset",train=True,transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="../dataset",train=False,transform=torchvision.transforms.ToTensor(),
                                         download=True)
# length长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size = 10,训练数据集的长度为：10
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度：{}".format(test_data_size))

# 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)

# 创建网络模型
tudui = Tudui()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10

# 添加tensorboard
writer = SummaryWriter("../logs_train")

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

    # 训练步骤开始
    tudui.train() # 设置网络为训练阶段
    for data in train_dataloader:
        imgs, targets = data
        outputs = tudui(imgs)
        loss = loss_fn(outputs,targets)

        # 优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            print("训练次数：{}，Loss：{}".format(total_train_step,loss.item()))
            writer.add_scalar("train_loss",loss.item(),total_train_step)
    # 测试步骤开始
    tudui.eval()# 设置网络为测试阶段
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = tudui(imgs)
            loss = loss_fn(outputs,targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

    print("整体测试集上的Loss:{}".format(total_test_loss))
    print("整体测试集上的正确率:{}".format(total_accuracy/test_data_size))
    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

    torch.save(tudui,"tudui_{}.pth".format(i+1))
    torch.save(tudui.state_dict(),"tudui_{}".format(i+1))
    print("模型已保存！")

writer.close()

model.py

import torch
from torch import nn

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

if __name__ == '__main__':
    tudui = Tudui()
    input = torch.ones((64,3,32,32))
    output = tudui(input)
    print(output.shape)

结果：

19、利用GPU训练

如果电脑没有GPU可以通过google colab来使用GPU训练，新建笔记本放入代码就可以。


代码1：

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

from torch import nn
from torch.utils.data import DataLoader
import time
'''
完整的模型训练套路
'''

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

# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="../dataset",train=True,transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="../dataset",train=False,transform=torchvision.transforms.ToTensor(),
                                         download=True)
# length长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size = 10,训练数据集的长度为：10
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度：{}".format(test_data_size))

# 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)

# 创建网络模型
tudui = Tudui()
if torch.cuda.is_available():
    tudui = tudui.cuda()

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

# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10

# 添加tensorboard
writer = SummaryWriter("../logs_train")
start_time = time.time()
for i in range(epoch):
    print("------第{}轮训练开始------".format(i+1))

    # 训练步骤开始
    tudui.train() # 设置网络为训练阶段
    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)

        # 优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time-start_time)
            print("训练次数：{}，Loss：{}".format(total_train_step,loss.item()))
            writer.add_scalar("train_loss",loss.item(),total_train_step)
    # 测试步骤开始
    tudui.eval()# 设置网络为测试阶段
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        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.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

    print("整体测试集上的Loss:{}".format(total_test_loss))
    print("整体测试集上的正确率:{}".format(total_accuracy/test_data_size))
    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

    torch.save(tudui,"tudui_{}.pth".format(i+1))
    torch.save(tudui.state_dict(),"tudui_{}".format(i+1))
    print("模型已保存！")

writer.close()

代码2：

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

from torch import nn
from torch.utils.data import DataLoader
import time
'''
完整的模型训练套路
'''

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

# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="../dataset",train=True,transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="../dataset",train=False,transform=torchvision.transforms.ToTensor(),
                                         download=True)
# 定义训练的设备
device = torch.device("cuda:0")
# device = torch.device("cuda")
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

# length长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size = 10,训练数据集的长度为：10
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度：{}".format(test_data_size))

# 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)

# 创建网络模型
tudui = Tudui()
tudui = tudui.to(device)

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

# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10

# 添加tensorboard
writer = SummaryWriter("../logs_train")
start_time = time.time()
for i in range(epoch):
    print("------第{}轮训练开始------".format(i+1))

    # 训练步骤开始
    tudui.train() # 设置网络为训练阶段
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = tudui(imgs)
        loss = loss_fn(outputs,targets)

        # 优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time-start_time)
            print("训练次数：{}，Loss：{}".format(total_train_step,loss.item()))
            writer.add_scalar("train_loss",loss.item(),total_train_step)
    # 测试步骤开始
    tudui.eval()# 设置网络为测试阶段
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        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.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

    print("整体测试集上的Loss:{}".format(total_test_loss))
    print("整体测试集上的正确率:{}".format(total_accuracy/test_data_size))
    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

    torch.save(tudui,"tudui_{}.pth".format(i+1))
    torch.save(tudui.state_dict(),"tudui_{}".format(i+1))
    print("模型已保存！")

writer.close()

20、完整的模型验证套路

import torch
from PIL import Image
import torchvision
from torch import nn

image_path = "../images/dog.png"
image = Image.open(image_path)
print(image)

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_30.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))

学习链接

1. 代码：https://github.com/xiaotudui/pytorch-tutorial
2. 蚂蚁蜜蜂/练手数据集：链接: https://pan.baidu.com/s/1jZoTmoFzaTLWh4lKBHVbEA 密码: 5suq
3. 课程资源：https://pan.baidu.com/s/1CvTIjuXT4tMonG0WltF-vQ?pwd=jnnp 提取码:jnnp
4. pytorch官网