CIFAR10模型训练及GPU加速对比

1.完整的模型训练套路

利用训练集CIFAR10模型进行训练

代码：

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

#准备数据集
train_data = torchvision.datasets.CIFAR10('/content/drive/MyDrive',train=True,
                                          transform=torchvision.transforms.ToTensor(),download=True)
test_data = torchvision.datasets.CIFAR10('/content/drive/MyDrive',train=False,
                                          transform=torchvision.transforms.ToTensor(),download=True)

train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度是：{}".format(train_data_size))
print("测试数据集的长度是：{}".format(test_data_size))

train_dataloader = DataLoader(train_data,batch_size=64)
test_dataloader = DataLoader(test_data,batch_size=64)

#创建网络模型
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(1024,64),
            nn.Linear(64,10)
        )
    def forward(self,x):
        x = self.model(x)
        return x
tudui = Tudui()
#损失函数
loss_fn = nn.CrossEntropyLoss()
#优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(),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
epochs = 10
#添加tensorboard
writer = SummaryWriter('../trains')
start_time = time.time()
for i in range(epochs):
    print("第{}轮训练开始".format(i+1))
    #训练步骤开始
    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+=1
        if total_train_step % 100 ==0:
            end_time = time.time()
            print("此轮时长为：{}".format(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
    total_accuracy = 0
    total_test_loss = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs,targets = data
            outputs = tudui(imgs)
            loss = loss_fn(outputs,targets)
            total_test_loss+=loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            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+=1
    torch.save(tudui,"tudui_{}.pth".format(i))
    print("模型已保存")
writer.close()

结果：

利用tensorboard图形化

可以看见损失在逐渐减少

也可增加正确率，即通过argmax（）与targets中的True和False相加，除以测试机长度

accuracy = (outputs.argmax(1) == targets).sum()
        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))

正确率上升中

2.使用GPU训练

网络模型&& 数据(输入，标注)&&损失函数-> .cuda()

由于我的电脑没有GPU，所以在colab上跑代码

为了比较区别，分别在GPU和CPU版本代码里加入time计时器

GPU代码

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


#准备数据集
train_data = torchvision.datasets.CIFAR10('/content/drive/MyDrive',train=True,
                                          transform=torchvision.transforms.ToTensor(),download=True)
test_data = torchvision.datasets.CIFAR10('/content/drive/MyDrive',train=False,
                                          transform=torchvision.transforms.ToTensor(),download=True)

train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度是：{}".format(train_data_size))
print("测试数据集的长度是：{}".format(test_data_size))

train_dataloader = DataLoader(train_data,batch_size=64)
test_dataloader = DataLoader(test_data,batch_size=64)

#创建网络模型
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(1024,64),
            nn.Linear(64, 10)
        )
    def forward(self,x):
        x = self.model(x)
        return x
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(),learning_rate)

#设置训练网络的一些参数
total_accuracy = 0
#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
epochs = 10
#添加tensorboard
writer = SummaryWriter('../trains')
start_time = time.time()
for i in range(epochs):
    print("第{}轮训练开始".format(i+1))
    #训练步骤开始
    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+=1
        if total_train_step % 100 ==0:
            end_time=time.time()
            print("此轮时长为：{}".format(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
    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+=loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            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+=1
    torch.save(tudui,"tudui_{}.pth".format(i))
    print("模型已保存")
writer.close()