P18：利用GPU训练

1、方式1：

找到：

（1）网络模型；

（2）数据（输入、标注）；

（3）损失函数；

调用 .cuda() ，再返回即可。

# 找到网络模型、数据（输入、标注）、损失函数；调用.cuda()，再返回就可以了

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

# from model import *

# 1、准备数据集
train_data = torchvision.datasets.CIFAR10('dataset', train = True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10('dataset', train = False, transform=torchvision.transforms.ToTensor(), download=True)

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

# 2、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)

# 3、搭建神经网络
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = nn.Sequential(
            Conv2d(3, 32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(32, 32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(32, 64, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(1024, 64),
            ReLU(),
            Linear(64, 10),
        )

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

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

# 5、创建损失函数
loss_fn = CrossEntropyLoss()
if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()
# 6、优化器
# learning_rate = 0.01
learning_rata = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr = learning_rata)

# 7、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()
    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(end_time - start_time)
            print('训练次数: {}，loss: {}'.format(total_train_step, loss.item())) # item表示只是数字
            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():
        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accuracy: {}'.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

    # 保存每一轮训练的模型
    torch.save(tudui, 'tudui_{}.pth'.format(i))
    print('模型已保存')

writer.close()

2、方式2：

.to(device)

device = torch.device('cuda:0')

# .to(device)
# device = torch.device('cpu')
# device = torch.device('cuda')
# device = torch.device('cuda:0')

# 找到网络模型、数据（输入、标注）、损失函数；调用.cuda()，再返回就可以了

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

# 定义训练的设备
device = torch.device('cuda:0')
# from model import *

# 1、准备数据集
train_data = torchvision.datasets.CIFAR10('dataset', train = True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10('dataset', train = False, transform=torchvision.transforms.ToTensor(), download=True)

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

# 2、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)

# 3、搭建神经网络
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = nn.Sequential(
            Conv2d(3, 32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(32, 32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(32, 64, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(1024, 64),
            ReLU(),
            Linear(64, 10),
        )

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

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

# 5、创建损失函数
loss_fn = CrossEntropyLoss()
loss_fn = loss_fn.to(device)

# 6、优化器
# learning_rate = 0.01
learning_rata = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr = learning_rata)

# 7、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 = 100

# 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()
    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 += 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())) # item表示只是数字
            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():
        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 += 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accuracy: {}'.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

    # 保存每一轮训练的模型
    torch.save(tudui, 'tudui_{}.pth'.format(i))
    print('模型已保存')

writer.close()