深度学习pytorch代码：利用GPU进行卷积神经网络训练(含代码注释)

GPU训练方法一

   .cuda

可以使用GPU训练的内容：

1. 数据(输入、标签)
2. 损失函数
3. 网络模型

 GPU训练方法二

.to(device)

# 使用cpu训练

device = torch.device("cpu")

#使用GPU训练

torch.device("cuda")

# 指定训练的GPU

torch.device("cuda:0")

model.eval()   # 将模型转化为测试类型

model.train()  #  将模型转化为训练模型

import torch.optim.optimizer
import torchvision
# 准备数据集
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter

from torch.utils.data import DataLoader
import time

train_data = torchvision.datasets.CIFAR10(r"C:\Users\123\Desktop\python4.7\test03\data", train=True, download=True,
                                       transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10(r"C:\Users\123\Desktop\python4.7\test03\data", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())

# 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：{}".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
class LR(nn.Module):

    def __init__(self):
        super(LR, 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


lrp = LR()
if torch.cuda.is_available():
    lrp = lrp.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(lrp.parameters(), lr=Learning_rate)

# 设置训练网络的参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 记录训练轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("./logs_train")
# 记录当前时间
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
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.cuda()
        if torch.cuda.is_available():
            targets = targets.cuda()
            imgs = imgs.cuda()
        outputs = lrp(imgs)
        # 计算预测损失
        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
        # 训练步骤不必每次打印
        if total_train_step % 100 == 0:
            # 记录结束时间
            end_time = time.time()
            print(end_time - start_time)
            print("训练次数：{},loss:{}".format(total_train_step, loss.item()))
            # tensorboard
            writer.add_scalar("train_loss", loss.item(), total_test_step)


    # 使用测试来判断网络是否训练好了
    total_test_loss = 0
    # 整体预测的准确度
    total_acc = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            if torch.cuda.is_available():
                targets = targets.cuda()
                imgs = imgs.cuda()
            outputs = lrp(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            acc = (outputs.argmax(1) == targets).sum()
            total_acc = total_acc + acc
    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_acc/test_data_size))
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    writer.add_scalar("test_acc", total_acc/test_data_size, total_test_step)
    total_test_step = total_test_step + 1
    # 保存模型
    torch.save(lrp, "lrp_{}.pth".format(i))
    print("模型已保存")

writer.close()

# GPU训练方式二
import torch.optim.optimizer
import torchvision
# 准备数据集
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter

from torch.utils.data import DataLoader
import time
# 定义训练的设备
device = torch.device("cuda:0")

# 常用方式
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

train_data = torchvision.datasets.CIFAR10(r"C:\Users\123\Desktop\python4.7\test03\data", train=True, download=True,
                                       transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10(r"C:\Users\123\Desktop\python4.7\test03\data", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())

# 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：{}".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
class LR(nn.Module):

    def __init__(self):
        super(LR, 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


lrp = LR()
lrp = lrp.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(lrp.parameters(), lr=Learning_rate)

# 设置训练网络的参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 记录训练轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("./logs_train")
# 记录当前时间
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
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = lrp(imgs)
        # 计算预测损失
        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
        # 训练步骤不必每次打印
        if total_train_step % 100 == 0:
            # 记录结束时间
            end_time = time.time()
            print(end_time - start_time)
            print("训练次数：{},loss:{}".format(total_train_step, loss.item()))
            # tensorboard
            writer.add_scalar("train_loss", loss.item(), total_test_step)


    # 使用测试来判断网络是否训练好了
    total_test_loss = 0
    # 整体预测的准确度
    total_acc = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = lrp(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            acc = (outputs.argmax(1) == targets).sum()
            total_acc = total_acc + acc
    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_acc/test_data_size))
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    writer.add_scalar("test_acc", total_acc/test_data_size, total_test_step)
    total_test_step = total_test_step + 1
    # 保存模型
    torch.save(lrp, "lrp_{}.pth".format(i))
    print("模型已保存")

writer.close()