小土堆pytorch学习笔记（二十、利用GPU训练1-2）

一、利用gpu训练

就是对网络模型、数据（输入和标注）、损失函数使用gpu训练。

1.1 第一种方式，调用cuda()函数：

import time

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

# from model import *

# 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)

# 查看训练集和验证集的长度
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))

# 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 Cow(nn.Module):
    def __init__(self):
        super(Cow, 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


cow = Cow()
if torch.cuda.is_available():
    cow = cow.cuda()

# 损失函数，使用交叉熵损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()

# 优化器
# 1e-3 = 1 x 10^(-3) = 0.001
learning_rate = 1e-3
optimizer = torch.optim.SGD(cow.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
    cow.train()
    for data in train_dataloader:
        imgs, targets = data
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        outputs = cow(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
        # 设置100次步骤才打印一次，方便查看测试集损失
        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
    # 测试步骤不需要调优，所以使用with torch.no_grad()函数
    cow.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 = cow(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Loss:{}".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

    # 保存每一轮训练的模型
    torch.save(cow, "cow_{}.pth".format(i))
    # 保存方式2 torch.save(cow.state_dict(), "cow_{}.pth".format(i))
    print("模型已保存")
writer.close()

可以使用google colab创建笔记本利用google提供的资源进行gpu训练。

1.2 第二种方式，使用.to()函数

.to(device)
# 表示使用cpu训练
device = torch.device("cpu")
# 表示使用gpu训练
device = torch.device("cuda")
# 表示使用第一张显卡
device = torch.device("cuda:0")
# 表示使用第二张显卡
device = torch.device("cuda:1")

完整代码：

import time

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

# from model import *

# 定义训练的设备
device = torch.device("cuda")
# 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)

# 查看训练集和验证集的长度
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))

# 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 Cow(nn.Module):
    def __init__(self):
        super(Cow, 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


cow = Cow()
cow.to(device)

# 损失函数，使用交叉熵损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn.to(device)
# 优化器
# 1e-3 = 1 x 10^(-3) = 0.001
learning_rate = 1e-3
optimizer = torch.optim.SGD(cow.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
    cow.train()
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = cow(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
        # 设置100次步骤才打印一次，方便查看测试集损失
        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
    # 测试步骤不需要调优，所以使用with torch.no_grad()函数
    cow.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 = cow(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Loss:{}".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

    # 保存每一轮训练的模型
    torch.save(cow, "cow_{}.pth".format(i))
    # 保存方式2 torch.save(cow.state_dict(), "cow_{}.pth".format(i))
    print("模型已保存")
writer.close()