利用GPU训练

方法一

网络模型、数据（输入、标注）以及损失函数.cuda()

点击查看代码

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

from model import *
# 准备数据集
from torch.utils.data import DataLoader
train_data = torchvision.datasets.CIFAR10("./dataset1", train=True, download=True,
                                       transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10("./dataset1", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())
# 数据集长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练集长度：{}".format(train_data_size))
print("测试集长度：{}".format(test_data_size))

# 利用DataLoader加载数据集
train_data_loader = DataLoader(train_data, batch_size=64)
test_data_loader = DataLoader(test_data, batch_size=64)

# 搭建神经网络
class Test(nn.Module):
    def __init__(self):
        super().__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, 1, 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
# 创建网络模型
test = Test()
if torch.cuda.is_available():
    test = test.cuda()

# 创建损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()
# 创建优化器
# 0.01 = 1e-2
learning_rate = 1e-2
optimizer = torch.optim.SGD(test.parameters(), lr=learning_rate)

# 设置训练网络的一些参数
# 训练次数
total_train_step = 0
# 测试次数
total_test_step = 0
# 训练轮数
epoch = 10

writer = SummaryWriter("./log_train")

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

    # 训练步骤
    # 针对特定的层有作用
    # test.train()
    for data in train_data_loader:
        imgs, targets = data
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        output = test(imgs)
        loss = loss_fn(output, 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
    # 针对特定的层有作用
    # test.eval()
    total_test_loss = 0
    # 整体正确的个数
    total_accuracy = 0
    with torch.no_grad():
        for data in test_data_loader:
            imgs, targets = data
            if torch.cuda.is_available():
                imgs = imgs.cuda()
                targets = targets.cuda()
            output = test(imgs)
            loss = loss_fn(output, targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (output.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

    print("整体测试集的loss: {}".format(total_test_loss))
    print("整体测试集的正确率: {}".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(test, "test_{}.pth".format(i))
    print("模型已保存")

writer.close()

方法二

device = torch.device("cuda")

网络模型、数据（输入、标注）以及损失函数.to(device)

点击查看代码

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader
from model import *

device = torch.device("cuda")

# 准备数据集
train_data = torchvision.datasets.CIFAR10("./dataset1", train=True, download=True,
                                       transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10("./dataset1", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())
# 数据集长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练集长度：{}".format(train_data_size))
print("测试集长度：{}".format(test_data_size))

# 利用DataLoader加载数据集
train_data_loader = DataLoader(train_data, batch_size=64)
test_data_loader = DataLoader(test_data, batch_size=64)

# 搭建神经网络
class Test(nn.Module):
    def __init__(self):
        super().__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, 1, 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
# 创建网络模型
test = Test()
test = test.to(device)

# 创建损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 创建优化器
# 0.01 = 1e-2
learning_rate = 1e-2
optimizer = torch.optim.SGD(test.parameters(), lr=learning_rate)

# 设置训练网络的一些参数
# 训练次数
total_train_step = 0
# 测试次数
total_test_step = 0
# 训练轮数
epoch = 10

writer = SummaryWriter("./log_train")

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

    # 训练步骤
    # 针对特定的层有作用
    # test.train()
    for data in train_data_loader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        output = test(imgs)
        loss = loss_fn(output, 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
    # 针对特定的层有作用
    # test.eval()
    total_test_loss = 0
    # 整体正确的个数
    total_accuracy = 0
    with torch.no_grad():
        for data in test_data_loader:
            imgs, targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            output = test(imgs)
            loss = loss_fn(output, targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (output.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

    print("整体测试集的loss: {}".format(total_test_loss))
    print("整体测试集的正确率: {}".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(test, "test_{}.pth".format(i))
    print("模型已保存")

writer.close()