使用GPU训练

GPU使用1

import torch
import torchvision.datasets
from torch.utils.tensorboard import SummaryWriter
import time


# 准备数据集
from torch import nn
from torch.utils.data import DataLoader

import nn_seq

train_data = torchvision.datasets.CIFAR10(root="../dataset", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="../dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=False)
# length长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# print(f'训练数据集的长度为{train_data_size}')
# print(f'测试数据集的长度为{test_data_size}')

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

# 创建网络模型
class MyModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.model = nn.Sequential(
            nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Flatten(),
            nn.Linear(in_features=64*4*4, out_features=64),
            nn.Linear(in_features=64, out_features=10)
        )

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

module = MyModule()
if torch.cuda.is_available():
    module = module.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(module.parameters(), lr=learning_rate)

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

# 添加tensorboard
writer = SummaryWriter("./logs_train")

start_time = time.time()

for i in range(epoch):

    print(f'--------第{i+1}轮训练开始---------')
    # 有特殊层，如dropout时调用
    module.train()
    for data in train_dataloader:
        optimizer.zero_grad()
        imgs, targets = data
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        outputs = module(imgs)
        loss = loss_fn(outputs, targets)
        loss.backward()
        optimizer.step()
        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time - start_time)
            print(f'训练次数{total_train_step}, Loss{loss.item()}')
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤
    # 有特殊层，如dropout时调用
    module.eval()
    total_test_loss = 0
    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()
            outputs = module(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(f'整体验证集上的Loss{total_test_loss}')
    print(f'整体测试集上的正确率{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(module, f'module_{i}.pth')
    print("模型已保存")

writer.close()

GPU使用2

import torch
import torchvision.datasets
from torch.utils.tensorboard import SummaryWriter
import time


# 准备数据集
from torch import nn
from torch.utils.data import DataLoader

import nn_seq

# 定义训练的设备
# device = torch.device("cpu")
# device = torch.device("cuda")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

train_data = torchvision.datasets.CIFAR10(root="../dataset", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="../dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=False)
# length长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# print(f'训练数据集的长度为{train_data_size}')
# print(f'测试数据集的长度为{test_data_size}')

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

# 创建网络模型
class MyModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.model = nn.Sequential(
            nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Flatten(),
            nn.Linear(in_features=64*4*4, out_features=64),
            nn.Linear(in_features=64, out_features=10)
        )

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

module = MyModule()
module = module.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(module.parameters(), lr=learning_rate)

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

# 添加tensorboard
writer = SummaryWriter("./logs_train")

start_time = time.time()

for i in range(epoch):

    print(f'--------第{i+1}轮训练开始---------')
    # 有特殊层，如dropout时调用
    module.train()
    for data in train_dataloader:
        optimizer.zero_grad()
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = module(imgs)
        loss = loss_fn(outputs, targets)
        loss.backward()
        optimizer.step()
        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time - start_time)
            print(f'训练次数{total_train_step}, Loss{loss.item()}')
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤
    # 有特殊层，如dropout时调用
    module.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_data_loader:
            imgs, targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = module(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(f'整体验证集上的Loss{total_test_loss}')
    print(f'整体测试集上的正确率{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(module, f'module_{i}.pth')
    print("模型已保存")

writer.close()

参考地址：https://www.bilibili.com/video/BV1hE411t7RN?p=30