利用GPU训练

今晚开车去看灯啦。很开心
言归正传，有两种方法可以用GPU训练

方法一：

在

上加上

 if torch.cuda.is_available():
            name = name.cuda()

方法二：

先加上这行代码

device = torch.device("cuda")

如果想用cpu，就直接把cuda改成cpu即可
然后还是在

上加上

name = name.to(device)

示例：
因为方法二比较常用，所以我使用方法二来进行演示

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

from model import *
from torch.utils.data import DataLoader
device = torch.device("cuda")
train_data = torchvision.datasets.CIFAR10("data",train=True,transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("data",train=False,transform=torchvision.transforms.ToTensor(),
                                          download=True)
# 计算数据集的长度
train_data_size = len(train_data)
print("训练数据集的长度为{}".format(train_data_size))
test_data_size = len(test_data)
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
star = Star()
star = star.to(device)

#损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 优化器
learning_rate = 1e-2 # 学习效率
optimizer = torch.optim.SGD(star.parameters(),lr=learning_rate)

# 设置训练网络中的一些参数
# 记录训练次数
total_train_step = 0
# 记录测试次数
total_test_step = 0
# 训练的轮次
epoch = 10

# 添加tensorboard
writer = SummaryWriter("logs")

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)
        output = star(imgs)

        #优化器优化模型
        loss = loss_fn(output,targets)
        optimizer.zero_grad()
        loss.backward()
        optimizer.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)

    # 测试步骤开始
    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)
            output = star(imgs)
            loss =loss_fn(output,targets)
            total_test_loss+=loss.item()
            accuracy = (output.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+=1

        # 保存模型
        torch.save(star,"star_{}.pth".format(i))
        print("模型已保存")
writer.close()

注意：

1.GPU训练只有电脑有gpu的情况下才能使用
2.如果没有GPU，但是想用，可以利用谷歌的google colab