Pytorch使用GPU或者CPU训练的切换

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

本文链接： https://blog.csdn.net/Elvirangel/article/details/102517388

代码示例转自： pytorch tips：使pytorch代码在不改动情况在有GPU自动在GPU运行

1. 定义训练方式：

方法一：

device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model=model.to(device)
x=x.to(device)
y=y.to(device)

方法二：

model=model.cuda()
x=x.cuda()
y=y.cuda()

 推荐使用方法一：

#gpu or not
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

2. 训练代码相应修改：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import argparse
import torch.utils.data
from resnet import ResNet18
 
#gpu or not
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
parser = argparse.ArgumentParser(description='Python CIFAR10 Training')
parser.add_argument('--outf', default='./model', help='folder to output images and model checkpoints')
parser.add_argument('--net', default=',.model/Resnet18.pth', help='path to net(to continue training)')
args = parser.parse_args()
 
#超参数设置
EPOCH = 135
pre_epoch = 0
BATCH_SIZE = 128
LR = 0.1
 
#准备数据集并预处理
transform_train = transforms.Compose([
    transforms.RandomCrop(size=32, padding=4), #先padding，再随机截取32*32
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),#R,G,B每层的归一化用到的均值和方差
])
transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
 
])
 
trianset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train) #训练数据集
trainloader = torch.utils.data.DataLoader(dataset=trianset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2) #生成一个个batch进行批训练，顺序打乱
 
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True,transform=transform_test)  #测试数据集
testloader = torch.utils.data.DataLoader(dataset=testset, batch_size=100,shuffle = False, num_workers=2)
 
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
 
#模型定义ResNet
net = ResNet18().to(device)
 
#定义损失函数和优化方法
criterion = nn.CrossEntropyLoss() #损失函数为交叉熵，多用于多分类问题
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9, weight_decay=5e-4)
 
#训练
if __name__ == "__main__":
    best_acc = 85 #2 初始化best test accuracy
    print("Start Training Resnet-18！")
    with open("acc.txt", "w") as f:
        with open("log.txt", "w") as f2:
            for epoch in range(pre_epoch, EPOCH):
                print('\nEpoch: %d' %   (epoch+1))
                net.train()
                sum_loss=0
                correct = 0
                total = 0
                for i,data in enumerate(trainloader, 0):
                    #准备数据
                    length = len(trainloader)
                    inputs, labels = data
################################
                    数据这里进行了修改
################################
                    inputs, labels = inputs.to(device), labels.to(device)
                    optimizer.zero_grad()
 
                    #forward + backward
                    outputs = net(inputs)
                    loss = criterion(outputs, labels)
                    loss.backward()
                    optimizer.step()
 
                    #每训练一个batch打印一次loss和准确率
                    sum_loss += loss.item()
                    _,predicted = torch.max(outputs.data,1)
                    total  += labels.size(0)
                    correct += predicted.eq(labels.data).cpu().sum()
                    print('[epoch: %d, iter: %d] Loss: %.03f | Acc: %.3f%% '
                          % (epoch+1, (i+1+epoch*length), sum_loss/(i+1), 100. * correct/ total))
                    f2.write('%03d  %05d |Loss: %.03f | Acc: %.3f%% '
                          % (epoch+1, (i+1+epoch*length), sum_loss/(i+1), 100. * correct/ total))
                    f2.write('\n')
                    f2.flush()
 
 
                #每次训练完一个epoch测试以下准确率
                print("Waiting Test！")
                with torch.no_grad():
                    correct = 0
                    total = 0
                    for data in testloader:
                        net.eval()
                        images, labels = data
################################
                    数据这里进行了修改
################################
                        images, labels = images.to(device), labels.to(device)
                        outputs = net(images)
 
                        #取得最高分的那个类（outputs.data的索引号
                        _, predicted = torch.max(outputs.data, 1)
                        total += labels.size(0)
                        correct += (predicted == labels).sum()
 
                    print('测试分类准确率为： %.3f%%' % (100*correct/total))
                    acc = 100. * correct / total
                    #将每次测试结果实时写入acc.txt文件中
                    print('Saving model......')
                    torch.sava(net.state_dict(), '%s/net_%03d.pth' % (args.outf, epoch+1))
                    f.write("EPOCH=%03d, Accuracy=.3f%%" % (epoch+1, acc))
                    f.write('\n')
                    f.flush()
 
                    # 记录最佳测试分类准确率并写入best_acc.txt文件中
                    if acc > best_acc:
                        f3 = open("best_acc.txt", "w")
                        f3.write("EPOCH=%d,best_acc=%.3f%%" % (epoch+1, acc))
                        f3.close()
                        best_acc = acc
 
            print("Training Finished, TotalEPOCH=%d" % EPOCH)