pytorch tips：使pytorch代碼在不改動情況在有GPU自動在GPU運作

定義：

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

使用：

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()

#超參數設定
EPOCH = 135
pre_epoch = 0
BATCH_SIZE = 128
LR = 0.1

#準備資料集并預處理
transform_train = transforms.Compose([
    transforms.RandomCrop(size=32, padding=4), #先padding，再随機截取32*32
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),#R,G,B每層的歸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) #訓練資料集
trainloader = torch.utils.data.DataLoader(dataset=trianset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2) #生成一個個batch進行批訓練，順序打亂

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True,transform=transform_test)  #測試資料集
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')

#模型定義ResNet
net = ResNet18().to(device)

#定義損失函數和優化方法
criterion = nn.CrossEntropyLoss() #損失函數為交叉熵，多用于多分類問題
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9, weight_decay=5e-4)

#訓練
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):
                    #準備資料
                    length = len(trainloader)
                    inputs, labels = data
                    inputs, labels = inputs.to(device), labels.to(device)
                    optimizer.zero_grad()

                    #forward + backward
                    outputs = net(inputs)
                    loss = criterion(outputs, labels)
                    loss.backward()
                    optimizer.step()

                    #每訓練一個batch列印一次loss和準确率
                    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()


                #每次訓練完一個epoch測試以下準确率
                print("Waiting Test！")
                with torch.no_grad():
                    correct = 0
                    total = 0
                    for data in testloader:
                        net.eval()
                        images, labels = data
                        images, labels = images.to(device), labels.to(device)
                        outputs = net(images)

                        #取得最高分的那個類（outputs.data的索引号
                        _, predicted = torch.max(outputs.data, 1)
                        total += labels.size(0)
                        correct += (predicted == labels).sum()

                    print('測試分類準确率為： %.3f%%' % (100*correct/total))
                    acc = 100. * correct / total
                    #将每次測試結果實時寫入acc.txt檔案中
                    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()

                    # 記錄最佳測試分類準确率并寫入best_acc.txt檔案中
                    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)