Pytorch GPU 使用率低

Question

我正在尝试https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html中的 pytorch 示例。当我运行这个示例时，GPU 使用率约为 1%，完成时间为 130 秒而对于 CPU 情况，CPU 使用率约为 90%，完成时间为 79 秒 我的 CPU 是 Intel(R) Core(TM) i7-8700 和我的 GPU 是 NVIDIA GeForce RTX 2070。

我想问CPU运行速度比GPU快是否正常？因为GPU使用量很小（与我从另一个网站看到的相比），这是我运行的代码（与网站类似）。

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F

def run():
    # ==================================================================================
    transform = transforms.Compose(
        [transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

    trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                            download=True, transform=transform)
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                              shuffle=True, num_workers=2)

    testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                           download=True, transform=transform)
    testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                             shuffle=False, num_workers=2)

    classes = ('plane', 'car', 'bird', 'cat',
               'deer', 'dog', 'frog', 'horse', 'ship', 'truck')


    # ==================================================================================
    # # functions to show an image


    # def imshow(img):
    #     img = img / 2 + 0.5     # unnormalize
    #     npimg = img.numpy()
    #     plt.imshow(np.transpose(npimg, (1, 2, 0)))
    #     plt.show()


    # # get some random training images
    # dataiter = iter(trainloader)
    # images, labels = dataiter.next()


    # # show images
    # imshow(torchvision.utils.make_grid(images))
    # # print labels
    # print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
    # ==================================================================================
    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.conv1 = nn.Conv2d(3, 6, 5)
            self.pool = nn.MaxPool2d(2, 2)
            self.conv2 = nn.Conv2d(6, 16, 5)
            self.fc1 = nn.Linear(16 * 5 * 5, 120)
            self.fc2 = nn.Linear(120, 84)
            self.fc3 = nn.Linear(84, 10)

        def forward(self, x):
            x = self.pool(F.relu(self.conv1(x)))
            x = self.pool(F.relu(self.conv2(x)))
            x = x.view(-1, 16 * 5 * 5)
            x = F.relu(self.fc1(x))
            x = F.relu(self.fc2(x))
            x = self.fc3(x)
            return x
    net = Net()
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    print(device)
    net.to(device)
    # ==================================================================================
    import torch.optim as optim

    criterion = nn.CrossEntropyLoss().to(device)
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
    # ==================================================================================
    for epoch in range(2):  # loop over the dataset multiple times

        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            # get the inputs; data is a list of [inputs, labels]
            inputs, labels = data[0].to(device), data[1].to(device)


            # zero the parameter gradients
            optimizer.zero_grad()

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

            # print statistics
            running_loss += loss.item()
            if i % 2000 == 1999:    # print every 2000 mini-batches
                print('[%d, %5d] loss: %.3f' %
                      (epoch + 1, i + 1, running_loss / 2000))
                running_loss = 0.0

    print('Finished Training')
    # ==================================================================================
    PATH = './cifar_net.pth'
    torch.save(net.state_dict(), PATH)

    # ==================================================================================
    # ==================================================================================
    # ==================================================================================


if __name__ == '__main__':
    run()