PyTorch之示例——MNIST

from __future__ import print_functionimport argparseimport torchimport torch.nn as nnimport torch.nn.functional as Fimport torch.optim as optimfrom torchvision import datasets, transformsfrom torch.autograd import Variable# Training settingsparser = argparse.ArgumentParser(description='PyTorch MNIST Example')parser.add_argument('--batch-size', type=int, default=64, metavar='N',                    help='input batch size for training (default: 64)')parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',                    help='input batch size for testing (default: 1000)')parser.add_argument('--epochs', type=int, default=10, metavar='N',                    help='number of epochs to train (default: 10)')parser.add_argument('--lr', type=float, default=0.01, metavar='LR',                    help='learning rate (default: 0.01)')parser.add_argument('--momentum', type=float, default=0.5, metavar='M',                    help='SGD momentum (default: 0.5)')parser.add_argument('--no-cuda', action='store_true', default=False,                    help='disables CUDA training')parser.add_argument('--seed', type=int, default=1, metavar='S',                    help='random seed (default: 1)')parser.add_argument('--log-interval', type=int, default=10, metavar='N',                    help='how many batches to wait before logging training status')args = parser.parse_args()args.cuda = not args.no_cuda and torch.cuda.is_available()torch.manual_seed(args.seed) #为CPU设置种子用于生成随机数，以使得结果是确定的if args.cuda:    torch.cuda.manual_seed(args.seed)#为当前GPU设置随机种子；如果使用多个GPU，应该使用torch.cuda.manual_seed_all()为所有的GPU设置种子。kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}"""加载数据。组合数据集和采样器，提供数据上的单或多进程迭代器参数：dataset：Dataset类型，从其中加载数据batch_size：int，可选。每个batch加载多少样本shuffle：bool，可选。为True时表示每个epoch都对数据进行洗牌sampler：Sampler，可选。从数据集中采样样本的方法。num_workers：int，可选。加载数据时使用多少子进程。默认值为0，表示在主进程中加载数据。collate_fn：callable，可选。pin_memory：bool，可选drop_last：bool，可选。True表示如果最后剩下不完全的batch,丢弃。False表示不丢弃。"""train_loader = torch.utils.data.DataLoader(    datasets.MNIST('../data', train=True, download=True,                   transform=transforms.Compose([                       transforms.ToTensor(),                       transforms.Normalize((0.1307,), (0.3081,))                   ])),    batch_size=args.batch_size, shuffle=True, **kwargs)test_loader = torch.utils.data.DataLoader(    datasets.MNIST('../data', train=False, transform=transforms.Compose([                       transforms.ToTensor(),                       transforms.Normalize((0.1307,), (0.3081,))                   ])),    batch_size=args.batch_size, shuffle=True, **kwargs)class Net(nn.Module):    def __init__(self):        super(Net, self).__init__()        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)#输入和输出通道数分别为1和10        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)#输入和输出通道数分别为10和20        self.conv2_drop = nn.Dropout2d()#随机选择输入的信道，将其设为0        self.fc1 = nn.Linear(320, 50)#输入的向量大小和输出的大小分别为320和50        self.fc2 = nn.Linear(50, 10)    def forward(self, x):        x = F.relu(F.max_pool2d(self.conv1(x), 2))#conv->max_pool->relu        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))#conv->dropout->max_pool->relu        x = x.view(-1, 320)        x = F.relu(self.fc1(x))#fc->relu        x = F.dropout(x, training=self.training)#dropout        x = self.fc2(x)        return F.log_softmax(x)model = Net()if args.cuda:    model.cuda()#将所有的模型参数移动到GPU上optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)def train(epoch):    model.train()#把module设成training模式，对Dropout和BatchNorm有影响    for batch_idx, (data, target) in enumerate(train_loader):        if args.cuda:            data, target = data.cuda(), target.cuda()        data, target = Variable(data), Variable(target)#Variable类对Tensor对象进行封装，会保存该张量对应的梯度，以及对生成该张量的函数grad_fn的一个引用。如果该张量是用户创建的，grad_fn是None，称这样的Variable为叶子Variable。        optimizer.zero_grad()        output = model(data)        loss = F.nll_loss(output, target)#负log似然损失        loss.backward()        optimizer.step()        if batch_idx % args.log_interval == 0:            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(                epoch, batch_idx * len(data), len(train_loader.dataset),                100. * batch_idx / len(train_loader), loss.data[0]))def test(epoch):    model.eval()#把module设置为评估模式，只对Dropout和BatchNorm模块有影响    test_loss = 0    correct = 0    for data, target in test_loader:        if args.cuda:            data, target = data.cuda(), target.cuda()        data, target = Variable(data, volatile=True), Variable(target)        output = model(data)        test_loss += F.nll_loss(output, target).data[0]#Variable.data        pred = output.data.max(1)[1] # get the index of the max log-probability        correct += pred.eq(target.data).cpu().sum()    test_loss = test_loss    test_loss /= len(test_loader) # loss function already averages over batch size    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(        test_loss, correct, len(test_loader.dataset),        100. * correct / len(test_loader.dataset)))for epoch in range(1, args.epochs + 1):    train(epoch)    test(epoch)