构建数据Dataset和DataLoader


import torch
from torch import nn, optim
from torch.autograd import Variable
from torch.utils.data import DataLoader, Dataset
from torchvision import datasets, transforms


class myDataset(Dataset):
    # torch.utils.data.Dataset 是代表这一数据的抽象类，
    # 自己定义你的数 据类继承和重写这个抽象类，非常简单，
    # 只需要定义 len一和_getitem一这两个 函数
    def __init__(self, ):
        self.x_test = [0, 1, 2, 3]
        self.y_test = [0, 1, 2, 3]

    def __len__(self):
        return len(self.x_test)

    def __getitem__(self, item):
        data = (self.x_test[item], self.y_test[item])
        return data
#
data = myDataset()
my_loader = DataLoader(data, batch_size=2, shuffle=True, drop_last=True)
for d in data:
    print(d)

print('data[3]: ', data[3])
dataiter = iter(my_loader)
print('dataiter', len(my_loader))
for i in dataiter:
    print(i)

构建网络

class Net(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super(Net, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Linear(in_dim, n_hidden_1),
            nn.BatchNorm1d(n_hidden_1),
            nn.ReLU(True)
        )
        self.layer2 = nn.Sequential(
            nn.Linear(n_hidden_1, n_hidden_2),
            nn.BatchNorm1d(n_hidden_2),
            nn.ReLU(True)
        )
        self.layer3 = nn.Sequential(
            nn.Linear(n_hidden_2, out_dim))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x

batch_size = 64
learning_rate = 1e-2
num_epoches = 1


data_tf = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize([0.5], [0.5]),])

train_dataset = datasets.MNIST(root='./data',
                                train=True,
                                transform=data_tf,
                                download=True)

test_dataset = datasets.MNIST(root='./data',
                                transform=data_tf,
                                download=True)

train_loader = DataLoader(train_dataset, batch_size=batch_size,shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size,shuffle=True)


model = Net(28*28, 300, 100, 10)
if torch.cuda.is_available():
    model = model.cuda()
model.train()



criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

#-----------------------------train------------------------------------------------
for epoch in range(num_epoches):
    for data in train_loader:
        x_train, y_train = data
        x_train = x_train.view(x_train.size(0), -1)
        if torch.cuda.is_available():
            inputs = Variable(x_train).cuda
            target = Variable(y_train).cuda
        else:
            inputs = Variable(x_train)
            target = Variable(y_train)

        # forward
        out = model(inputs)
        loss = criterion(out, target)

        # backward
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (epoch + 1) :
            print('Epoch : [{}/{}], loss: {:.6f}'.format(epoch + 1,
                                                         num_epoches,
                                                         loss.item()))

#-----------------------------eavl------------------------------------------------
model.eval()
eval_loss = 0
eval_acc = 0

for data in test_loader:
    x_test, y_test = data
    x_test = x_test.view(x_test.size(0), -1)

    if torch.cuda.is_available():
        inputs = Variable(x_test, volatile=True).cuda()
        target = Variable(y_test, volatile=True).cuda()
    else:
        inputs = Variable(x_test, volatile=True)
        target = Variable(y_test, volatile=True)

    out = model(inputs)
    loss = criterion(out, target)
    eval_loss += loss.item() * target.size(0)
    _, pred = torch.max(out, 1)
    num_correct = (pred == target).sum()
    eval_acc += num_correct.item()

print('Test Loss : {:.6f}, Acc: {:.6f}'.format(
    eval_loss / (len(test_dataset)),
    eval_acc / (len(test_dataset))
))