多分类问题(手写数字 pytorch)

# 手写数字识别
import torch
# 数据集处理
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
# 函数  激活函数等
import torch.nn.functional as F
# 优化器包
import torch.optim as optim
# 分批
batch_size = 64
# 1. 数据处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, ))
])

train_dataset = datasets.MNIST(root='../dataset/mnist/',
                            train=True,
                            download=True,
                            transform=transform)
test_dataset = datasets.MNIST(root='../dataset/mnist/',
                              train=False,
                              download=True,
                              transform=transform)
train_loader = DataLoader(test_dataset,
                         shuffle=True,
                         batch_size=batch_size)

test_loader = DataLoader(test_dataset,
                         shuffle=False,
                         batch_size=batch_size)

# 数据为1 * 28 * 28
# 2. 建立模型
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1, 784)
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        return self.l5(x)

model = Net()

# 3.损失函数和优化器  交叉熵损失
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

# 4.循环训练
def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader):
        inputs, target = data
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        print(batch_idx% 300)
        if batch_idx % 300 == 0:
            print('[%d,%d] loss: %.10f' % (epoch+1, batch_idx+1, running_loss / 300))
            running_loss = 0.0

# 测试验证
def test():
    correct = 0
    total = 0
    with torch.no_grad(): # 不会再进行梯度
        for data in  test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total+=labels.size(0)
            correct+=(predicted==labels).sum().item()
    print("Accuracy on test set: %d %%" % (100 * correct / total))


# 程序入口处
if __name__ == '__main__':
    for epoch in range(200):
        train(epoch)
        test()
    print("训练结束...")

存在的问题, 因为全连接, 可能会存在过拟合;