Mnist手写体识别

Mnist手写体识别

网络结构

• 单通道28×28的图像
• 采用四层全连接网络
• 采用分类的交叉熵损失

代码

导入库

import torch
import torch.nn as  nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets,transforms

MNIST数据集

#批量大小
batch_size = 64
#MNIST数据集
train_dataset = datasets.MNIST(root='./mnist_data',
                               train=True,
                               transform=transforms.ToTensor(),
                               download=True)
test_dataset = datasets.MNIST(root='./mnist_data/',
                               train=False,
                               transform=transforms.ToTensor())
#Data Loader(Input Pipeline)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                            batch_size=batch_size,
                                            shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                            batch_size=batch_size,
                                            shuffle=False)

网络模型

class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.l1 = nn.Linear(784,520)
        self.l2 = nn.Linear(520,320)
        self.l3 = nn.Linear(320,240)
        self.l4 = nn.Linear(240,120)
        self.l5 = nn.Linear(120,10)
    def forward(self,x):
        x = x.view(-1,784)#Flatten the data (n,1,28,28)->(n,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()
model = nn.DataParallel(model).cuda()

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr=0.01,momentum=0.5)#所有参数都更新，学习率0.01，动量0.5

训练

def train(epoch):
    model.train()
    for batch_idx,(data,target) in enumerate(train_loader):
        data = data.cuda()
        target = target.cuda()
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output,target)
        loss.backward()
        optimizer.step()#参数更新
        if batch_idx % 10 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                 epoch,batch_idx*len(data),len(train_loader.dataset),
                 100. *batch_idx / len(train_loader),loss.item()))

测试

def test():
    model.eval()
    test_loss = 0
    correct = 0
    for data , target in test_loader:
        data  = data.cuda()
        target = target.cuda()
        output = model(data)
        #计算批量损失
        test_loss += criterion(output,target).item()
        #得到最大值的索引
        pred = output.data.max(1,keepdim=True)[1]
        correct += pred.eq(target.data.view_as(pred)).cuda().sum()
    test_loss /= len(test_loader.dataset)
    print('\nTest set:Average loss:{:.4f},Accuracy:{}/{}  ({:.0f}%)\n'.format(
        test_loss,correct,len(test_loader.dataset),
        100. *correct / len(test_loader.dataset)))

结果展示

for epoch in range(1,10):
    train(epoch)
    test()