Pytorch_Task_7

用Pytorch实现手写数字识别

1. 定义一个CNN网络

from torch import nn
 
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 25, kernel_size=3),
            nn.BatchNorm2d(25),
            nn.ReLU(inplace=True)
        )
 
        self.layer2 = nn.Sequential(
            nn.MaxPool2d(kernel_size=2, stride=2)
        )
 
        self.layer3 = nn.Sequential(
            nn.Conv2d(25, 50, kernel_size=3),
            nn.BatchNorm2d(50),
            nn.ReLU(inplace=True)
        )
 
        self.layer4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=2, stride=2)
        )
 
        self.fc = nn.Sequential(
            nn.Linear(50 * 5 * 5, 1024),
            nn.ReLU(inplace=True),
            nn.Linear(1024, 128),
            nn.ReLU(inplace=True),
            nn.Linear(128, 10)
        )
 
    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

2.测试

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


# 定义一些超参数
batch_size = 64
learning_rate = 0.02
num_epoches = 20

# 数据预处理。transforms.ToTensor()将图片转换成PyTorch中处理的对象Tensor,并且进行标准化（数据在0~1之间）
# transforms.Normalize()做归一化。它进行了减均值，再除以标准差。两个参数分别是均值和标准差
# transforms.Compose()函数则是将各种预处理的操作组合到了一起
data_tf = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize([0.5], [0.5])])

# 数据集的下载器
train_dataset = datasets.MNIST(
    root='./data', train=True, transform=data_tf, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=data_tf)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

# 选择模型
model = CNN()
# model = net.Activation_Net(28 * 28, 300, 100, 10)
# model = net.Batch_Net(28 * 28, 300, 100, 10)
if torch.cuda.is_available():
    model = model.cuda()

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

# 训练模型
epoch = 0
for data in train_loader:
    img, label = data
    # img = img.view(img.size(0), -1)
    img = Variable(img)
    if torch.cuda.is_available():
        img = img.cuda()
        label = label.cuda()
    else:
        img = Variable(img)
        label = Variable(label)
    out = model(img)
    loss = criterion(out, label)
    print_loss = loss.data.item()

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    epoch+=1
    if epoch%50 == 0:
        print('epoch: {}, loss: {:.4}'.format(epoch, loss.data.item()))

# 模型评估
model.eval()
eval_loss = 0
eval_acc = 0
for data in test_loader:
    img, label = data
    # img = img.view(img.size(0), -1)
    img = Variable(img)
    if torch.cuda.is_available():
        img = img.cuda()
        label = label.cuda()

    out = model(img)
    loss = criterion(out, label)
    eval_loss += loss.data.item()*label.size(0)
    _, pred = torch.max(out, 1)
    num_correct = (pred == label).sum()
    eval_acc += num_correct.item()
print('Test Loss: {:.6f}, Acc: {:.6f}'.format(
    eval_loss / (len(test_dataset)),
    eval_acc / (len(test_dataset))
))

3.结果

epoch: 50, loss: 1.974
epoch: 100, loss: 1.243
epoch: 150, loss: 0.6076
epoch: 200, loss: 0.4551
epoch: 250, loss: 0.3107
epoch: 300, loss: 0.3195
epoch: 350, loss: 0.1471
epoch: 400, loss: 0.3002
epoch: 450, loss: 0.08808
epoch: 500, loss: 0.1151
epoch: 550, loss: 0.1539
epoch: 600, loss: 0.1201
epoch: 650, loss: 0.1032
epoch: 700, loss: 0.05643
epoch: 750, loss: 0.09671
epoch: 800, loss: 0.05831
epoch: 850, loss: 0.08721
epoch: 900, loss: 0.1273
Test Loss: 0.098649, Acc: 0.971200
[Finished in 60.1s]

• Reference
• https://github.com/liamlycoder/PyTorch_Primer/tree/master/PyTorch_Primer/05CNNonMNIST