使用卷积神经网络识别MNIST数据集

最新推荐文章于 2025-04-03 22:54:02 发布

书中藏着宇宙

最新推荐文章于 2025-04-03 22:54:02 发布

阅读量348

点赞数 3

分类专栏：个人文章标签： cnn 人工智能神经网络

本文链接：https://blog.youkuaiyun.com/m0_49586319/article/details/146878633

版权

个人专栏收录该内容

6 篇文章

订阅专栏

卷积神经网络

卷积神经网络本质是共享权重+稀疏链接的全连接网络

编写步骤

构建一个神经网络，步骤是几乎不变的，大概有以下几步

准备数据集

#更高级的CNN网络
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
#准备数据集
batch_size = 64

transforms = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.1307,),(0.3081,))])

trainset = torchvision.datasets.MNIST(root=r'../data/mnist',
                                      train=True,
                                      download=True,
                                      transform=transforms)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True)



testset = torchvision.datasets.MNIST(root=r'../data/mnist',
                                     train=False,
                                     download=True,
                                     transform=transforms)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False)

不使用官方数据集读取方法，可以自己继承Dataset类重写

class Mydataset(Dataset):
    def __init__(self,filepath):
        xy=np.loadtxt(filepath,delimiter=',',dtype=np.float32)
        self.len=xy.shape[0]
        self.x_data=torch.from_numpy(xy[:,:-1])
        self.y_data=torch.from_numpy(xy[:,[-1]])
    #魔法方法，容许用户通过索引index得到值
    def __getitem__(self,index):
        return self.x_data[index],self.y_data[index]
    def __len__(self):
        return self.len

构建模型

class CNN_net(nn.Module):
    def __init__(self):
        super(CNN_net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=3, bias=False)#输出存为[10,26,26]
        self.conv2 = nn.Conv2d(10, 20, kernel_size=3, bias=False)#输出为【20,5,5】
        self.pooling = nn.MaxPool2d(2, 2)#输出为将其中尺寸减半
        self.fc1 = nn.Linear(500, 10)
    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        #
        x = x.view(batch_size, -1)
        #(x.size())
        x = F.relu(self.fc1(x))
        return x

如果想使用残差网络可以定义残差网络块儿

# 定义残差网络块儿
class ResidualBlock(nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(channels, kernel_size=3, padding=1, bias=False)
        self.conv2 = nn.Conv2d(channels,channels, kernel_size=3, padding=1, bias=False)
    def forward(self, x):
        out = F.relu(self.conv1(x))
        out = self.conv2(out)
        return F.relu(out + x)

那么对应的forward哪里可以添加进去残差块


class CNN_net(nn.Module):
    def __init__(self):
        super(CNN_net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=3, bias=False)#输出存为[10,26,26]
        self.conv2 = nn.Conv2d(10, 20, kernel_size=3, bias=False)#输出为【20,5,5】
        self.resblock1 = ResidualBlock(10)
        self.resblock2 = ResidualBlock(20)
        self.pooling = nn.MaxPool2d(2, 2)#输出为将其中尺寸减半
        self.fc1 = nn.Linear(500, 10)
    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x=self.resblock1(x)
        x = F.relu(self.pooling(self.conv2(x)))
        x = self.resblock2(x)
        x = x.view(batch_size, -1)
        #(x.size())
        x = F.relu(self.fc1(x))
        return x

构建模型和损失函数

# 构建模型和损失
model=CNN_net()

# 定义一个设备，如果我们=有能够访问的CUDA设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(torch.cuda.is_available())
#将模型搬移到CUDA支持的GPU上面
model.to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

训练（和测试）模型

def train(epoch):
    running_loss = 0.0
    for batch_idx, (inputs, targets) in enumerate(trainloader):
        inputs,targets = inputs.to(device),targets.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()
        #需要将张量转换为浮点数运算
        running_loss += loss.item()
        if batch_idx % 100 == 0:
            print('Train Epoch: {}, Loss: {:.6f}'.format(epoch, loss.item()))
            running_loss = 0
def test(epoch):
    correct = 0
    total = 0
    with torch.no_grad():
        for batch_idx, (inputs, targets) in enumerate(testloader):
            inputs,targets = inputs.to(device),targets.to(device)
            outputs = model(inputs)
            _, predicted = torch.max(outputs.data, 1)
            total += targets.size(0)
            correct=correct+(predicted.eq(targets).sum()*1.0)
    print('Accuracy of the network on the 10000 test images: %d %%' % (100*correct/total))

全部代码

#更高级的CNN网络
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
#准备数据集
batch_size = 64
transforms = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.1307,),(0.3081,))])

trainset = torchvision.datasets.MNIST(root=r'../data/mnist',
                                      train=True,
                                      download=True,
                                      transform=transforms)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True)



testset = torchvision.datasets.MNIST(root=r'../data/mnist',
                                     train=False,
                                     download=True,
                                     transform=transforms)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False)


# 定义残差网络块儿
class ResidualBlock(nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(channels,channels, kernel_size=3, padding=1, bias=False)
        self.conv2 = nn.Conv2d(channels,channels, kernel_size=3, padding=1, bias=False)
    def forward(self, x):
        out = F.relu(self.conv1(x))
        out = self.conv2(out)
        return F.relu(out + x)
# 定义卷积神经网络

class CNN_net(nn.Module):
    def __init__(self):
        super(CNN_net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=3, bias=False)#输出存为[10,26,26]
        self.conv2 = nn.Conv2d(10, 20, kernel_size=3, bias=False)#输出为【20,5,5】
        self.resblock1 = ResidualBlock(10)
        self.resblock2 = ResidualBlock(20)
        self.pooling = nn.MaxPool2d(2, 2)#输出为将其中尺寸减半
        self.fc1 = nn.Linear(500, 10)
    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x=self.resblock1(x)
        x = F.relu(self.pooling(self.conv2(x)))
        x = self.resblock2(x)
        x = x.view(batch_size, -1)
        #(x.size())
        x = F.relu(self.fc1(x))
        return x


# 构建模型和损失
model=CNN_net()

# 定义一个设备，如果我们=有能够访问的CUDA设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(torch.cuda.is_available())
#将模型搬移到CUDA支持的GPU上面
model.to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

def train(epoch):
    running_loss = 0.0
    for batch_idx, (inputs, targets) in enumerate(trainloader):
        inputs,targets = inputs.to(device),targets.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()
        #需要将张量转换为浮点数运算
        running_loss += loss.item()
        if batch_idx % 100 == 0:
            print('Train Epoch: {}, Loss: {:.6f}'.format(epoch, loss.item()))
            running_loss = 0
def test(epoch):
    correct = 0
    total = 0
    with torch.no_grad():
        for batch_idx, (inputs, targets) in enumerate(testloader):
            inputs,targets = inputs.to(device),targets.to(device)
            outputs = model(inputs)
            _, predicted = torch.max(outputs.data, 1)
            total += targets.size(0)
            correct=correct+(predicted.eq(targets).sum()*1.0)
    print('Accuracy of the network on the 10000 test images: %d %%' % (100*correct/total))
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test(epoch)