PyTorch深度学习（五）【卷积神经网络】

卷积神经网络(基础篇)：

下采样（Subsampling）：通道数不变，减少数据量，降低运算需求。

做这个卷积：

网络：

最大池化层（MaxPooling）：通道数不变，图像大小缩成原来的一半，没有权重。

代码：

import torchfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport torch.optim as optim# prepare datasetbatch_size = 64transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass Net(torch.nn.Module):    def __init__(self):        super(Net, self).__init__()        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)        self.pooling = torch.nn.MaxPool2d(2)        self.fc = torch.nn.Linear(320, 10)    def forward(self, x):        # flatten data from (n,1,28,28) to (n, 784)        batch_size = x.size(0)     #求batchsize        x = F.relu(self.pooling(self.conv1(x)))   #卷积、池化、激活        x = F.relu(self.pooling(self.conv2(x)))        x = x.view(batch_size, -1)     # -1 此处自动算出的是320；view的目的就是变成全连接网络需要的格式。flatten        x = self.fc(x)        return xmodel = Net()device = torch.device("cuda" if torch.cuda.is_available() else "cpu")    #如果你有GPU，这两行的意思就是用GPU跑model.to(device)   #没有GPU的话这两行可以不写（写上也无妨）# construct loss and optimizercriterion = torch.nn.CrossEntropyLoss()optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):    running_loss = 0.0    for batch_idx, data in enumerate(train_loader, 0):        inputs, target = data        inputs, target = inputs.to(device), target.to(device)#把数据迁移到GPU上，如果没有GPU，这行可以不写        optimizer.zero_grad()        outputs = model(inputs)        loss = criterion(outputs, target)        loss.backward()        optimizer.step()        running_loss += loss.item()        if batch_idx % 300 == 299:            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))            running_loss = 0.0def test():    correct = 0    total = 0    with torch.no_grad():        for data in test_loader:            images, labels = data            images, labels = images.to(device), labels.to(device)   #如果没有GPU，这行可以不写            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))if __name__ == '__main__':    for epoch in range(10):        train(epoch)        test()

经过10轮的训练后，模型的准确度达到了98%，用线性模型是97%。

卷积神经网络(提高篇)：

Inception Module:

Concatenate：把张量拼接到一块；

Average Pooling：均值池化；

1×1卷积：将来的卷积核是1×1，个数取决于输出张量的通道。

1×1卷积作用：（主要就是降维）

部分模块代码：

代码：

import torchimport torch.nn as nnfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport torch.optim as optim# prepare datasetbatch_size = 64transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass InceptionA(nn.Module):    def __init__(self, in_channels):        super(InceptionA, self).__init__()        self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1)        self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1)        self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2)        self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1)        self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1)        self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1)        self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1)    def forward(self, x):        branch1x1 = self.branch1x1(x)        branch5x5 = self.branch5x5_1(x)        branch5x5 = self.branch5x5_2(branch5x5)        branch3x3 = self.branch3x3_1(x)        branch3x3 = self.branch3x3_2(branch3x3)        branch3x3 = self.branch3x3_3(branch3x3)        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)        branch_pool = self.branch_pool(branch_pool)        outputs = [branch1x1, branch5x5, branch3x3, branch_pool]        return torch.cat(outputs, dim=1)  # b,c,w,h  c对应的是dim=1class Net(nn.Module):    def __init__(self):        super(Net, self).__init__()        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)        self.conv2 = nn.Conv2d(88, 20, kernel_size=5)  # 88 = 24x3 + 16        self.incep1 = InceptionA(in_channels=10)  # 与conv1 中的10对应        self.incep2 = InceptionA(in_channels=20)  # 与conv2 中的20对应        self.mp = nn.MaxPool2d(2)        self.fc = nn.Linear(1408, 10)    def forward(self, x):        in_size = x.size(0)        x = F.relu(self.mp(self.conv1(x)))  #通道变为10        x = self.incep1(x)                  #88        x = F.relu(self.mp(self.conv2(x)))  #20        x = self.incep2(x)                  #88        x = x.view(in_size, -1)        x = self.fc(x)        return xmodel = Net()# construct loss and optimizercriterion = torch.nn.CrossEntropyLoss()optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):    running_loss = 0.0    for batch_idx, data in enumerate(train_loader, 0):        inputs, target = data        optimizer.zero_grad()        outputs = model(inputs)        loss = criterion(outputs, target)        loss.backward()        optimizer.step()        running_loss += loss.item()        if batch_idx % 300 == 299:            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))            running_loss = 0.0def test():    correct = 0    total = 0    with torch.no_grad():        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))if __name__ == '__main__':    for epoch in range(10):        train(epoch)        test()

Residual Network:

？：保持输入和输出大小相同。

代码：

import torchimport torch.nn as nnfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport torch.optim as optim# prepare datasetbatch_size = 64transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass ResidualBlock(nn.Module):    def __init__(self, channels):        super(ResidualBlock, self).__init__()        self.channels = channels        self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)        self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)    def forward(self, x):        y = F.relu(self.conv1(x))        y = self.conv2(y)        return F.relu(x + y)class Net(nn.Module):    def __init__(self):        super(Net, self).__init__()        self.conv1 = nn.Conv2d(1, 16, kernel_size=5)        self.conv2 = nn.Conv2d(16, 32, kernel_size=5)  # 88 = 24x3 + 16        self.rblock1 = ResidualBlock(16)        self.rblock2 = ResidualBlock(32)        self.mp = nn.MaxPool2d(2)        self.fc = nn.Linear(512, 10)  # 暂时不知道1408咋能自动出来的    def forward(self, x):        in_size = x.size(0)        x = self.mp(F.relu(self.conv1(x)))        x = self.rblock1(x)        x = self.mp(F.relu(self.conv2(x)))        x = self.rblock2(x)        x = x.view(in_size, -1)        x = self.fc(x)        return xmodel = Net()# construct loss and optimizercriterion = torch.nn.CrossEntropyLoss()optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):    running_loss = 0.0    for batch_idx, data in enumerate(train_loader, 0):        inputs, target = data        optimizer.zero_grad()        outputs = model(inputs)        loss = criterion(outputs, target)        loss.backward()        optimizer.step()        running_loss += loss.item()        if batch_idx % 300 == 299:            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))            running_loss = 0.0def test():    correct = 0    total = 0    with torch.no_grad():        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))if __name__ == '__main__':    for epoch in range(10):        train(epoch)        test()