【PyTorch深度学习实践】第10讲 卷积神经网络

下采样Subsampling
通道数不变，图像的高度宽度不变，为了减少数据量，降低运算需求。

Fearture Extraction:通过卷积运算找到某种特征
Classification:经过特征提取变成向量后，再接一个全连接网络去做分类。

import torch
in_channels, out_channels = 5, 10
width, height = 100, 100
kernel_size = 3
batch_size = 1

# 随机产生均值为0方差为1的正态分布
input = torch.randn(batch_size, in_channels, width, height)
# 创建卷积层
# 输入的channel 输出的channel 卷积核大小
conv_layer = torch.nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size)
output = conv_layer(input)
print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)

输出：

torch.Size([1, 5, 100, 100])
torch.Size([1, 10, 98, 98])
torch.Size([10, 5, 3, 3])   # 卷积层权重的形状，10输出通道 5输入通道

padding
33 padding=1
55 padding=2
最常见的是填充0

input = [3, 4, 6, 5, 7,
         2, 4, 6, 8, 2,
         1, 6, 7, 8, 4,
         9, 7, 4, 6, 2,
         3, 7, 5, 4, 1]
# view(B C W H)
input = torch.Tensor(input).view(1, 1, 5, 5)
# batch=1表示一次送入一张图片
conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, padding=1, bias=False)
# 构造卷积核
# View(O,I,W,H)
kernel = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
conv_layer.weight.data = kernel.data

output = conv_layer(input)
print(output)

输出：
stride=2

MaxPooling最大池化层

通道数量不变，默认步长stride=2

2828 用55的卷积要小两圈（batch,10,24,24）
池化是每每两列数据合成一列即列数减半，行数同理。

先不定义全连接层，先把输出结果的维度输出一下

不激活失去非线性变换

batch_size = 64
transform = 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)


class 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)
        # 池化层
        self.pooling = torch.nn.MaxPool2d(2)
        # 全连接层
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        # 取第0个 拿出维度
        batch_size = x.size(0)
        # 先卷积再池化最后relu
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        # 变成全连接网络需要的输入
        x = x.view(batch_size, -1)
        # 全连接层做变换
        x = self.fc(x)
        return x

model = Net()
# GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        # 输入和输出都迁移到对应的device上
        inputs, target = inputs.to(device), target.to(device)
        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 = 0.0


def 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)
            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))
    return correct/total


if __name__ == '__main__':
    epoch_list = []
    acc_list = []

    for epoch in range(10):
        train(epoch)
        acc = test()
        epoch_list.append(epoch)
        acc_list.append(acc)

    plt.plot(epoch_list, acc_list)
    plt.ylabel('accuracy')
    plt.xlabel('epoch')
    plt.show()

输出：
[1, 300] loss: 0.662
[1, 600] loss: 0.198
[1, 900] loss: 0.148
accuracy on test set: 96 %
[2, 300] loss: 0.113
[2, 600] loss: 0.099
[2, 900] loss: 0.094
accuracy on test set: 97 %
[3, 300] loss: 0.076
[3, 600] loss: 0.078
[3, 900] loss: 0.074
accuracy on test set: 98 %
[4, 300] loss: 0.061
[4, 600] loss: 0.064
[4, 900] loss: 0.065
accuracy on test set: 98 %
[5, 300] loss: 0.053
[5, 600] loss: 0.056
[5, 900] loss: 0.060
accuracy on test set: 98 %
[6, 300] loss: 0.048
[6, 600] loss: 0.049
[6, 900] loss: 0.051
accuracy on test set: 98 %
[7, 300] loss: 0.043
[7, 600] loss: 0.047
[7, 900] loss: 0.045
accuracy on test set: 98 %
[8, 300] loss: 0.047
[8, 600] loss: 0.041
[8, 900] loss: 0.037
accuracy on test set: 98 %
[9, 300] loss: 0.039
[9, 600] loss: 0.039
[9, 900] loss: 0.037
accuracy on test set: 98 %
[10, 300] loss: 0.036
[10, 600] loss: 0.039
[10, 900] loss: 0.036
accuracy on test set: 98 %