【PyTorch深度学习】 第九讲：CNN基础

1.概念原理

利用卷积核，对数据矩阵进行相乘相加
每个通道对应一个核

2.代码实现

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

# prepare dataset

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)


# design model using class
'''
torch.nn.Conv2d
    输入通道
    输出通道
    卷积核大小
    padding填充
    bias偏执
MaxPool2d
    维度
'''

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)
        self.conv3 = torch.nn.Conv2d(20, 30, kernel_size=3)
        self.pooling = torch.nn.MaxPool2d(2)
        self.l1 = torch.nn.Linear(120, 64)
        self.l2 = torch.nn.Linear(64, 32)
        self.l3 = torch.nn.Linear(32, 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 = F.relu((self.conv3(x)))
        x = x.view(batch_size, -1)  # 变化全连接类型输入
        x = self.l1(x)
        x = self.l2(x)
        x = self.l3(x)
        return x


model = Net()

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


# training cycle forward, backward, update


def 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 = 0.0


def 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()

3.结果

[1,   300] loss: 1.682
[1,   600] loss: 0.345
[1,   900] loss: 0.225
accuracy on test set: 94 % 
[2,   300] loss: 0.175
[2,   600] loss: 0.136
[2,   900] loss: 0.116
accuracy on test set: 96 % 
[3,   300] loss: 0.107
[3,   600] loss: 0.096
[3,   900] loss: 0.089
accuracy on test set: 97 % 
[4,   300] loss: 0.080
[4,   600] loss: 0.074
[4,   900] loss: 0.075
accuracy on test set: 98 % 
[5,   300] loss: 0.064
[5,   600] loss: 0.066
[5,   900] loss: 0.062
accuracy on test set: 98 % 
[6,   300] loss: 0.058
[6,   600] loss: 0.053
[6,   900] loss: 0.056
accuracy on test set: 98 % 
[7,   300] loss: 0.051
[7,   600] loss: 0.048
[7,   900] loss: 0.050
accuracy on test set: 98 % 
[8,   300] loss: 0.045
[8,   600] loss: 0.043
[8,   900] loss: 0.047
accuracy on test set: 98 % 
[9,   300] loss: 0.039
[9,   600] loss: 0.038
[9,   900] loss: 0.045
accuracy on test set: 98 % 
[10,   300] loss: 0.035
[10,   600] loss: 0.036
[10,   900] loss: 0.041
accuracy on test set: 98 %