卷积神经网络基础篇

1，使用卷积神经网络解决MNIST

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

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

batch_size = 64

transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307, ),(0.3081, )) # 均值和标准差
])

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
)

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.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320,10)

    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 = self.fc(x)
        return x
model = Net()
model.to(device)

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

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data # inputs : x   target: y
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()
        # forward + backward + update
        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(): # with语句下不执行梯度
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            # print(outputs)
            _, predicted = torch.max(outputs.data, dim=1) # dim：维度1  两个返回值：最大概率值及其下标
            # print(predicted)
            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()

相比于直接把input数据展开，使用卷积可以提高1%（98-99）的准确率（在原来模型基础上，减少1/3的错误率）