PyTorch学习笔记（9）

简单的卷积神经网络

和之前相比，主要是网络结构（Model）的搭建不一样了。
用到了Conv2d、MaxPool2d、pooling等
还有全连接层Linear

根据视频

#simple CNN
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

# 1.prepare datasets
batch_size = 64
transform = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.1307,), (0.3081,))])
train_dataset = datasets.MNIST(root=r'E:\03study\Python',
                               train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root=r'E:\03study\Python'
                              , train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)


# 2.Design Model
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()

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


# 4.Train and Test
def train(epoch):
    l_sum = 0
    for index, data in enumerate(train_loader, 0):
        inputs, labels = data
        y_pre = model(inputs)
        loss = criterion(y_pre, labels)
        # print(epoch,index,loss.item())

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        l_sum += loss.item()
        # print('This is the %d train'%(index+1))
        if index % 300 == 299:
            print('[%d,%5d]loss=%.3f' % (epoch + 1, index + 1, l_sum / 300))
            l_sum = 0


def test():
    correct = 0
    totel = 0
    with torch.no_grad():
        for data in test_loader:
            inputs, labels = data
            y_pre = model(inputs)
            _, predicted = torch.max(y_pre.data, dim=1)
            totel += labels.size(0)
            # print(totel,correct)
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set:%d %%' % (100 * correct / totel))


if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()