数字矩阵输入的卷积神经网络程序pytorch

以下是一个数字矩阵输入的卷积神经网络程序，使用PyTorch实现。该程序接受28x28像素的数字图片作为输入，并使用一个包含两个卷积层和两个全连接层的神经网络进行分类。我们将使用MNIST数据集进行训练和测试。

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms

# 定义网络结构
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
        self.fc1 = nn.Linear(64*7*7, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2)
        x = x.view(-1, 64*7*7)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

# 加载数据集
train_dataset = datasets.MNIST(root='./data', train=True, download=True,
                               transform=transforms.Compose([
                                   transforms.ToTensor(),
                                   transforms.Normalize((0.1307,), (0.3081,))
                               ]))

test_dataset = datasets.MNIST(root='./data', train=False, download=True,
                              transform=transforms.Compose([
                                  transforms.ToTensor(),
                                  transforms.Normalize((0.1307,), (0.3081,))
                              ]))

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=True)

# 定义优化器和损失函数
model = Net()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
criterion = nn.CrossEntropyLoss()

# 训练网络
def train(epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 100 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))

# 测试网络
def test():
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            output = model(data)
            test_loss += criterion(output, target).item()
            pred = output.argmax(dim=1, keepdim=True) # 获取最大值的位置
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    print('Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

# 训练和测试网络
for epoch in range(1, 11):
    train(epoch)
    test()

在该程序中，我们首先定义了一个包含两个卷积层和两个全连接层的神经网络。接下来，我们加载了MNIST数据集，并定义了优化器和损失函数。然后，我们定义了训练和测试函数，并使用这些函数对网络进行训练和测试。最后，我们使用循环对网络进行多次训练和测试。在每个训练周期中，我们打印出当前的损失值和准确率。