Python实战小项目之Mnist手写数字识别

BATCH_SIZE = 512
EPOCHS = 8
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('data', train=True, download=True,
                   transform=transforms.Compose([.
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=BATCH_SIZE, shuffle=True)

test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('data', train=False,
                   transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=BATCH_SIZE, shuffle=True)

examples = enumerate(test_loader)
batch_idx, (example_data, example_targets) = next(examples)
print(example_targets)
print(example_data.shape)
print(example_data)
 
import matplotlib.pyplot as plt
fig = plt.figure()
for i in range(6):
  plt.subplot(2,3,i+1)
  plt.tight_layout()
  plt.imshow(example_data[i][0], cmap='gray', interpolation='none')
  plt.title("Ground Truth: {}".format(example_targets[i]))
  plt.xticks([])
  plt.yticks([])
plt.show()

class linearNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(784, 128)
        self.fc2 = nn.Linear(128, 64)
        self.fc3 = nn.Linear(64, 10)
    def forward(self, x):
        x = x.view(-1, 784)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.fc2(x)
        x = F.relu(x)
        x = self.fc3(x)
        x = F.log_softmax(x, dim=1)
        return x

def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
 
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if (batch_idx) % 30 == 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()))

def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item() # 将一批的损失相加
            pred = output.max(1, keepdim=True)[1] # 找到概率最大的下标
            correct += pred.eq(target.view_as(pred)).sum().item()
 
    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

if __name__ == '__main__':
    model = linearNet()
    optimizer = optim.Adam(model.parameters())
 
    for epoch in range(1, EPOCHS + 1):
        train(model, device, train_loader, optimizer, epoch)
        test(model, device, test_loader)

torch.save(model, 'MNIST.pth')