pytorch 构建神经网络对CIFAR10 数据集进行分类

1. 先建立网络模型（卷积层加全连接层）

import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

 

2. 准备数据

# torchvision 数据集的输出是范围在[0,1]之间的 PILImage，
# 我们将他们转换成归一化范围为[-1,1]之间的张量 Tensors
transform = transforms.Compose(
    [transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

# 公共数据集的数据加载模块 torchvision.datasets 和 支持加载图像数据数据转换模块 torch.utils.data.DataLoader
trainset = torchvision.datasets.CIFAR10(root='C:/Users/bcl/Desktop/Torch_P/data', train=True,download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,shuffle=True, num_workers=0)
testset = torchvision.datasets.CIFAR10(root='C:/Users/bcl/Desktop/Torch_P/data', train=False,download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,shuffle=False, num_workers=0)

classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')
def imshow(img):
    img = img / 2 + 0.5 # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

 

3. 训练模型并保存训练结果

# 定义网络
net = Net()
# device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# print(device)
#net.to(device)
criterion = nn.CrossEntropyLoss()  # 损失函数
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)  # 优化函数

for epoch in range(2):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        #inputs, labels = data[0].to(device), data[1].to(device)
        inputs, labels = data[0], data[1]
        # zero the parameter gradients
        optimizer.zero_grad()
        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:  # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %(epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)

 

4. 测试训练结果

net = Net()
net.load_state_dict(torch.load("./cifar_net.pth"))
outputs = net(images)
_, predicted = torch.max(outputs, 1)

print("Predicted:",' '.join('%5s'%classes[predicted[j]] for j in range(4)))

# 计算在整个测试集上的准确率
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))

# 测试集中每一类的准确率
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1

for i in range(10):
    print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i] / class_total[i]))