pytorch 深度学习框架

# 定义网络
net = Net()

# 定义数据
#数据预处理，1.转为tensor，2.归一化
transform = transforms.Compose(    
     [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 训练集
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)
# 验证集
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=2)

# 定义损失函数和优化器 
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

# 开始训练
net.train()
for epoch in range(2):  # loop over the dataset multiple times
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data
        # 将梯度置为0
        # zero the parameter gradients
        optimizer.zero_grad()
        # 求loss
        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        # 梯度反向传播
        loss.backward()
        # 由梯度，更新参数
        optimizer.step()

        # 可视化
        # 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

# 查看在验证集上的效果
dataiter = iter(testloader)
images, labels = dataiter.next()

# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))

net.eval()
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                              for j in range(4)))

作者：石郎
链接：https://www.zhihu.com/question/406133826/answer/1334319004
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。