深度学习之完整网络模型的搭建

1，准备数据集（以CIFAR10为例）

train_data = torchvision.datasets.CIFAR10("../data", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)

（补充）计算数据集的长度用len()

train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练集的长度为：".format(train_data_size))
print("测试集的长度为：".format(test_data_size))

 2,利用dataloader来加载数据集

train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

3，创建网络模型

class Sjwl(nn.Module):
    def __init__(self):
        super(Sjwl, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64 * 4 * 4, 64),
            nn.Linear(64, 10)

        )

    def forward(self, x):
        x = self.model(x)
        return x
4，使用损失函数，这里使用的是交叉熵损失函数

loss_fountion = nn.CrossEntropyLoss()

 5，使用优化器

learnspeed = 0.01
optim = torch.optim.SGD(sjwl.parameters(), lr=learnspeed)

6，设置训练网络的一些参数

# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10
#添加tensorboard
writer=SummaryWriter("../logs_train")

7，训练步骤的开始

for i in range(epoch):
    print("-----第{}轮训练开始------".format(i + 1))
    # 训练步骤的开始
    for data in train_dataloader:
        imgs, targets = data
        output = sjwl(imgs)
        loss = loss_fountion(output, targets)

        # 优化器优化模型
        optim.zero_grad()
        loss.backward()
        optim.step()

        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            print("训练次数为{}时，Loss：{}".format(total_train_step, loss.item()))
        writer.add_scalar("train_loss",loss.item(),total_train_step)

8，测试步骤的开始

 # 测试步骤的开始
    total_test_loss = 0
    total_accuracy=0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            output = sjwl(imgs)
            loss = loss_fountion(output, targets)
            total_test_loss = total_test_loss + loss.item()
            #计算正确率的次数
            accuracy=(output.argmax(1)==targets).sum()
            total_accuracy=total_accuracy+accuracy
    print("整体测试集上的loss:{}".format(total_test_loss))
    print("整体测试集上的正确率：{}".format(accuracy))
    writer.add_scalar("test_loss",total_test_loss,total_test_step)
    writer.add_scalar("test_accuracy",accuracy,total_test_step )
    total_test_step=total_test_step+1
    torch.save(sjwl,"sjwl_{}.pth".format(i))
    print("模型已保存")
writer.close()

其中还使用了tensorboard，并且还可以进行网络模型的保存