完整地模型训练套路

import torch.optim
import torchvision.datasets
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

# dataset, input
train_data = torchvision.datasets.CIFAR10(root='../dataset', train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)

test_data = torchvision.datasets.CIFAR10(root='../dataset', train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)

# 输出数据集长度
train_data_size = len(train_data)
print("训练数据集的长度为: {}".format(train_data_size))

test_data_size = len(test_data)
print("测试数据集的长度为: {}".format(test_data_size))

# dataloader
train_dataloader = DataLoader(dataset=train_data, batch_size=64)
test_dataloader = DataLoader(dataset=test_data, batch_size=64)

# 搭建神经网络
class Tao(nn.Module):
    def __init__(self):
        super(Tao, self).__init__()
        self.model = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(in_features=64 * 4 * 4, out_features=64),
            Linear(in_features=64, out_features=10)
        )

    def forward(self, x):
        x = self.model(x)
        return x

# 创建网络模型
tao = Tao()

# 创建损失函数
loss_fn = nn.CrossEntropyLoss()

# 定义优化器
learning_rate = 1e-4
optim = torch.optim.SGD(tao.parameters(), lr=learning_rate) # 随机梯度下降

# 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

# 使用tensorboard记录
writer = SummaryWriter('../logs_train')

for i in range(epoch):
    print("-----第{}轮训练开始-----".format(i+1))

    # 训练步骤开始
    for data in train_dataloader:
        imgs, targets = data
        output = tao(imgs)
        loss = loss_fn(output, targets)  # 计算损失值

        # 优化器优化模型
        loss_fn.zero_grad()  # 梯度清零
        loss.backward()  # 损失值进行反向传播
        optim.step()  # 优化器进行优化模型

        total_train_step += 1

        if total_train_step % 100 == 0:
            print("训练次数: {}, Loss: {}".format(total_train_step, loss.item()))  # item()挺好用的, 去掉类型, 只保留值
            writer.add_scalar('train_loss', loss.item(), total_train_step)

    # 测试步骤开始
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            output = tao(imgs)
            loss = loss_fn(output, targets)
            total_test_loss += loss.item()

            # 添加正确率判断 argmax(1):横向, argmax(0):纵向
            accuracy = (output.argmax(1) == targets).sum()
            total_accuracy += accuracy
    print("整体测试集上的Loss: {}".format(total_test_loss))
    print("整体测试集上面的正确率：{}".format(total_accuracy / test_data_size))
    writer.add_scalar('test_loss', total_test_loss, total_test_step)
    writer.add_scalar('test_accuracy', total_accuracy / test_data_size, total_test_step)
    total_test_step += 1

    # 保存模型
    torch.save(tao.state_dict(), 'tao_{}.pth'.format(i))
    print('模型已保存')

writer.close()