完整的模型训练套路

检查网络正确性： 

class Suibao(nn.Module):
    def __init__(self):
        super(Suibao, 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


if __name__ == '__main__':
    suibao = Suibao()
    input = torch.ones((64, 3, 32, 32))
    output = suibao(input)
    print(output.shape)



output: torch.Size([64, 10]) #代表64张图片，在10个分类上的概率

训练模型：

from model import *
import torchvision
from torch import nn
from torch.utils.data import DataLoader
#准备数据集
train_data = torchvision.datasets.CIFAR10(root="D:\\Myproject\\pytorch-tutorial\\data", train=True,
                                          transform=torchvision.transforms.ToTensor(), download=True)

test_data = torchvision.datasets.CIFAR10(root="D:\\Myproject\\pytorch-tutorial\\data", train=False,
                                         transform=torchvision.transforms.ToTensor(), download=True)

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

#利用 Dataloader 加载数据集
train_data_loader = DataLoader(train_data, batch_size=64)
test_data_loader = DataLoader(test_data, batch_size=64)

#创建网络模型
suibao = Suibao()

#损失函数
loss_fn = nn.CrossEntropyLoss()

#优化器
#learning_rate = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(suibao.parameters(), lr=learning_rate)

#设置训练网络的一些参数
#记录训练次数
total_train_step = 0
#记录测试次数
total_test_step = 0
#训练轮数
epoch = 10

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_data_loader:
        imgs, targets = data
        outputs = suibao(imgs)
        loss = loss_fn(outputs, targets)

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

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

测试数据：

#测试步骤开始
    total_test_loss = 0
    with torch.no_grad():
        for data in train_data_loader:
            imgs, targets = data
            outputs = suibao(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
    print("整体测试集上的Loss：{}".format(total_test_loss))

添加SummaryWriter和正确率后的整体代码：

from torch.utils.tensorboard import SummaryWriter

from model import *
import torchvision
from torch import nn
from torch.utils.data import DataLoader
#准备数据集
train_data = torchvision.datasets.CIFAR10(root="D:\\Myproject\\pytorch-tutorial\\data", train=True,
                                          transform=torchvision.transforms.ToTensor(), download=True)

test_data = torchvision.datasets.CIFAR10(root="D:\\Myproject\\pytorch-tutorial\\data", train=False,
                                         transform=torchvision.transforms.ToTensor(), download=True)

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

#利用 Dataloader 加载数据集
train_data_loader = DataLoader(train_data, batch_size=64)
test_data_loader = DataLoader(test_data, batch_size=64)

#创建网络模型
suibao = Suibao()

#损失函数
loss_fn = nn.CrossEntropyLoss()

#优化器
#learning_rate = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(suibao.parameters(), lr=learning_rate)

#设置训练网络的一些参数
#记录训练次数
total_train_step = 0
#记录测试次数
total_test_step = 0
#训练轮数
epoch = 10

#添加tensorboard
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
    suibao.train()
    for data in train_data_loader:
        imgs, targets = data
        outputs = suibao(imgs)
        loss = loss_fn(outputs, targets)

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

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

    #测试步骤开始
    suibao.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in train_data_loader:
            imgs, targets = data
            outputs = suibao(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.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(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 = total_test_step + 1

    torch.save(suibao, "suibao_{}.pth".format(i))
    print("模型已保存")

writer.close()