完整的模型训练套路

model.py文件：

# -*- coding: utf-8 -*-
# @Author  : XZC
# @Time    : 2022/12/5 12:14
import torch
from torch import nn

# 搭建神经网络
class XZC(nn.Module):
    def __init__(self):
        super(XZC, self).__init__()
        self.model=nn.Sequential(
            # in_channels,out_channels,kernel_size,stride,padding
            nn.Conv2d(3,32,5,1,2),
            nn.MaxPool2d(2),
            nn.Conv2d(32,32,3,1,2),
            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__':
    xzc=XZC()
    input=torch.ones((64,3,32,32))
    output=xzc(input)
    print(output.shape)

 train.py文件：

# -*- coding: utf-8 -*-
# @Author  : XZC
# @Time    : 2022/12/5 11:49
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from model import *
# 准备数据集
train_data=torchvision.datasets.CIFAR10(root='data',train=True,transform=torchvision.transforms.ToTensor(),
                                        download=True)
test_data=torchvision.datasets.CIFAR10(root='data',train=False,transform=torchvision.transforms.ToTensor(),
                                        download=True)
# length 长度
train_data_size=len(train_data)
test_data_size=len(test_data)
print("训练数据集的长度:{}".format(train_data_size))
print("测试数据集的长度:{}".format(test_data_size))

# 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)

# 搭建神经网络,model.py文件

# 创建网络模型
xzc=XZC()

# 损失函数
loss_fn=nn.CrossEntropyLoss()

# 优化器
learning_rate=0.01
optimizer=torch.optim.SGD(xzc.parameters(),lr=learning_rate)

# 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
# 记录训练的轮数
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
    # xzc.train()
    for data in train_dataloader:
        imgs,targets=data
        outputs=xzc(imgs)
        # 计算真实值与目标值之间的误差
        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
        # loss.item()将值转换成真实数字
        if total_train_step%100==0:
            print("训练次数:{},loss:{}".format(total_train_step,loss.item()))
            writer.add_scalar("train_loss",loss.item(),total_train_step)

    # 测试步骤开始
    # xzc.eval()
    total_test_loss=0
    total_accuracy=0
    with torch.no_grad():
        for data in test_dataloader:
            imgs,targets=data
            outputs=xzc(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

    #保存每一轮的模型
    torch.save(xzc,"xzc_{}.pth".format(i))
    print("模型已保存")

writer.close()