Pytorch学习--神经网络--完整的模型训练套路

love_and_hope2024-11-12 22:52

一、下载数据集

python 复制代码 
train_data = torchvision.datasets.CIFAR10(root="datasets",train=True,transform=torchvision.transforms.ToTensor(),download=True)
train_data = torchvision.datasets.CIFAR10(root="datasets",train=False,transform=torchvision.transforms.ToTensor(),download=True)

二、数据大小

python 复制代码 
train_data_len = len(train_data)
test_data_len = len(test_data)
print(train_data_len)
print(test_data_len)

三、数据加载

python 复制代码 
train = DataLoader(train_data,batch_size=64)
test = DataLoader(test_data,batch_size=64)

四、模型定义

python 复制代码 
class Mary(nn.Module):
    def __init__(self):
        super(Mary,self).__init__()
        self.model1 = nn.Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )
    def forward(self,x):
        x = self.model1(x)
        return x

五、定义对象

python 复制代码 
Yorelee = Mary()

六、损失函数

python 复制代码 
loss_fn = nn.CrossEntropyLoss()

七、优化器

python 复制代码 
learning_rate = 0.01
optimizer = torch.optim.SGD(Yorelee.parameters(),lr=learning_rate)

八、训练过程

python 复制代码 
epoch = 10
for i in range(epoch):
    print("***********第{}轮训练***********".format(i+1))
    index = 1
    for data in train:
        imgs,targets = data
        output = Yorelee(imgs)
        loss = loss_fn(output,targets)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        print("({}) ".format(index),loss.item())
        index += 1

九、训练过程+测试过程

python 复制代码 
# 训练过程
epoch = 10
for i in range(epoch):
    print("***********第{}轮训练***********".format(i+1))
    index = 1
    for data in train:
        imgs,targets = data
        output = Yorelee(imgs)
        loss = loss_fn(output,targets)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        print("({}) ".format(index),loss.item())
        index += 1

    #测试过程
    total_loss = 0
    with torch.no_grad():
        for data in test:
            imgs,targets = data
            output = Yorelee(imgs)
            loss = loss_fn(output,targets)
            total_loss += loss
    print("测试： ",total_loss.item())

十、Tensorboard 可视化

python 复制代码 
#  Tensorboard 可视化
writer = SummaryWriter("logs")

# 训练过程
epoch = 10
for i in range(epoch):
    print("***********第{}轮训练***********".format(i+1))
    index = 1
    for data in train:
        imgs,targets = data
        output = Yorelee(imgs)
        loss = loss_fn(output,targets)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        print("({}) ".format(index),loss.item())
        if index % 100 == 0:
            writer.add_scalar("train_loss",loss,index)
        index += 1

    #测试过程
    total_loss = 0
    with torch.no_grad():
        for data in test:
            imgs,targets = data
            output = Yorelee(imgs)
            loss = loss_fn(output,targets)
            total_loss += loss
    print("测试： ",total_loss.item())
    writer.add_scalar("test_loss", total_loss, i)
writer.close()

十一、对于分类任务

可以用准确率来衡量，而不是用 total_loss 来衡量效果

先来举个简单的例子：


代码如下：

python 复制代码 
import torch

output = torch.tensor([[0.1,0.2],
                       [0.3,0.4]])
output = torch.argmax(output,dim=1)
preds = torch.tensor([0,1])
print((output==preds).sum())

输出：

python 复制代码 
tensor(1)

十二、对测试过程的重新改进

python 复制代码 
#  Tensorboard 可视化
writer = SummaryWriter("logs")

# 训练过程
epoch = 10
for i in range(epoch):
    print("***********第{}轮训练***********".format(i+1))
    index = 1
    for data in train:
        imgs,targets = data
        output = Yorelee(imgs)
        loss = loss_fn(output,targets)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        print("({}) ".format(index),loss.item())
        if index % 100 == 0:
            writer.add_scalar("train_loss",loss,index)
        index += 1

    #测试过程
    total_loss = 0
    with torch.no_grad():
        find_true = 0
        for data in test:
            imgs,targets = data
            output = Yorelee(imgs)
            # loss = loss_fn(output,targets)
            # total_loss += loss
            output = torch.argmax(output,dim=1)
            find_true += (output == targets).sum()
    print("测试： ",find_true/test_data_len.item())
    writer.add_scalar("test_loss", find_true/test_data_len, i)

十三、总结

model.py

python 复制代码 
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear


class Mary(nn.Module):
    def __init__(self):
        super(Mary,self).__init__()
        self.model1 = nn.Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )
    def forward(self,x):
        x = self.model1(x)
        return x

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

train.py

python 复制代码 
import torch
import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from model import *

# 数据集
train_data = torchvision.datasets.CIFAR10(root="datasets",train=True,transform=torchvision.transforms.ToTensor(),download=True)
test_data = torchvision.datasets.CIFAR10(root="datasets",train=False,transform=torchvision.transforms.ToTensor(),download=True)

# 数据大小
train_data_len = len(train_data)
test_data_len = len(test_data)
print(train_data_len)
print(test_data_len)

# 数据加载
train = DataLoader(train_data,batch_size=64)
test = DataLoader(test_data,batch_size=64)

# 定义对象
Yorelee = Mary()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

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

#  Tensorboard 可视化
writer = SummaryWriter("logs")

# 训练过程
epoch = 10
for i in range(epoch):
    print("***********第{}轮训练***********".format(i+1))
    index = 1
    for data in train:
        imgs,targets = data
        output = Yorelee(imgs)
        loss = loss_fn(output,targets)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        print("({}) ".format(index),loss.item())
        if index % 100 == 0:
            writer.add_scalar("train_loss",loss,index)
        index += 1

    #测试过程
    total_loss = 0
    with torch.no_grad():
        find_true = 0
        for data in test:
            imgs,targets = data
            output = Yorelee(imgs)
            # loss = loss_fn(output,targets)
            # total_loss += loss
            output = torch.argmax(output,dim=1)
            find_true += (output == targets).sum()
    print("测试： ",find_true/test_data_len.item())
    writer.add_scalar("test_loss", find_true/test_data_len, i)
writer.close()

十四、XX.train() 和 XX.eval() 的说明



相关推荐
周树皮不皮22 分钟前
20250704【翻转&二叉树】|Leetcodehot100之226【pass】&今天计划
python
魔芋红茶22 分钟前
spring-initializer
python·学习·spring
喜欢吃豆27 分钟前
快速手搓一个MCP服务指南（九）： FastMCP 服务器组合技术：构建模块化AI应用的终极方案
服务器·人工智能·python·深度学习·大模型·github·fastmcp
星融元asterfusion34 分钟前
基于路径质量的AI负载均衡异常路径检测与恢复策略
人工智能·负载均衡·异常路径
一个天蝎座 白勺 程序猿34 分钟前
Python（28）Python循环语句指南：从语法糖到CPython字节码的底层探秘
开发语言·python
zskj_zhyl39 分钟前
智慧养老丨从依赖式养老到自主式养老：如何重构晚年生活新范式
大数据·人工智能·物联网
创小匠40 分钟前
创客匠人视角下创始人 IP 打造与知识变现的底层逻辑重构
人工智能·tcp/ip·重构
西岭千秋雪_1 小时前
Redis性能优化
数据库·redis·笔记·学习·缓存·性能优化
随便取个六字1 小时前
GIT操作 学习
git·学习
热门推荐
012024年 最新 iPhone手机 历代机型、屏幕尺寸、纵横比、分辨率 整理02Coze实战第13讲：飞书多维表格读取+豆包生图模型，轻松批量生成短剧封面03Coze扣子平台完整体验和实践（附国内和国际版对比）04MIUI显示/隐藏5G开关的方法，信号弱时开启手机Wifi通话方法05手机电脑之间快速传输图片视频文件，不压缩画质、不限制大小的方法！06扣子（coze）实战|我用扣子搭建了一个自动分析小红薯笔记内容的AI应用|详细步骤拆解07Word粘贴时出现“运行时错误53,文件未找到：MathPage.WLL“的解决方案08华为昇腾 910B 部署 DeepSeek-R1 蒸馏系列模型详细指南09DeepSeek各版本说明与优缺点分析10微软账户和本地账户有什么区别？如何切换登录账户？