PyTorch基础完整模型训练套路（土堆老师版）详细注释及讲解！小白学习必看！_python训练模型

目录

1、准备数据集

2、利用dataloader加载数据集

3、创建网络模型

model.py

4、损失函数

5、优化器

6、设置训练网络的参数

7 、添加tensorboard

8 、训练过程并保存模型结构及参数

①  cyx.train()和cyx.eval()

② loss.item()

③ with torch.no_grad():

④ argmax()

 9、关闭writer

完整代码

---

1、准备数据集

# 准备数据集
from torch.utils.data import DataLoader
 
train_data = torchvision.datasets.CIFAR10(root="datasets", train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=False)
 
test_data = torchvision.datasets.CIFAR10(root="datasets", train=False,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=False)
 
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))

2、利用dataloader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

from model import *
cyx = CYX()

model.py

# 搭建神经网络
import torch
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
 
 
class CYX(nn.Module):
    def __init__(self):
        super(CYX, self).__init__()
        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5,
                   padding=2, stride=1),
            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
 
# 验证模型是否成功搭建
 
# if __name__ == '__main__':
#     cyx = CYX()
#     input = torch.ones((64, 3, 32, 32))
#     output = cyx(input)
#     print(output.shape)

4、损失函数

loss_fn = nn.CrossEntropyLoss()

5、优化器

learning_rate = 0.01
optimizer = torch.optim.SGD(cyx.parameters(), lr=learning_rate)

6、设置训练网络的参数

# 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

7 、添加tensorboard

writer = SummaryWriter("logs_train")

8 、训练过程并保存模型结构及参数

for i in range(epoch):
    print("---------第{}轮训练开始---------".format(i+1))
    # 训练步骤开始
    # 只对特定层起作用
    cyx.train()
    for data in train_dataloader:
        imgs, targets = data
        outputs = cyx(imgs)
        loss = loss_fn(outputs, targets)
        # 优化器优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_step = total_train_step + 1
        # 每逢100的时候再打印（好看）
        if total_train_step % 100 == 0:
            # .item()会把tensor里面的变成数字，比如tensor(5)->5
            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
    # 只对特定层起作用
    cyx.eval()
    # 看的是整个数据集的损失
    total_test_loss = 0
    total_accuracy = 0
    # 不累计梯度
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = cyx(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            # 见截图
            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_train_step)
    total_test_step = total_test_step + 1
 
    torch.save(cyx, "cyx_cpu_{}.pth".format(i))
    # torch.save(cyx.state_dict(), "cyx_{}.pth".format(i))
    print("模型已保存")

注意细节：

①  cyx.train()和cyx.eval()

是否启用 Batch Normalization 和 Dropout，分别在训练时和测试时添加。

参考文章：

【Pytorch】model.train() 和 model.eval() 原理与用法

② loss.item()

把tensor里面的变成数字，比如tensor(5)->5

参考文章：

【Pytorch】.item() 方法介绍

③ with torch.no_grad():

with 语句适用于对资源进行访问的场合，确保不管使用过程中是否发生异常都会执行必要的“清理”操作，释放资源，比如文件使用后自动关闭／线程中锁的自动获取和释放等。

因为是测试，不累计梯度

参考文章：

【pytorch】 with torch.no_grad():用法详解

④ argmax()

 9、关闭writer

writer.close()

完整代码

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter
 
from model import *
 
# 准备数据集
from torch.utils.data import DataLoader
 
train_data = torchvision.datasets.CIFAR10(root="datasets", train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=False)
 
test_data = torchvision.datasets.CIFAR10(root="datasets", train=False,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=False)
 
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加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
 
# 创建网络模型
cyx = CYX()
 
# 损失函数
loss_fn = nn.CrossEntropyLoss()
 
# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(cyx.parameters(), lr=learning_rate)
 
# 设置训练网络的参数
# 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
    # 只对特定层起作用
    cyx.train()
    for data in train_dataloader:
        imgs, targets = data
        outputs = cyx(imgs)
        loss = loss_fn(outputs, targets)
        # 优化器优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_step = total_train_step + 1
        # 每逢100的时候再打印（好看）
        if total_train_step % 100 == 0:
            # .item()会把tensor里面的变成数字，比如tensor(5)->5
            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
    # 只对特定层起作用
    cyx.eval()
    # 看的是整个数据集的损失
    total_test_loss = 0
    total_accuracy = 0
    # 不累计梯度
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = cyx(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            # 见截图
            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_train_step)
    total_test_step = total_test_step + 1
 
    torch.save(cyx, "cyx_cpu_{}.pth".format(i))
    # torch.save(cyx.state_dict(), "cyx_{}.pth".format(i))
    print("模型已保存")
writer.close()