完整的模型训练套路（一、二、三）

搭建神经网络

model

import torch
from torch import nn

#搭建神经网络
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, 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__':
    tudui = Tudui()
    input = torch.ones((64, 3, 32, 32))
    output = tudui(input)
    print(output.size())  # torch.Size([64, 10])

train

import torchvision
from model import *
from torch.utils.data import DataLoader

#准备数据集
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=torchvision.transforms.ToTensor())
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))  # 50000
print("测试数据集的长度为：{}".format(test_data_size))  # 10000
#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)

#创建网络模型
tudui = Tudui()
#损失函数
loss_fn = nn.CrossEntropyLoss()
#优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.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
#训练的轮数
epochs = 10

for epoch in range(epochs):
    print("------第{}轮训练开始------".format(epoch+1))
    #训练步骤开始
    for data in train_dataloader:
        imgs, targets = data
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)

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

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

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

确实每轮有所提升

添加tensorboard

writer = SummaryWriter(log_dir='./logs_train')
writer.add_scalar('train_loss', loss, total_train_step)
writer.add_scalar('test_loss', total_test_loss, total_test_step)
total_test_step += 1
writer.close()

test_loss train_loss

保存模型

torch.save(tudui, "tudui_{}.pth".format(epoch+1))
print('模型已保存')

整体代码

import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter

from model import *
from torch.utils.data import DataLoader

#准备数据集
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=torchvision.transforms.ToTensor())
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))  # 50000
print("测试数据集的长度为：{}".format(test_data_size))  # 10000
#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)

#创建网络模型
tudui = Tudui()
#损失函数
loss_fn = nn.CrossEntropyLoss()
#优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.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
#训练的轮数
epochs = 10

#添加tensorboard
writer = SummaryWriter(log_dir='./logs_train')

for epoch in range(epochs):
    print("------第{}轮训练开始------".format(epoch+1))
    #训练步骤开始
    for data in train_dataloader:
        imgs, targets = data
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)

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

    #测试步骤开始
    total_test_loss = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = tudui(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss
        print("整体测试集上的Loss: {}".format(total_test_loss))
        writer.add_scalar('test_loss', total_test_loss, total_test_step)
        total_test_step += 1

        torch.save(tudui, "tudui_{}.pth".format(epoch+1))
        print('模型已保存')

writer.close()

预测

import torch
outputs = torch.tensor([[0.1, 0.2],
                        [0.3, 0.4]])
print(outputs.argmax(dim=1))  # 取最大值的位置；1横着看， 0竖着看

预测的正确率

import torch

outputs = torch.tensor([[0.1, 0.2],
                        [0.3, 0.4]])
print(outputs.argmax(dim=1))  # 取最大值的位置；1横着看， 0竖着看
preds = outputs.argmax(1)
targets = torch.tensor([0, 1])
print((preds == targets).sum())  # 对应位置相等的个数

对源代码的进行修改（增正确取率）

主要加了这一句，看分类的正确率

total_accuracy += (outputs.argmax(1) == targets).sum()

完整

import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter

from model import *
from torch.utils.data import DataLoader

#准备数据集
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=torchvision.transforms.ToTensor())
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))  # 50000
print("测试数据集的长度为：{}".format(test_data_size))  # 10000
#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)

#创建网络模型
tudui = Tudui()
#损失函数
loss_fn = nn.CrossEntropyLoss()
#优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.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
#训练的轮数
epochs = 10

#添加tensorboard
writer = SummaryWriter(log_dir='./logs_train')

for epoch in range(epochs):
    print("------第{}轮训练开始------".format(epoch+1))
    #训练步骤开始
    for data in train_dataloader:
        imgs, targets = data
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)

        #优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.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, 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
            outputs = tudui(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss
            total_accuracy += (outputs.argmax(1) == targets).sum()

        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 += 1

        torch.save(tudui, "tudui_{}.pth".format(epoch+1))
        print('模型已保存')

writer.close()

正确率是有提升的

（三）细节

tudui.train()
tudui.eval()

并不是这样才能开始，仅对部分层有用，比如Dropout