【土堆pytorch实战】P27-29 完整模型训练套路

P27

from model import *
import torchvision
#准备数据集
from torch import nn
from torch.utils.data import DataLoader

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)

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("测试数据的长度为：{}".format(test_data_size))

#利用dataloader加载数据集
train_loader=DataLoader(train_data,batch_size=64)
test_loader=DataLoader(test_data,batch_size=64)

#创建网络模型
mob=Mob()

#损失函数
loss_function=nn.CrossEntropyLoss()
#优化器
learning_rate=0.01
optimizer=torch.optim.SGD(mob.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
#记录测试的次数
total_test_step=0
#训练的轮数
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_loader:
        imgs,targets=data
        outputs=mob(imgs)
        loss=loss_function(outputs,targets)

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

        total_train_step=total_train_step+1
        print("训练次数：{}，loss:{}".format(total_train_step,loss.item()))

P28使用tensorboard

from torch.utils.tensorboard import SummaryWriter

from model import *
import torchvision
#准备数据集
from torch import nn
from torch.utils.data import DataLoader

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)

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("测试数据的长度为：{}".format(test_data_size))

#利用dataloader加载数据集
train_loader=DataLoader(train_data,batch_size=64)
test_loader=DataLoader(test_data,batch_size=64)

#创建网络模型
mob=Mob()

#损失函数
loss_function=nn.CrossEntropyLoss()
#优化器
learning_rate=0.01
optimizer=torch.optim.SGD(mob.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
#记录测试的次数
total_test_step=0
#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
    for data in train_loader:
        imgs,targets=data
        outputs=mob(imgs)
        loss=loss_function(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:  #每100次打印一次
            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
    total_test_loss=0
    with torch.no_grad():  #没有梯度 ---不会调优
        for data in test_loader:
            imgs,targets=data
            outputs=mob(imgs)
            loss=loss_function(outputs,targets)
            total_test_loss=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=total_test_step+1

    torch.save(mob,"mob_{}.pth".format(i))
    print("模型已保存")
writer.close()

P29 增加准确率

from torch.utils.tensorboard import SummaryWriter

from model import *
import torchvision
#准备数据集
from torch import nn
from torch.utils.data import DataLoader

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)

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("测试数据的长度为：{}".format(test_data_size))

#利用dataloader加载数据集
train_loader=DataLoader(train_data,batch_size=64)
test_loader=DataLoader(test_data,batch_size=64)

#创建网络模型
mob=Mob()

#损失函数
loss_function=nn.CrossEntropyLoss()
#优化器
learning_rate=0.01
optimizer=torch.optim.SGD(mob.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
#记录测试的次数
total_test_step=0
#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
    for data in train_loader:
        imgs,targets=data
        outputs=mob(imgs)
        loss=loss_function(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:  #每100次打印一次
            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
    total_test_loss=0
    total_accuracy=0
    with torch.no_grad():  #没有梯度 ---不会调优
        for data in test_loader:
            imgs,targets=data
            outputs=mob(imgs)
            loss=loss_function(outputs,targets)
            total_test_loss=total_test_loss+loss
            accuracy=(outputs.argmax(1)==targets).sum()    #argmax(1) 横向
            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_accuarcy",total_accuracy/test_data_size,total_test_step)
    total_test_step=total_test_step+1

    torch.save(mob,"mob_{}.pth".format(i))
    print("模型已保存")
writer.close()

model.py

# 搭建神经网络
import torch
from torch import nn


class Mob(nn.Module):
    def __init__(self):
        super(Mob, 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__":
    mob=Mob()
    input=torch.ones((64,3,32,32))
    output=mob(input)
    print(output.shape)