p29完整的模型训练套路3

细节

需要设置是train还是eval模式

 # 训练步骤开始
    lixinyu.train()   ####
     # 测试步骤开始
    lixinyu.eval()  #####

# 准备数据集
import torch.optim
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from model import *

train_data = torchvision.datasets.CIFAR10("./dataset", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)
# length
train_data_size = len(train_data)
test_data_siz = len(test_data)
print(f"训练数据集的长度为：{train_data_size}")
print(f"测试数据集的长度为：{test_data_siz}")

# 利用DataLoader加载
train_data_loader = DataLoader(train_data, batch_size=256)
test_data_loader = DataLoader(test_data, batch_size=256)

# 创建网络模型
lixinyu = Lixinyu()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
# learning_rate = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(lixinyu.parameters(), learning_rate)

# 设置训练网络参数
# 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
epoch = 5

# 添加tensorboard
writer = SummaryWriter("p28")

for i in range(epoch):
    print(f"--------------------第{i+1}轮训练开始了-----------------")

    # 训练步骤开始
    lixinyu.train()   ####
    for data in train_data_loader:
        imgs, targets = data
        output = lixinyu(imgs)
        loss = loss_fn(output, targets)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_step += 1
        if total_train_step % 100 == 0:
            print(f"训练次数{total_train_step} 损失值{loss.item()}")  # loss.item()标准写法，这里直接写loss也行
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    lixinyu.eval()  #####
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_data_loader:
            imgs, targets = data
            outputs = lixinyu(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(f'整体测试loss为：{total_test_loss}')
    print(f'整体测试数据集上的正确率：{total_accuracy/test_data_siz}')
    writer.add_scalar("total_test_loss", total_test_loss, total_test_step)
    writer.add_scalar("total_accuracy", total_accuracy/test_data_siz, total_test_step)
    total_test_step = total_test_step + 1
    torch.save(lixinyu, f"lixinyu_epoch{i}.pth")
    print("模型已保存")

writer.close()

是因为

准备数据，加载数据，准备模型，设置损失函数，设置优化器,设置训练参数，训练，测试，结果聚合展示

# 准备数据集
import torch.optim
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from model import *

train_data = torchvision.datasets.CIFAR10("./dataset", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)
# length
train_data_size = len(train_data)
test_data_siz = len(test_data)
print(f"训练数据集的长度为：{train_data_size}")
print(f"测试数据集的长度为：{test_data_siz}")

# 利用DataLoader加载
train_data_loader = DataLoader(train_data, batch_size=256)
test_data_loader = DataLoader(test_data, batch_size=256)

# 创建网络模型
lixinyu = Lixinyu()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
# learning_rate = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(lixinyu.parameters(), learning_rate)

# 设置训练网络参数
# 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
epoch = 5

# 添加tensorboard
writer = SummaryWriter("p28")

for i in range(epoch):
    print(f"--------------------第{i+1}轮训练开始了-----------------")

    # 训练步骤开始
    lixinyu.train()   ####
    for data in train_data_loader:
        imgs, targets = data
        output = lixinyu(imgs)
        loss = loss_fn(output, targets)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_step += 1
        if total_train_step % 100 == 0:
            print(f"训练次数{total_train_step} 损失值{loss.item()}")  # loss.item()标准写法，这里直接写loss也行
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    lixinyu.eval()  #####
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_data_loader:
            imgs, targets = data
            outputs = lixinyu(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(f'整体测试loss为：{total_test_loss}')
    print(f'整体测试数据集上的正确率：{total_accuracy/test_data_siz}')
    writer.add_scalar("total_test_loss", total_test_loss, total_test_step)
    writer.add_scalar("total_accuracy", total_accuracy/test_data_siz, total_test_step)
    total_test_step = total_test_step + 1
    torch.save(lixinyu, f"lixinyu_epoch{i}.pth")
    # torch.save(lixinyu.state_dict(), f"lixinyu_{i}.pth")
    print("模型已保存")

writer.close()