torch之训练过程

torch之训练过程train()

1.cpu版本

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

# 1.准备数据集
train_data = torchvision.datasets.CIFAR10(root='./dataset', train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root='./dataset', train=False, transform=torchvision.transforms.ToTensor(),
                                          download=True)
# length
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

#加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 2.搭建神经网络(model.py)
# 3.创建网络模型
firstmodel = FirstModel()
# 4.创建损失函数
loss_fn = nn.CrossEntropyLoss()
#5.优化器
learning_rate = 0.01
optimzer = torch.optim.SGD(params=firstmodel.parameters(), lr=learning_rate)

# 6.设置训练网络的一些参数
# 记录训练次数
total_train_step = 0
# 记录训练次数
total_test_step = 0
# 记录训练轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("./logs")
for i in range(epoch):
    print("—————————————第{}轮训练开始————————————".format(i + 1))

    # 训练步骤开始
    firstmodel.train()
    for data in train_dataloader:
        imgs, targets = data
        outputs = firstmodel(imgs)
        loss = loss_fn(outputs, targets)
        # 优化器优化模型
        optimzer.zero_grad()
        loss.backward()
        optimzer.step()

        total_train_step += 1
        if total_train_step % 100 == 0:
            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
    firstmodel.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = firstmodel(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("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
    # 模型保存——>方式一
    torch.save(firstmodel, "firstmodel_{}.pth".format(i))
    # 方式二:
    # torch.save(firstmodel.state_dict(), "firstmodel_{}.pth".format(i))
    print("模型已保存")
    writer.close()

2.gpu版本

import torch
import torchvision
from torch import nn
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader

# 1.准备数据集
# 定义训练设备
# device = torch.device("cuda")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
train_data = torchvision.datasets.CIFAR10(root='./dataset', train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root='./dataset', train=False, transform=torchvision.transforms.ToTensor(),
                                          download=True)
# length
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

#加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 2.搭建神经网络(model.py)
class FirstModel(nn.Module):
    def __init__(self):
        super(FirstModel, 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
# 3.创建网络模型
firstmodel = FirstModel()
firstmodel = firstmodel.to(device)
# 4.创建损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
#5.优化器
learning_rate = 0.01
optimzer = torch.optim.SGD(params=firstmodel.parameters(), lr = learning_rate)

# 6.设置训练网络的一些参数
# 记录训练次数
total_train_step = 0
# 记录训练次数
total_test_step = 0
# 记录训练轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("./logs")
for i in range(epoch):
    print("—————————————第{}轮训练开始————————————".format(i + 1))

    # 训练步骤开始
    firstmodel.train()
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = firstmodel(imgs)
        loss = loss_fn(outputs, targets)
        # 优化器优化模型
        optimzer.zero_grad()
        loss.backward()
        optimzer.step()

        total_train_step += 1
        if total_train_step % 100 == 0:
            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
    firstmodel.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = firstmodel(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("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
    # 模型保存——>方式一
    torch.save(firstmodel, "firstmodel_{}.pth".format(i))
    # 方式二:
    # torch.save(firstmodel.state_dict(), "firstmodel_{}.pth".format(i))
    print("模型已保存")
    writer.close()