pytorch基本的模型训练流程（GPU）

Ling_Ze

已于 2024-04-21 17:43:59 修改

阅读量232

点赞数 4

CC 4.0 BY-SA版权

分类专栏：深度学习 pytorch 文章标签：深度学习人工智能

于 2024-04-21 17:43:23 首次发布

本文链接：https://blog.youkuaiyun.com/Ling_Ze/article/details/138039775

深度学习同时被 2 个专栏收录

12 篇文章

订阅专栏

pytorch

1 篇文章

订阅专栏

本文介绍了如何使用PyTorch库在CIFAR-10数据集上构建、训练一个简单的卷积神经网络，并使用TensorBoard进行训练过程的可视化。包括数据预处理、模型定义、损失函数和优化器的选择，以及训练和测试的详细步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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

# 定义训练的设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# device = torch.device("cpu")

train_data = torchvision.datasets.CIFAR10('./dataset', train=True, download=True,
                                          transform=torchvision.transforms.ToTensor())

test_data = torchvision.datasets.CIFAR10('./dataset', 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：", train_data_size)
print("测试数据集的长度为：", test_data_size)

# 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
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

tudui = TuDui()
tudui = tudui.to(device)

# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)

# 优化器
# learning_rate = 0.01
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
epoch = 10

# 打开logs中的文件夹 tensorboard --logdir=logs --port=6007
# 添加tensorboard
writer = SummaryWriter('./logs_train')
start_time = time.time()
for i in range(epoch):
    print('----------第 {} 轮训练开始----------'.format(i + 1))

    # 训练步骤开始
    tudui.train()
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        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:
            end_time = time.time()
            print(end_time - start_time)
            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：
    tudui.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 = tudui(imgs)
            loss_test = loss_fn(outputs, targets)
            total_test_loss += loss_test.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            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

    torch.save(tudui, 'tudui_{}.pth'.format(i))
    # torch.save(tudui.state_dict(), 'tudui_{}.pth'.format(i))
    print('模型已保存')

writer.close()