第一个GPU训练程序_init gpu first-优快云博客

本文链接：https://blog.youkuaiyun.com/mez_Blog/article/details/120153740

本文介绍了一个使用PyTorch实现的CIFAR-10图像分类模型，详细步骤包括数据预处理、模型定义、训练过程、损失函数和评估指标。展示了如何使用GPU加速训练，并用TensorBoard记录训练进度和测试结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import time

import torchvision
import torch
from torch.utils.tensorboard import SummaryWriter
from torch import nn
from torch.utils.data import DataLoader
class Test(nn.Module):
    def __init__(self):
        super(Test, 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__':
    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("测试数据集的长度为：{}".format(test_data_size))
    train_dataloader=DataLoader(train_data,batch_size=64)
    test_dataloader=DataLoader(test_data,batch_size=64)
    test=Test()
    test=test.cuda()
    loss_fn=nn.CrossEntropyLoss()
    loss_fn=loss_fn.cuda()
    optimizer=torch.optim.SGD(test.parameters(),lr=0.01)
    total_train_step=0
    total_test_step=0
    epoch=10
    writer=SummaryWriter("./logs_train")
    for i in range(epoch):
        start=time.time()
        print("**********第{}轮训练开始*********".format(i+1))
        test.train()
        for data in train_dataloader:
            imgs,targets=data
            imgs=imgs.cuda()
            targets=targets.cuda()
            outputs=test(imgs)
            loss=loss_fn(outputs,targets)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            total_train_step=total_train_step+1
            if total_train_step%100==0:
                end=time.time()
                print("训练时间为：",end-start)
                print("训练次数: {},loss:{}".format(total_train_step,loss.item()))
                writer.add_scalar("train_loss",loss.item(),total_train_step)
        test.eval()
        total_test_loss=0
        total_accuracy=0
        with torch.no_grad():
            for data in test_dataloader:
                imgs,targets=data
                imgs=imgs.cuda()
                targets=targets.cuda()
                outputs=test(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)
        total_test_step=total_test_step+1
        torch.save(test,"test_{}.pth".format(i))
        print("模型已保存")
    writer.close()

运行结果：