pytorch入门16：优化器的使用_cobyla pytorch-优快云博客

本文链接：https://blog.youkuaiyun.com/qq_42360017/article/details/123775406

本文介绍了一个使用PyTorch实现的CIFAR10图像分类模型。该模型包含多个卷积层和全连接层，并使用了SGD优化器和交叉熵损失函数进行训练。通过对CIFAR10数据集进行训练，展示了模型的基本结构和训练流程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import torch.optim
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10('./torchvision_dataset',train=False,download=False,transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset,batch_size=64,drop_last=True)


class Zkl(nn.Module):
    def __init__(self):
        super(Zkl, self).__init__()
        # self.conv1 = Conv2d(3,32,5,padding=2)
        # self.maxpool1 = MaxPool2d(2)
        # self.conv2 = Conv2d(32,32,5,padding=2)
        # self.maxpool2 = MaxPool2d(2)
        # self.conv3 = Conv2d(32,64,5,padding=2)
        # self.maxpool3 = MaxPool2d(2)
        # self.flatten = Flatten()
        # self.linear1 = Linear(1024,64)
        # self.linear2 = Linear(64,10)

        self.modle1 = nn.Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64,10)
        )

    def forward(self,x):
        # x = self.conv1(x)
        # x = self.maxpool1(x)
        # x = self.conv2(x)
        # x = self.maxpool2(x)
        # x = self.conv3(x)
        # x = self.maxpool3(x)
        # x = self.flatten(x)
        # x = self.linear1(x)
        # x = self.linear2(x)
        x = self.modle1(x)
        return x
#引用类
zkl = Zkl()
#定义损失函数
loss = nn.CrossEntropyLoss()
#定义优化器
optim = torch.optim.SGD(zkl.parameters(),lr=0.1)
for epoch in range(20):
    running_loss = 0.0
    for data in dataloader:
        #获取输入特征和输入标签
        imgs,targets = data
        #将输入放入模型，获取输出
        output = zkl(imgs)
        #再通过损失函数获取损失值
        loss_cro = loss(output,targets)  # 两个参数为实际输出和目标输出
        #loss_cro.backward()  # 梯度下降法
        #为防止梯度累积，每一次循环都要将每个节点对应的梯度归为0，上一次循环计算出来的梯度对这一次循环没有用
        optim.zero_grad()
        #再获取每个参数可以调节的梯度
        loss_cro.backward()
        #再对每个参数进行调优
        optim.step()
        #最后打印每一次训练的损失值，观察是否在缩小
        #print(loss_cro)
        running_loss += loss_cro
    print(running_loss)