dylan1998的博客

训练一个图像分类器1.使用torchvision加载和正则化CIFAR10训练集和测试集2.构造一个CNN3.构造损失函数4.训练网络5.测试网络1. 加载和正规化CIFAR10import torchimport torchvisionimport torchvision.transforms as transformstransform = transforms.Compose( [transforms.ToTenso

import torchimport torch.nn as nnimport torch.nn.functional as Fclass Net(nn.Module): # 括号里的为父类 def __init__(self): # 构造方法 super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 6, 3) # 1个输入，6个输出特征，3x3的卷积核 self.conv2 = n