说明：  如果刚接触深度学习，快速而轻松的入门方法是使用现有网络，比如 AlexNet，用一百多万张图像训练好的 CNN。AlexNet 最常用于图像分类。它可将图像划分为 1000 个不同的类别，包括键盘、鼠标、铅笔和其他办公设备，以及各个品种的狗、猫、马和其他动物。
(If you're new to in-depth learning, a quick and easy way to get started is to use an existing network such as AlexNet, a CNN trained with more than a million images. AlexNet is most commonly used in image classification. It divides images into 1,000 different categories, including keyboards, mice, pencils and other office equipment, as well as various breeds of dogs, cats, horses and other animals.)