The CIFAR-10 dataset :http://www.cs.toronto.edu/~kriz/cifar.html 原来为bin格式,我全部转成了png图,让我们对数据集有很好的直观印象。资源太大,分开上传,该部分为测试集部分(test_batch、batches.meta.txt)。剩余部分见http://download.csdn.net/download/qq_24380063/10196039
做cs231n时候的作业上使用到的机器学习分类数据集。 国内下载速度巨慢,而且还需要使用linux系统才能运行那个脚本,因此直接贴在CSDN上。 The CIFAR-10 and CIFAR-100 are labeled subsets of the 80 million tiny images dataset. They were collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton. The CIFAR-10 data
The CIFAR-10 and CIFAR-100 are labeled subsets of the 80 million tiny images dataset. They were collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton. from:http://www.cs.toronto.edu/~kriz/cifar.html
二进制数据集