cifar-10数据集由10个类的60000个32x32彩色图像组成，每个类有6000个图像。有50000个训练图像和10000个测试图像。数据集分为五个训练批次和一个测试批次，每个批次有10000个图像。测试批次包含来自每个类别的恰好1000个随机选择的图像。训练批次以随机顺序包含剩余图像，但一些训练批次可能包含来自一个类别的图像比另一个更多。总体来说，五个训练集之和包含来自每个类的正好5000张图像。
具体：batch2.mat文件，该训练集可以用于图片识别，非负矩阵分解等。(The cifar-10 dataset consists of 60000 32x32 color images of 10 classes, each of which has 6000 images. There are 50000 training images and 10000 test images. The data set is divided into five training batches and one test batch, each batch has 10000 images. The test batch contains exactly 1000 randomly selected images from each category. Training batches contain the remaining images in random order, but some training batches may contain more images from one category than another. Overall, the sum of the five training sets contains exactly 5000 images from each class.
Specific: including 5 batch.mat File and a test file. It can be used for image recognition, nonnegative matrix decomposition and so on.)