数据集

http://www.cs.toronto.edu/~kriz/cifar.html

Baseline results

You can find some baseline replicable results on this dataset on the project page for cuda-convnet. These results were obtained with a convolutional neural network. Briefly, they are 18% test error without data augmentation and 11% with. Additionally, Jasper Snoek has a new paper in which he used Bayesian hyperparameter optimization to find nice settings of the weight decay and other hyperparameters, which allowed him to obtain a test error rate of 15% (without data augmentation) using the architecture of the net that got 18%.

您可以在cuda-convnet的项目页面上找到此数据集上的一些基线可复制结果。 这些结果是用卷积神经网络获得的。 简而言之，它们是18％的测试错误，没有数据增加，11％有。 此外，Jasper Snoek有一篇新论文，他使用贝叶斯超参数优化来找到重量衰减和其他超参数的好设置，这使他能够使用网络的体系结构获得15％的测试错误率（无数据增加） 得到了18％。

Dataset layout布局

Python / Matlab versions

I will describe the layout of the Python version of the dataset. The layout of the Matlab version is identical.

The archive contains the files data_batch_1, data_batch_2, …, data_batch_5, as well as test_batch

. Each of these files is a Python “pickled” object produced with cPickle 文件中的每一个都是使用cPickle生成的Python”pickled”对象

. Here is a python2 routine例程 which will open such a file and return a dictionary:将会打开这样一个文件，并且返回一个字典

def unpickle(file):
    import cPickle
    with open(file, 'rb') as fo:
        dict = cPickle.load(fo)
    return dict

And a python3 version:

def unpickle(file):
    import pickle
    with open(file, 'rb') as fo:
        dict = pickle.load(fo, encoding='bytes')
    return dict

Loaded in this way以这种方式加载, each of the batch files contains a dictionary with the following elements:

• data – a 10000x3072 numpy array of uint8s. Each row of the array stores a 32x32 colour image. The first 1024 entries条目 contain the red channel values, the next 1024 the green, and the final 1024 the blue. The image is stored in row-major order图像以主顺序存储, so that the first 32 entries of the array are the red channel values of the first row of the image.数组的前32个条目是图像第一行的红色通道数
• labels – a list of 10000 numbers in the range 0-9. The number at index i indicates the label of the ith image in the array data. 0-9范围内的10000个数字列表。 索引i处的数字表示阵列数据中第i个图像的标签。

The dataset contains another file, called batches.meta

. It too contains a Python dictionary object. It has the following entries:

• label_names – 十维元素列表-a 10-element list which gives meaningful names to the numeric labels in the labels array described above. For example, label_names[0] == “airplane”, label_names[1] == “automobile”, etc.