在python中读取(SVHN)数据集

Question

我想用python阅读以下数据集:http://ufldl.stanford.edu/housenumbers/train_32x32.mat

我使用io.loadmat('train_32x32.mat')加载了这个mat文件但是当我试图显示上面numpy数组的图像时,我没有得到具有良好分辨率和着色的图像.

知道如何从这个数据集中读取和绘制图像吗？

Answer 1

loadmat函数的输出是字典.请参阅以下代码:

import numpy as np
import scipy.io as sio
import matplotlib.pyplot as plt
%matplotlib inline

image_ind = 10
train_data = sio.loadmat('train_32x32.mat')

# access to the dict
x_train = train_data['X']
y_train = train_data['y']

# show sample
plt.imshow(x_train[:,:,:,image_ind])
plt.show()


print y_train[image_ind]