卜若的代码笔记-puthon系列-神经网络篇-第六章：The CIFAR-10 dataset的图片的读取

 

最终效果

1.从官网下载https://www.cs.toronto.edu/~kriz/cifar.html

2.解压：

3.调用逛网给的api

 

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

 

4.读取数据

 

import readImage as rt

data1 = rt.unpickle('F:/软件包/cifar-10-python/cifar-10-batches-py/test_batch')
data = data1[b'data']
label = data1[b'labels']
a = data.reshape(10000, 3, 32,32).transpose(0,2,3,1).astype("float")

ima = a[0]

 5.显示图像

plt.imshow(ima/255)
plt.show()

 

6.完整的代码

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mlt
import os
import readImage as rt

data1 = rt.unpickle('F:/软件包/cifar-10-python/cifar-10-batches-py/test_batch')
data = data1[b'data']
label = data1[b'labels']
a = data.reshape(10000, 3, 32,32).transpose(0,2,3,1).astype("float")
ima = a[0]
plt.imshow(ima/255)
plt.show()

 readImage ：

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