深度学习基操：batch shuffle编程

在训练网络时，经常会遇到数据集中数据与标签分离的情况，此时进行batch shuffle时需要保持数据与标签一一对应的关系，编程实现如下。

以图像识别中玩滥的MNIST数据集为例：

MNIST 数据集可在 http://yann.lecun.com/exdb/mnist/ 获取, 它包含了四个部分:

Training set images: train-images-idx3-ubyte.gz (9.9 MB, 解压后 47 MB, 包含 60,000 个样本)
Training set labels: train-labels-idx1-ubyte.gz (29 KB, 解压后 60 KB, 包含 60,000 个标签)
Test set images: t10k-images-idx3-ubyte.gz (1.6 MB, 解压后 7.8 MB, 包含 10,000 个样本)
Test set labels: t10k-labels-idx1-ubyte.gz (5KB, 解压后 10 KB, 包含 10,000 个标签)

我们首先将数据以数组的形式读取：

def load_mnist(path, kind='train'):
    """Load MNIST data from `path`"""
    labels_path = os.path.join(path,
                               '%s-labels.idx1-ubyte'
                               % kind)
    images_path = os.path.join(path,
                               '%s-images.idx3-ubyte'
                               % kind)
    with open(labels_path, 'rb') as lbpath:
        magic, n = struct.unpack('>II',
                                 lbpath.read(8))
        labels = np.fromfile(lbpath,
                             dtype=np.uint8)

    with open(images_path, 'rb') as imgpath:
        magic, num, rows, cols = struct.unpack('>IIII',
                                               imgpath.read(16))
        images = np.fromfile(imgpath,
                             dtype=np.uint8).reshape(len(labels), 784)

    return images, labels

将读取的图像利用matplotlib.pyplot可视化：

def show():
    X_train,y_train = load_mnist(os.getcwd())
    fig, ax = plt.subplots(
        nrows=2,
        ncols=5,
        sharex=True,
        sharey=True, )
    ax = ax.flatten()
    for i in range(10):
        img = X_train[y_train == i][0].reshape(28, 28)#显示0-9
        #img = X_train[y_train == 7][i].reshape(28, 28)#仅显示数字7
        ax[i].imshow(img, cmap='Greys', interpolation='nearest')
    ax[0].set_xticks([])
    ax[0].set_yticks([])
    plt.tight_layout()
    plt.show()

可视化结果：

训练时进行batch shuffle：

import numpy as np
def batch_shuffle(images,labels,batch_size):
    state = np.random.get_state()
    np.random.shuffle(images)
    np.random.set_state(state)
    np.random.shuffle(labels)
    return images[:batch_size],labels[:batch_size]

数据处理完毕，后续训练即可。