更新

现在，keras-cv正式支持此功能。
要在CutMix或MixUp类型扩充中创建一个类标签，我们可以使用beta，如np.random.beta或scipy.stats.beta，并对两个标签执行以下操作：

label = label_one*beta + (1-beta)*label_two

但是如果我们有两个以上的图像呢？在YoLo4中，他们尝试了一个有趣的增强，称为Mosaic增强，用于对象检测问题。与CutMix或MixUp不同，这种增强会创建具有4图像的增强样本。在物体检测的情况下，我们可以计算每个示例坐标的偏移，从而可以得到正确的地面实况here。但是对于仅图像分类的情况，我们如何做到这一点？
这是一个开始。

import tensorflow as tf
import matplotlib.pyplot as plt 
import random

(train_images, train_labels), (test_images, test_labels) = \
tf.keras.datasets.cifar10.load_data()
train_images = train_images[:10,:,:]
train_labels = train_labels[:10]
train_images.shape, train_labels.shape

((10, 32, 32, 3), (10, 1))

这是我们为这个增广写的函数;（太丑了，有一个“内外循环”！请建议我们是否能有效地做到这一点。）

def mosaicmix(image, label, DIM, minfrac=0.25, maxfrac=0.75):
    '''image, label: batches of samples 
    '''
    xc, yc  = np.random.randint(DIM * minfrac, DIM * maxfrac, (2,))
    indices = np.random.permutation(int(image.shape[0]))
    mosaic_image = np.zeros((DIM, DIM, 3), dtype=np.float32)
    final_imgs, final_lbs = [], []

    # Iterate over the full indices 
    for j in range(len(indices)): 
        # Take 4 sample for to create a mosaic sample randomly 
        rand4indices = [j] + random.sample(list(indices), 3) 
        
        # Make mosaic with 4 samples 
        for i in range(len(rand4indices)):
            if i == 0:    # top left
                x1a, y1a, x2a, y2a =  0,  0, xc, yc
                x1b, y1b, x2b, y2b = DIM - xc, DIM - yc, DIM, DIM # from bottom right        
            elif i == 1:  # top right
                x1a, y1a, x2a, y2a = xc, 0, DIM , yc
                x1b, y1b, x2b, y2b = 0, DIM - yc, DIM - xc, DIM # from bottom left
            elif i == 2:  # bottom left
                x1a, y1a, x2a, y2a = 0, yc, xc, DIM
                x1b, y1b, x2b, y2b = DIM - xc, 0, DIM, DIM-yc   # from top right
            elif i == 3:  # bottom right
                x1a, y1a, x2a, y2a = xc, yc,  DIM, DIM
                x1b, y1b, x2b, y2b = 0, 0, DIM-xc, DIM-yc    # from top left
                
            # Copy-Paste
            mosaic_image[y1a:y2a, x1a:x2a] = image[i,][y1b:y2b, x1b:x2b]

        # Append the Mosiac samples
        final_imgs.append(mosaic_image)
        
    return final_imgs, label

扩增样本，当前标签错误。

data, label = mosaicmix(train_images, train_labels, 32)
plt.imshow(data[5]/255)

然而，这里有一些例子来激励你。数据来自Cassava Leaf竞赛。

（来源：googleapis.com）

（来源：googleapis.com）