对多幅图像应用相同的Keras-Tensorflow预处理变换

我目前正在使用数据扩充构建自己的自定义生成器。我必须对两个图像应用相同的变换，一个是训练图像，一个是目标图像，但函数只能一个接一个地工作。你知道如何在两幅图像中应用精确变换吗？ 这是我正在尝试的一个功能：

tf.keras.preprocessing.image.random_zoom

发电机的代码：

def generator(data, batch_size = 32, data_augmentation = False):
batch_number = 0
while True:
    original_train = []
    original_target = []
    train = []
    target = []
    if batch_number * batch_size >= data.shape[0]:
            batch_number = 0        
    for x in train_pd.values[batch_number * batch_size: (batch_number + 1) * batch_size ]:
        train_image = load_image_as_array(train_path+'images/'+x[0]+'.png').reshape(101,101,1)
        target_image = load_image_as_array(train_path+'masks/'+x[0]+'.png').reshape(101,101,1)
        original_train.append(train_image)
        original_target.append(target_image)
        if data_augmentation:
            train_image = random_zoom(train_image, (.25,.25))
            target_image = random_zoom(target_image, (.25,.25))
        train.append(train_image)
        target.append(target_image)            
    batch_number += 1
    yield np.array(train), np.array(target), np.array(original_train), np.array(original_target)

---

嗯。除了调用函数两次之外，它似乎还应用了精确的变换