使用我自己的数据集在 Keras 中创建自定义数据生成器

Question

我想在自己的数据集上创建自己的自定义 DataGenerator。我已阅读所有图像并将位置及其标签存储在两个名为 images 和 labels 的变量中。我已经编写了这个自定义生成器：

def data_gen(img_folder, y, batch_size):
    c = 0
    n_image = list(np.arange(0,len(img_folder),1)) #List of training images
    random.shuffle(n_image)

    while (True):
        img = np.zeros((batch_size, 224, 224, 3)).astype('float')   #Create zero arrays to store the batches of training images
        label = np.zeros((batch_size)).astype('float')  #Create zero arrays to store the batches of label images

        for i in range(c, c+batch_size): #initially from 0 to 16, c = 0.

            train_img = imread(img_folder[n_image[i]])
            # row,col= train_img.shape
            train_img = cv2.resize(train_img, (224,224), interpolation = cv2.INTER_LANCZOS4)
            train_img = train_img.reshape(224, 224, 3)
#            binary_img = binary_img[:,:128//2]

            img[i-c] = train_img #add to array - img[0], img[1], and so on.

            label[i-c] = y[n_image[i]]

        c+=batch_size
        if(c+batch_size>=len((img_folder))):
            c=0
            random.shuffle(n_image)
                      # print "randomizing again"
        yield img, label

我想知道的是如何向此生成器添加其他增强功能，例如 flip、crop、rotate？此外，我应该如何yield 这些扩充，以便它们与正确的标签相关联。

请告诉我。

Answer 1

您可以在train_img 上添加flip、crop、rotate，然后再将其放入img。也就是说，

    # ....
    While(True):
        # ....

        # add your data augmentation function here
        train_img = data_augmentor(train_img)

        img[i-c] = train_img

        # ....