使用keras.preprocessing.image.ImageDataGenerator进行图像数据论证的技巧? [英] Image data agumentation tequniques using keras.preprocessing.image.ImageDataGenerator?

问题描述

我想通过随机旋转，平移，剪切和翻转来生成图像的增强数据.

I would like to generate augmented data for images by Random rotation, shifts, shear and flips.

我发现了此 keras函数.

函数keras.preprocessing.image.ImageDataGenerator但是我已经看到它被用于直接训练网络.

The function keras.preprocessing.image.ImageDataGenerator But I've seen this being used to directly train networks.

是否可以输入图像，然后将转换后的图像保存在HDD上，而不是当前

Is there a way to input images and then save the transformed images on HDD instead of how if currently works in examples in this link

还是有另一个简单的即插即用python包，我可以使用它代替使用numpy或opencv来实现所有功能?

Or is there another simple plug and use python package I can use instead of implementing everything with numpy or opencv ?

推荐答案

基本上-这是generator，它会无限返回一批图像.一个人可以做以下事情:

Basically - this is generator which is infinitely returning a batches of images. One could do the following:

def save_images_from_generator(maximal_nb_of_images, generator):
    nb_of_images_processed = 0
    for x, _ in generator:
        nb_of_images += x.shape[0]
        if nb_of_images <= maximal_nb_of_images:
            for image_nb in range(x.shape[0]):
                your_custom_save(x[image_nb]) # your custom function for saving images
        else:
            break

从keras图像生成器保存图像.

to save images from keras image generator.

这篇关于使用keras.preprocessing.image.ImageDataGenerator进行图像数据论证的技巧?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！