在Keras ImageDataGenerator流方法中调整图像大小 [英] Resizing images in Keras ImageDataGenerator flow methods

问题描述

Keras ImageDataGenerator类提供了两个流方法flow(X, y)和flow_from_directory(directory)( https://keras.io/preprocessing/image/).

The Keras ImageDataGenerator class provides the two flow methods flow(X, y) and flow_from_directory(directory) (https://keras.io/preprocessing/image/).

为什么是参数

target_size:整数元组，默认值:(256，256).找到的所有图像的尺寸将被调整为

target_size: tuple of integers, default: (256, 256). The dimensions to which all images found will be resized

仅由 flow_from_directory(directory)提供?使用 flow(X，y)将图像的重塑添加到预处理管道中的最简洁方法是什么?

Only provided by flow_from_directory(directory) ? And what is the most concise way to add reshaping of images to the preprocessing pipeline using flow(X, y) ?

推荐答案

flow_from_directory(directory)从带有任意图像集合的目录中生成增强图像.因此，需要参数target_size来制作所有具有相同形状的图像.

flow_from_directory(directory) generates augmented images from directory with arbitrary collection of images. So there is need of parameter target_size to make all images of same shape.

flow(X, y)会增强已经按顺序存储在X中的图像，这些图像不过是numpy矩阵，在传递给flow之前可以很容易地进行预处理/调整大小.因此，不需要target_size参数.至于调整大小，我更喜欢使用scipy.misc.imresize而不是PIL.Image resize或cv2.resize，因为它可以处理numpy图片数据.

While flow(X, y) augments images which are already stored in a sequence in X which is nothing but numpy matrix and can be easily preprocessed/resized before passing to flow. So no need for target_size parameter. As for resizing I prefer using scipy.misc.imresize over PIL.Image resize, or cv2.resize as it can operate on numpy image data.

import scipy
new_shape = (28,28,3)
X_train_new = np.empty(shape=(X_train.shape[0],)+new_shape)
for idx in xrange(X_train.shape[0]):
    X_train_new[idx] = scipy.misc.imresize(X_train[idx], new_shape)

这篇关于在Keras ImageDataGenerator流方法中调整图像大小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！