我无法从keras运行简单的数据生成器代码

import os
import keras as K
from keras.preprocessing.image import ImageDataGenerator

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

Gen=ImageDataGenerator(featurewise_center=True,
    samplewise_center=False,
    featurewise_std_normalization=False,
    samplewise_std_normalization=False,
    zca_whitening=True,
    rotation_range=90,
    width_shift_range=0.2,
    height_shift_range=0.1,
    shear_range=0.5,
    zoom_range=0.2,
    channel_shift_range=0.1,
    fill_mode='nearest',
    cval=0.,
    horizontal_flip=True,
    vertical_flip=True,
    rescale=None,
    preprocessing_function=None)


if __name__ == '__main__':
    save_images_from_generator(40,Gen.flow_from_directory('C:\\Users\\aanilil\\PycharmProjects\\untitled\\images_input', target_size=(150, 150),class_mode=None,save_prefix='augm',save_to_dir='C:\\Users\\aanilil\\PycharmProjects\\untitled\\im_output\\'))

输出量

Using TensorFlow backend.
Found 0 images belonging to 0 classes.
Found 0 …

我已经使用Debug标志编译了caffe.现在我跑的时候

./examples/mnist/train_lenet.sh

我得到输出

I0112 22:50:49.680357 114020 data_layer.cpp:103]      Read time: 0.095 ms.
I0112 22:50:49.680376 114020 data_layer.cpp:104] Transform time: 0.821 ms.
I0112 22:50:49.681077 113921 solver.cpp:409]     Test net output #0: accuracy = 0.9902
I0112 22:50:49.681115 113921 solver.cpp:409]     Test net output #1: loss = 0.0292544 (* 1 = 0.0292544 loss)
I0112 22:50:49.681125 113921 solver.cpp:326] Optimization Done.
I0112 22:50:49.681133 113921 caffe.cpp:215] Optimization Done.
I0112 22:50:49.681915 114020 data_layer.cpp:102] Prefetch batch: 1 ms.
I0112 22:50:49.681929 114020 data_layer.cpp:103]      Read time: 0.095 ms.
I0112 22:50:49.681948 114020 data_layer.cpp:104] Transform time: …

import tensorflow as tf
import numpy as np
import scipy as sci
import cv2
import input_data_conv


# Parameters
learning_rate = 0.001
training_iters = 200000
batch_size = 64
display_step = 20
n_classes=101 # number of classes

#Input data and classes
global train_data,train_class,test_data,test_classs,train_i,test_i
test_i, train_i = 0,0
train_data=input_data_conv.train_list_file
train_class=input_data_conv.train_single_classes
test_data=input_data_conv.test_single_frames
test_classs=input_data_conv.test_single_classes


# Network Parameters
n_input = [227, 227, 3 ]# MNIST data input (img shape: 227*227*3)
dropout = 0.5 # Dropout, probability to keep units

# tf Graph input
x = tf.placeholder(tf.float32, …

我在使用caffe从图像生成HDF5数据文件时遇到了这个问题.

所述caffe.io.load_image载荷图像转换成在归一化范围0-1 varible.

调整大小,但所有值都img转换为零

    img = caffe.io.load_image( patht_to_file )
    print img.shape
    print img.dtype
    img = caffe.io.resize( img, (3,SIZE, SIZE) ) #resizes but all values in img converted to zero
    print img.shape
    print img.dtype

我得到的输出是

  (240, 320, 3) 
  float32
  (3, 58, 58) 
  float64

img对于某些值,将值更改为全0,任何人都可以帮我修复此问题.

我想同样的float32改变resize命令的顺序给出正确的输出 给var真正的非零值,img 但顺序和类型不是我需要的

img = caffe.io.resize( img, (SIZE, SIZE, 3) ) # Gives real non zero values to var img
print img.shape
print img.dtype

产量

(240, 320, 3) 
float32 …

我想实现一个小型程序，该程序将随机翻转并引入RGB抖动/轻微值变化。

并尽可能将抖动/轻微值更改为彩色图像中3层中的2层。

import cv2
import random

probofflip=0.5
probofRGBjit= 0.6

img=cv2.imread('path/to/img.png',1)
if (random.uniform(0,1)>1-probofflip):
    img= cv2.flip(img,1)
if if (random.uniform(0,1)>1-probofRGBjit):
    #function to jitter the RGB layers 
#do something with resultant image.