Python3 kerasのImageDataGenerator使用時にエラーが出る

前提・実現したいこと

kerasのimagedatageneratorを使って，各画像の平均を０にする処理を行おうとしたのですが，以下のようなエラーが発生してしまいました．
generatorのoutputが正しくないといわれているようなのですが，kerasの公式ドキュメントを見ても修正方法がよくわかりませんでした．お手数お掛けいたしますが，どのように修正したら良いかご教示いただけますと大変助かります．

発生している問題・エラーメッセージ

ValueError                                Traceback (most recent call last)
<ipython-input-7-86574fd9be32> in <module>()
    340                           validation_steps=epochs,
    341                           verbose=1,
--> 342                           callbacks=callbacks)
    343 
    344     plot_results(models, data, batch_size=batch_size, model_name="vae_OCT")

ValueError: Output of generator should be a tuple `(x, y, sample_weight)` or `(x, y)`. Found: [[[[-0.12498678]
   [-0.12498678]
   [-0.12498678]
   ...
   [-0.03086913]
   [-0.07400638]
   [-0.12498678]]

  [[-0.12498678]
   [-0.12498678]
   [-0.12498678]
   ...
   [-0.05439854]
   [-0.08184952]
   [-0.12106521]]

  [[-0.12498678]
   [-0.12498678]
   [-0.12498678]
   ...
   [-0.08577108]
   [-0.0975358 ]
   [-0.1093005 ]]

  ...

該当のソースコード

Python
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from keras.layers import Lambda, Input, Dense
from keras.models import Model
from keras.models import Sequential, model_from_json
from keras.losses import mse, binary_crossentropy
from keras.layers import Conv2D, Flatten
from keras.layers import Reshape, Conv2DTranspose
from keras.utils import plot_model, np_utils 
from keras.utils import plot_model
from keras.callbacks import Callback, EarlyStopping, TensorBoard, ModelCheckpoint, LearningRateScheduler, CSVLogger
from keras import optimizers
from keras import backend as K
from keras.preprocessing.image import array_to_img, img_to_array,load_img
from keras.preprocessing.image import ImageDataGenerator
from keras.layers import Activation, BatchNormalization

import numpy as np
import matplotlib.pyplot as plt
import argparse
import os
import re
import glob
import random as rn
import tensorflow as tf
import cv2
from PIL import Image

import warnings
warnings.filterwarnings('ignore')

%matplotlib inline
get_ipython().run_line_magic('matplotlib', 'inline')


#reparameterization trick
# instead of sampling from Q(z|X), sample eps = N(0,I)
# z = z_mean + sqrt(var)*eps
def sampling(args):
    """Reparameterization trick by sampling fr an isotropic unit Gaussian.

    # Arguments
        args (tensor): mean and log of variance of Q(z|X)

    # Returns
        z (tensor): sampled latent vector
    """
    z_mean, z_log_var = args
    batch = K.shape(z_mean)[0]
    dim = K.int_shape(z_mean)[1]
    # by default, random_normal has mean=0 and std=1.0
    epsilon = K.random_normal(shape=(batch, dim))
    return z_mean + K.exp(0.5 * z_log_var) * epsilon


def plot_results(models,
                 data,
                batch_size=25,
                 model_name="vae_OCT"):
    """Plots labels and MNIST digits as function of 2-dim latent vector

    # Arguments
        models (tuple): encoder and decoder models
        data (tuple): test data and label
        batch_size (int): prediction batch size
        model_name (string): which model is using this function
    """

    encoder, decoder = models
    x_test = data
    os.makedirs(model_name, exist_ok=True)

    filename = os.path.join(model_name, "vae_mean.png")
    # display a 2D plot of the digit classes in the latent space
    z_mean, _, _ = encoder.predict(x_test,
                                   batch_size=batch_size)

#original dataset
#train
filenames = glob.glob("./NORMAL_resize_pixel_100_1_0506/*.jpeg")
x_train= []

for filename in filenames:
    img = img_to_array(load_img(
    filename, color_mode = "grayscale"
    , target_size=(512,496)))
    x_train.append(img)

x_train = np.asarray(x_train)
print(x_train.shape)

#test
filenames = glob.glob("./NORMAL_resize_pixel_0506/*.jpeg")
x_test= []

for filename in filenames:
    img = img_to_array(load_img(
    filename, color_mode = "grayscale"
    , target_size=(512,496)))
    x_test.append(img)

x_test = np.asarray(x_test)


image_size_width = x_train.shape[1]
image_size_height = x_train.shape[2]
original_dim = 512 * 496  #3削除
x_train = np.reshape(x_train, [-1, image_size_width,image_size_height,1])
x_test = np.reshape(x_test,[ -1, image_size_width,image_size_height,1])
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255

#numpy配列をタプルに変換
x_train = tuple(x_train)
x_test = tuple(x_test)

#各サンプルの平均を0にする
train_datagen = ImageDataGenerator(samplewise_center=True)
train_generator = train_datagen.flow(x_train, batch_size=32)

validation_datagen = ImageDataGenerator(samplewise_center=True)
validation_generator = validation_datagen.flow(x_test, batch_size=32)

print(x_train.shape)
print(x_test.shape)

# network parameters
input_shape = (image_size_width,image_size_height,1)
batch_size = 25#50
kernel_size = 3
filters = 16
latent_dim = 2
epochs = 100

# VAE model = encoder + decoder
# build encoder model
inputs = Input(shape=input_shape, name='encoder_input')
x = inputs
for i in range(4):
    filters *= 2
    x = Conv2D(filters=filters,
               kernel_size=kernel_size,
               activation = 'relu',
               strides=2,padding='same')(x)
    #x = BatchNormalization()(x)
    #x = Activation('relu')(x)

# shape info needed to build decoder model
shape = K.int_shape(x)

# generate latent vector Q(z|X)
x = Flatten()(x)
x = Dense(64, activation='relu')(x)
z_mean = Dense(latent_dim, name='z_mean')(x)
z_log_var = Dense(latent_dim, name='z_log_var')(x)

# use reparameterization trick to push the sampling out as input
# note that "output_shape" isn't necessary with the TensorFlow backend
z = Lambda(sampling, output_shape=(latent_dim,), name='z')([z_mean, z_log_var])

# instantiate encoder model
encoder = Model(inputs, [z_mean, z_log_var, z], name='encoder')
encoder.summary()
plot_model(encoder, to_file='vae_cnn_encoder.png', show_shapes=True)

# build decoder model
latent_inputs = Input(shape=(latent_dim,), name='z_sampling')
x = Dense(shape[1] * shape[2] * shape[3], activation='relu')(latent_inputs)
x = Reshape((shape[1], shape[2], shape[3]))(x)

for i in range(4):
    x = Conv2DTranspose(filters=filters,
               kernel_size=kernel_size,
               activation = 'relu',         
               strides=2,padding='same')(x)
    #x = BatchNormalization()(x)
    #x = Activation('relu')(x)
    filters //= 2

outputs = Conv2DTranspose(filters=1,
                          kernel_size=kernel_size,
                          activation='sigmoid',
                          padding='same',
                          name='decoder_output')(x)
#outputs = BatchNormalization()(outputs)#(x)
#outputs = Activation('sigmoid')(outputs)#(x)

# instantiate decoder model
decoder = Model(latent_inputs, outputs, name='decoder')
decoder.summary()
plot_model(decoder, to_file='vae_cnn_decoder.png', show_shapes=True)

# instantiate VAE model
outputs = decoder(encoder(inputs)[2])
vae = Model(inputs, outputs, name='vae')



def plot_history(history):

    # ??????????
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('model loss')
    plt.xlabel('epoch')
    plt.ylabel('loss')
    plt.legend(['loss', 'val_loss'], loc='lower right')
    plt.savefig('loss.png')  # -----(2)
    plt.show()



if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    help_ = "Load h5 model trained weights"
    parser.add_argument("-w", "--weights", help=help_)
    help_ = "Use mse loss instead of binary cross entropy (default)"
    parser.add_argument("-m", "--mse", help=help_, action='store_true')
    args = parser.parse_args([])
    models = (encoder, decoder)
    data = (x_test)

 


    # VAE loss = mse_loss or xent_loss + kl_loss
    if args.mse:
        reconstruction_loss = mse(K.flatten(inputs), K.flatten(outputs))
    else:
        reconstruction_loss = binary_crossentropy(K.flatten(inputs),
                                                  K.flatten(outputs))

    reconstruction_loss *= image_size_width * image_size_height
    kl_loss = 1 + z_log_var - K.square(z_mean) - K.exp(z_log_var)
    kl_loss = K.sum(kl_loss, axis=-1)
    kl_loss *= -0.5
    vae_loss = K.mean(reconstruction_loss + kl_loss)
    vae.add_loss(vae_loss)
    Adam = optimizers.Adam(lr=0.0005)
    vae.compile(optimizer=Adam)
    vae.summary()
    plot_model(vae, to_file='vae_cnn.png', show_shapes=True)
    
    callbacks = []
    callbacks.append(ModelCheckpoint(filepath="model.ep{epoch:02d}.h5", save_best_only = True, period=5))
    callbacks.append(EarlyStopping(monitor='val_loss', patience=7, verbose=1))
    callbacks.append(CSVLogger("history.csv"))

    if args.weights:
        vae.load_weights(args.weights)
    else:
        # train the autoencoder
        history = vae.fit_generator(train_generator,
                          steps_per_epoch=x_train.shape[0] // batch_size,
                          epochs=epochs,#20,
                          validation_data=(validation_generator,None),
                          validation_steps=x_test.shape[0] // batch_size,
                          verbose=1,
                          callbacks=callbacks)

    plot_results(models, data, batch_size=batch_size, model_name="vae_OCT")
    plot_history(history)