cycle-GAN keras

./datasets/lane2road/trainA(B)

from keras_contrib.layers.normalization.instancenormalization import InstanceNormalization
from keras.layers import Input, Concatenate, Activation
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.convolutional import UpSampling2D, Conv2D
from keras.models import Sequential, Model
from keras.optimizers import Adam
import matplotlib.pyplot as plt
import scipy.misc
from glob import glob
import numpy as np
import os

class DataLoader():
    def __init__(self, dataset_name, img_res=(128, 128)):
        self.dataset_name = dataset_name
        self.img_res = img_res

    def load_batch(self, batch_size=1, is_testing=False):
        data_type = "train"
        path_A = glob('./datasets/%s/%sA/*' % (self.dataset_name, data_type))
        path_B = glob('./datasets/%s/%sB/*' % (self.dataset_name, data_type))
        self.n_batches = int(min(len(path_A), len(path_B)) / batch_size)
        total_samples = self.n_batches * batch_size
        path_A = np.random.choice(path_A, total_samples, replace=False)
        path_B = np.random.choice(path_B, total_samples, replace=False)
        for i in range(self.n_batches-1):
            batch_A = path_A[i*batch_size:(i+1)*batch_size]
            batch_B = path_B[i*batch_size:(i+1)*batch_size]
            imgs_A, imgs_B = [], []
            for img_A, img_B in zip(batch_A, batch_B):
                img_A = scipy.misc.imread(img_A, mode='RGB').astype(np.float)
                img_B = scipy.misc.imread(img_B, mode='RGB').astype(np.float)
                i