kerasでSegNetで画像サイズの変更、画像読み込みについて

Question

「keras(tensorflow)でSegNet」
(https://qiita.com/uni-3/items/a62daa5a03a02f5fa46d)
を参考に記載されているコードをそのまま自分でも動かしてみようと
試みておりますが、実行するとメモリーのエラーがでてしまうため
下記を試みました。

試したこと：読み込み画像サイスを(360×480)から(176×240)に変更し
コード中の対応する数値を変更しました(フォルダ内の全ての画像サイズを変更）。

## dataset.py
import cv2
import numpy as np

from keras.applications import imagenet_utils

import os

DataPath = './CamVid/'
data_shape = 176*240

class Dataset:
    def __init__(self, classes=12, train_file='train.txt', test_file='test.txt'):
        self.train_file = train_file
        self.test_file = test_file
        self.data_shape = 176*240
        self.classes = classes

    def normalized(self, rgb):
        #return rgb/255.0
        norm=np.zeros((rgb.shape[0], rgb.shape[1], 3),np.float32)

        b=rgb[:,:,0]
        g=rgb[:,:,1]
        r=rgb[:,:,2]

        norm[:,:,0]=cv2.equalizeHist(b)
        norm[:,:,1]=cv2.equalizeHist(g)
        norm[:,:,2]=cv2.equalizeHist(r)

        return norm

    def one_hot_it(self, labels):
        x = np.zeros([176,240,12])
        for i in range(176):
            for j in range(240):
                x[i,j,labels[i][j]] = 1
        return x

    def load_data(self, mode='train'):
        data = []
        label = []
        if (mode == 'train'):
            filename = self.train_file
        else:
            filename = self.test_file

        with open(DataPath + filename) as f:
            txt = f.readlines()
            txt = [line.split(' ') for line in txt]

        for i in range(len(txt)):
            data.append(self.normalized(cv2.imread(os.getcwd() + txt[i][0][7:])))
            label.append(self.one_hot_it(cv2.imread(os.getcwd() + txt[i][1][7:][:-1])[:,:,0]))
            print('.',end='')
        #print("train data file", os.getcwd() + txt[i][0][7:])
        #print("label data raw", cv2.imread(os.getcwd() + '/CamVid/trainannot/0001TP_006690.png'))
        return np.array(data), np.array(label)


    def preprocess_inputs(self, X):
    ### @ https://github.com/fchollet/keras/blob/master/keras/applications/imagenet_utils.py
        """Preprocesses a tensor encoding a batch of images.
        # Arguments
            x: input Numpy tensor, 4D.
            data_format: data format of the image tensor.
            mode: One of "caffe", "tf".
                - caffe: will convert the images from RGB to BGR,
                    then will zero-center each color channel with
                    respect to the ImageNet dataset,
                    without scaling.
                - tf: will scale pixels between -1 and 1,
                    sample-wise.
        # Returns
            Preprocessed tensor.
        """
        return imagenet_utils.preprocess_input(X)

    def reshape_labels(self, y):
        return np.reshape(y, (len(y), self.data_shape, self.classes))

ここで

## train.py
import os
import glob
import numpy as np
import keras

from model import SegNet

import dataset

input_shape = (176, 240, 3)
classes = 12
epochs = 10
batch_size = 1
log_filepath='./logs/'

data_shape = 176*240

class_weighting = [0.2595, 0.1826, 4.5640, 0.1417, 0.5051, 0.3826, 9.6446, 1.8418, 6.6823, 6.2478, 3.0, 7.3614]

## set gpu usage
import tensorflow as tf
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True, per_process_gpu_memory_fraction = 0.8))
session = tf.Session(config=config)
keras.backend.tensorflow_backend.set_session(session)

def main():
    print("loading data...")
    ds = dataset.Dataset(classes=classes)
    train_X, train_y = ds.load_data('train') # need to implement, y shape is (None, 176, 240, classes)

    train_X = ds.preprocess_inputs(train_X)
    train_Y = ds.reshape_labels(train_y)
    print("input data shape...", train_X.shape)
    print("input label shape...", train_Y.shape)

    test_X, test_y = ds.load_data('test') # need to implement, y shape is (None, 176, 240, classes)
    test_X = ds.preprocess_inputs(test_X)
    test_Y = ds.reshape_labels(test_y)

    tb_cb = keras.callbacks.TensorBoard(log_dir=log_filepath, histogram_freq=1, write_graph=True, write_images=True)
    print("creating model...")
    model = SegNet(input_shape=input_shape, classes=classes)
    model.compile(loss="categorical_crossentropy", optimizer='adadelta', metrics=["accuracy"])

    model.fit(train_X, train_Y, batch_size=batch_size, epochs=epochs,
              verbose=1, class_weight=class_weighting , validation_data=(test_X, test_Y), shuffle=True
              , callbacks=[tb_cb])

    model.save('seg.h5')

if __name__ == '__main__':
    main()

を実行すると下記エラーが表示されます。
runfile('C:/Users/user/code/train.py', wdir='C:/Users/user/code')
loading data...
Traceback (most recent call last):

File "<ipython-input-18-ea305e956635>", line 1, in <module>
runfile('C:/Users/user/code/train.py', wdir='C:/Users/user/code')

File "C:\Users\user\anaconda3\envs\DL\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 704, in runfile
execfile(filename, namespace)

File "C:\Users\user\anaconda3\envs\DL\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 108, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "C:/Users/user/code/train.py", line 52, in <module>
main()

File "C:/Users/user/code/train.py", line 29, in main
train_X, train_y = ds.load_data('train') # need to implement, y shape is (None, 176, 240, classes)

File "C:\Users\user\code\dataset.py", line 53, in load_data
label.append(self.one_hot_it(cv2.imread(os.getcwd() + txt[i][1][7:][:-1])[:,:,0]))

File "C:\Users\user\code\dataset.py", line 36, in one_hot_it
x[i,j,labels[i][j]] = 1

IndexError: index 35 is out of bounds for axis 2 with size 12

このエラーの意味と対処方法が分からずに困っております。
お手数をお掛けいたしますが、ご教示いただけると大変ありがたいです。

補足：CamVidフォルダ中のtestannot,trainannot,valannotを元画像サイズ(360×480)で
実行すると正常に学習が開始されます。

windows10
python3.6.7
tensorflow1.12.0
keras2.2.4

Answer 1

画像サイズ変更したtestannot、trainannot、valannot の画像に問題が
あって読み込みに失敗していたようです。
「FastStone Photo Resizer」で色深度8bit(256)まで指定して(176×240)に
画像サイズを変更したらうまく動作しました。