chainerで画像の学習させようとdataset作成部分でエラーが出ます。

前提・実現したいこと

chainer、pythonを用いて犬猫を分類するプログラムを作ろうとしています。
dataset作成の際に、augmentationをして検証データと訓練データを分割しようとしたところ、エラーが生じています。

発生している問題・エラーメッセージ

Exception in main training loop: 
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/trainer.py", line 306, in run
    update()
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py", line 149, in update
    self.update_core()
  File "/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py", line 154, in update_core
    in_arrays = self.converter(batch, self.device)
  File "/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py", line 133, in concat_examples
    [example[i] for example in batch], padding[i])))
  File "/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py", line 163, in _concat_arrays
    return xp.concatenate([array[None] for array in arrays])
Will finalize trainer extensions and updater before reraising the exception.
---------------------------------------------------------------------------
MemoryError                               Traceback (most recent call last)
<ipython-input-150-3287ea1d3afc> in <module>()
----> 1 trainer.run()

/usr/local/lib/python3.5/dist-packages/chainer/training/trainer.py in run(self, show_loop_exception_msg)
    318                 print('Will finalize trainer extensions and updater before '
    319                       'reraising the exception.', file=sys.stderr)
--> 320             six.reraise(*sys.exc_info())
    321         finally:
    322             for _, entry in extensions:

/usr/local/lib/python3.5/dist-packages/six.py in reraise(tp, value, tb)
    691             if value.__traceback__ is not tb:
    692                 raise value.with_traceback(tb)
--> 693             raise value
    694         finally:
    695             value = None

/usr/local/lib/python3.5/dist-packages/chainer/training/trainer.py in run(self, show_loop_exception_msg)
    304                 self.observation = {}
    305                 with reporter.scope(self.observation):
--> 306                     update()
    307                     for name, entry in extensions:
    308                         if entry.trigger(self):

/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py in update(self)
    147 
    148         """
--> 149         self.update_core()
    150         self.iteration += 1
    151 

/usr/local/lib/python3.5/dist-packages/chainer/training/updaters/standard_updater.py in update_core(self)
    152     def update_core(self):
    153         batch = self._iterators['main'].next()
--> 154         in_arrays = self.converter(batch, self.device)
    155 
    156         optimizer = self._optimizers['main']

/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py in concat_examples(batch, device, padding)
    131         for i in six.moves.range(len(first_elem)):
    132             result.append(to_device(device, _concat_arrays(
--> 133                 [example[i] for example in batch], padding[i])))
    134 
    135         return tuple(result)

/usr/local/lib/python3.5/dist-packages/chainer/dataset/convert.py in _concat_arrays(arrays, padding)
    161     xp = cuda.get_array_module(arrays[0])
    162     with cuda.get_device_from_array(arrays[0]):
--> 163         return xp.concatenate([array[None] for array in arrays])
    164 
    165 

MemoryError:

該当のソースコード

python
1%matplotlib inline
2from PIL import Image
3from glob import glob
4import numpy as np  
5import pandas as pd  
6import matplotlib.pyplot as plt 
7import chainer
8import chainer.functions as F 
9import chainer.links as L
10import scipy
11from scipy.ndimage.interpolation import rotate
12import cv2
13from glob import glob
14
15import random 
16def reset_seed(seed=0):
17    random.seed(seed)
18    np.random.seed(seed)
19if chainer.cuda.available:
20    chainer.cuda.cupy.random.seed(seed)
21reset_seed()
22
23cat_paths = 'data/cat/*.jpg'
24dog_paths = 'data/dog/*.jpg'
25cat_files = glob(cat_paths)
26dog_files = glob(dog_paths)
27
28#cat元画像格納場所
29x_basec,t_basec = [],[]
30for filepath in cat_files:
31    img = Image.open(filepath)
32    img = np.array(img, 'f')#この下に水増し関数いれる
33    img = np.transpose(img,(2, 0, 1))
34    x_basec.append(img)
35    t_basec.append(np.array(0, 'i'))  # 猫は0
36#dog元画像格納場所
37x_based,t_based = [],[]
38for filepath in dog_files:
39    img = Image.open(filepath)
40    img = np.array(img, 'f')#この下に水増し関数いれる
41    img = np.transpose(img,(2, 0, 1))
42    x_based.append(img)
43    t_based.append(np.array(1, 'i'))  # 犬は1
44x_train, x_test = [],[]
45t_train, t_test = [],[]
46for filepath in cat_files:
47    if random.random() <0.7 : #訓練とテストの分割をランダム化
48        x_train.append(x_basec)
49        t_train.append(t_basec)  
50    else:     
51        x_test.append(x_basec)
52        t_test.append(t_basec)   
53
54for filepath in dog_files:
55    if random.random() <0.7 : #訓練とテストの分割をランダム化
56        x_train.append(x_based)
57        t_train.append(t_based)  
58
59    else:     
60        x_test.append(x_based)
61        t_test.append(t_based) 
62
63**train = chainer.datasets.TupleDataset(x_train,t_train) 
64test = chainer.datasets.TupleDataset(x_test,t_test) **
65
66class CNN(chainer.Chain):
67
68    def __init__(self, n_mid=100, n_out=2):
69        super().__init__()
70        with self.init_scope():
71            self.conv1 = L.Convolution2D(in_channels=1, out_channels=3, ksize=3, stride=1, pad=1)
72            self.fc1 = L.Linear(None, n_mid)
73            self.fc2 = L.Linear(None, n_out)
74
75    def __call__(self, x):
76        h = F.relu(self.conv1(x))
77        h = F.max_pooling_2d(h, 3, 3)
78        h = self.fc1(h)
79        h = self.fc2(h)
80        return h
81import random
82
83def reset_seed(seed=0):
84    random.seed(seed)
85    np.random.seed(seed)
86    if chainer.cuda.available:
87        chainer.cuda.cupy.random.seed(seed)
88# CPUとGPU関連のシードをすべて固定
89reset_seed(0)
90
91gpu_id = 0  # 使用したGPUに割り振られているID
92model.to_gpu(gpu_id)
93# Optimizerの定義とmodelとの紐づけ
94optimizer = chainer.optimizers.Adam()
95optimizer.setup(model)
96batchsize = 128
97train_iter = chainer.iterators.SerialIterator(train, batchsize)
98test_iter = chainer.iterators.SerialIterator(test, batchsize, repeat=False, shuffle=False)
99from chainer import training
100from chainer.training import extensions
101
102epoch = 30
103
104updater = training.StandardUpdater(train_iter, optimizer, device=gpu_id)
105
106trainer = training.Trainer(updater, (epoch, 'epoch'), out='dc0')
107
108# バリデーション用のデータで評価
109trainer.extend(extensions.Evaluator(test_iter, model, device=gpu_id))
110

試したこと

augmentation部分は文字数の関係で省いていますがそれでも本エラーが発生しています。
augmentationせずにdatasetを一気に作成し、tupledataset_randomしたところプログラムが通ったため、
dataset作成orそれ以前の個所にエラーが発生していると考えられます。