ValueError: num must be 1 <= num <= 121, not 122 の解決

前提・実現したいこと

以下のページのソースを利用して
https://recruit.gmo.jp/engineer/jisedai/blog/deep-learning-keras/

tensorflow kerasで、下のソースを実行中に、以下のエラーが出ます。
Matplotlibでのsubplotを利用したグラフ作成のところかと思いますが、
解決法をご教示頂けますと助かります。

発生している問題・エラーメッセージ

ValueError Traceback (most recent call last)
<ipython-input-8-849bb41a5d35> in <module>()
8 for ind, val in enumerate(test_wrong):
9 plt.subplots_adjust(left=0, right=1, top=1, bottom=0)
---> 10 plt.subplot(11, 11, ind + 1)
11 # plt.subplot(11, 11, ind)
12 im = 1 - val[0][0]

~\AppData\Local\conda\conda\envs\tensorflow-gpu\lib\site-packages\matplotlib\pyplot.py in subplot(*args, **kwargs)
1070
1071 fig = gcf()
-> 1072 a = fig.add_subplot(*args, **kwargs)
1073 bbox = a.bbox
1074 byebye = []

~\AppData\Local\conda\conda\envs\tensorflow-gpu\lib\site-packages\matplotlib\figure.py in add_subplot(self, *args, **kwargs)
1237 self._axstack.remove(ax)
1238
-> 1239 a = subplot_class_factory(projection_class)(self, *args, **kwargs)
1240 self._axstack.add(key, a)
1241 self.sca(a)

~\AppData\Local\conda\conda\envs\tensorflow-gpu\lib\site-packages\matplotlib\axes_subplots.py in init(self, fig, args, **kwargs)
65 raise ValueError(
66 ("num must be 1 <= num <= {maxn}, not {num}"
---> 67 ).format(maxn=rowscols, num=num))
68 self._subplotspec = GridSpec(
69 rows, cols, figure=self.figure)[int(num) - 1]

ValueError: num must be 1 <= num <= 121, not 122

該当のソースコード

python
1import os
2import sys
3import numpy as np
4import pandas as pd
5import matplotlib.pyplot as plt
6
7# Kerasで必要なものをimport
8from keras.datasets import mnist
9from keras.models import Sequential
10from keras.layers.core import Dense, Dropout, Activation, Flatten
11from keras.layers.convolutional import Convolution2D, MaxPooling2D
12from keras.utils import np_utils
13
14# データを用意＆加工
15size_img = 28
16n_label = 10
17
18(X_train, y_train), (X_test, y_test) = mnist.load_data()
19X_train = X_train.reshape(-1, 1, size_img, size_img).astype('float32') / 255.
20X_test = X_test.reshape(-1, 1, size_img, size_img).astype('float32') / 255.
21Y_train = np_utils.to_categorical(y_train, n_label)
22Y_test = np_utils.to_categorical(y_test, n_label)
23# 試しに、どんなインプットイメージが見てみる
24%matplotlib inline
25import matplotlib.cm as cm
26
27i = 7
28plt.imshow(X_train[i, 0], interpolation='nearest', cmap=cm.binary)
29print("label : ", Y_train[i,:])
30# CNNモデルの構築
31# 単純なconv1層 x full connect1層モデル
32n_filter = 16
33size_filter = 5
34size_pool = 2
35n_hidden = 100
36
37model = Sequential()
38model.add(Convolution2D(n_filter, size_filter, size_filter,
39                        border_mode='same', input_shape = (1, size_img, size_img)))
40model.add(Activation("relu"))
41model.add(MaxPooling2D(pool_size=(size_pool, size_pool)))
42model.add(Dropout(0.2))
43model.add(Flatten())
44model.add(Dense(n_hidden))
45model.add(Dropout(0.2))
46model.add(Dense(n_label))
47model.add(Activation('softmax'))
48          
49model.compile(loss='categorical_crossentropy', optimizer='Adam', metrics=['accuracy'])
50# 学習
51model.fit(X_train, Y_train, batch_size=50, nb_epoch=10,
52          verbose=1, validation_split=0.1)
53vs = model.evaluate(X_test, Y_test)
54print("\nTest classification rate %0.05f" % vs[1])
55# ~99%と高い正解率
56# 正誤表
57print('Cross tabulation')
58y_pred = model.predict_classes(X_test)
59pd.crosstab(y_pred, y_test)
60# そこで実際に、間違いの数字を見る。
61# 青ラベル：実際の数字；赤ラベル：間違えて予測した数字
62test_wrong = [im for im in zip(X_test, y_pred, y_test)
63              if im[1] != im[2]]
64print(len(test_wrong))
65
66plt.figure(figsize=(15, 15))
67for ind, val in enumerate(test_wrong):
68    plt.subplots_adjust(left=0, right=1, top=1, bottom=0)
69    plt.subplot(11, 11, ind + 1)
70#     plt.subplot(11, 11, ind)
71    im = 1 - val[0][0]
72    plt.axis("off")
73    plt.imshow(im, cmap='gray')
74    plt.text(8, 0, val[1], fontsize=14, color='red')
75    plt.text(0, 0, val[2], fontsize=14, color='blue')
76#     break