Kerasを用いて、画像認識

前提・実現したいこと

現在CNN、Kerasを用いて画像認識を行っています。
その中でホールアウト法では学習を行うことはできたのですが、
クロスバリデーションで学習をさせてみたいです。

その中で以下のエラーが発生したので、
教えていただけると幸いです。

発生している問題・エラーメッセージ

Traceback (most recent call last):
  File "learning2.py", line 161, in <module>
    shuffle=True,callbacks=[early_stopping])
  File "/home/mlab-user/anaconda3/envs/image/lib/python3.5/site-packages/keras/engine/training.py", line 970, in fit
    batch_size=batch_size)
  File "/home/mlab-user/anaconda3/envs/image/lib/python3.5/site-packages/keras/engine/training.py", line 787, in _standardize_user_data
    exception_prefix='target')
  File "/home/mlab-user/anaconda3/envs/image/lib/python3.5/site-packages/keras/engine/training_utils.py", line 127, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking target: expected dense_2 to have 2 dimensions, but got array with shape (10800, 3, 3, 3)

該当のソースコード

import keras
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.convolutional import MaxPooling2D
from keras.layers import Conv2D, Flatten, Dense, Dropout
from sklearn.model_selection import train_test_split
from PIL import Image
from keras.callbacks import EarlyStopping
import numpy as np
import glob
import matplotlib.pyplot as plt
from sklearn.model_selection import KFold
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix


classes = ["犬","猫","兎"
           ]

num_classes = len(classes)

X = []
Y = []
for index, classlabel in enumerate(classes):
    dir = "./" + classlabel 
    files = glob.glob(dir + "/*.jpg")
    for i, file in enumerate(files):
        image = Image.open(file)
        image = image.convert("RGB")
        image = image.resize((128, 128))
        data = np.asarray(image)
        X.append(data)
        Y.append(index)

X = np.array(X)
Y = np.array(Y)
X = X.astype('float32')/255.0

Y = np_utils.to_categorical(Y, num_classes)
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.1)

kf = KFold(n_splits=10, shuffle=True)
all_loss=[]
all_val_loss=[]
all_acc=[]
all_val_acc=[]

for train_index, val_index in kf.split(X_train, y_train):

    train_data=X_train[train_index]
    train_label=y_train[train_index]
    val_data=X_train[val_index]
    val_label=y_train[val_index]

    y_train = np_utils.to_categorical(y_train, num_classes)
    y_test = np_utils.to_categorical(y_train, num_classes)

    model = Sequential()
    model.add(Conv2D(32, (3, 3), padding='same',input_shape=X_train.shape[1:], activation="relu"))
    model.add(Conv2D(32, (3, 3), padding='same', activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Conv2D(64, (3, 3), padding='same', activation="relu"))
    model.add(Conv2D(64, (3, 3), padding='same', activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Conv2D(128, (3, 3), padding='same', activation="relu"))
    model.add(Conv2D(128, (3, 3), padding='same', activation="relu"))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Flatten())
    model.add(Dense(128 ,activation="relu"))
    model.add(Dropout(0.5))
    model.add(Dense(num_classes, activation="softmax"))

    # model.summary()

    opt = keras.optimizers.Adam(lr=0.0005, decay=1e-5)
    model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])

    # patience -> 10回学習して精度が上がらなかったとき、終了する
    early_stopping = EarlyStopping(monitor='val_acc', min_delta=0.8, patience=5, verbose=1)

    hist = model.fit(train_data, train_label, batch_size=10, verbose=1,
                    epochs=10, validation_data=(val_data, y_test),
                    shuffle=True,callbacks=[early_stopping])

    score=model.evaluate(X_test, y_test)
    print('Test loss:', score[0])
    print('test acc:', score[1])

model.save('./cnn.h5')