kerasによる最終層の出力の設定

問題点

kerasによる画像認識を拝見し，Inception v3のfine tuning(4クラス分類)をやりたいと思っています．
しかし，最終層の設定において出力を4つに設定し，モデルのサマリを見ても

dense_1 (Dense)                  (None, 4)             8196        global_average_pooling2d_1[0][0] 

となっているにも関わらず，以下のエラーが出ます

ValueError: Error when checking target: expected dense_1 to have shape (None, 1) but got array with shape (32, 4)

何が原因かが未だ分からないので助言をお願いしたいと思います．
以下ソースコードです．

該当のソースコード

import os
from keras.applications.inception_v3 import InceptionV3
from keras.applications.inception_v3 import preprocess_input
from keras.models import Sequential, Model
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2D, GlobalAveragePooling2D, AveragePooling2D
from keras.regularizers import l2
from keras.utils import np_utils
from keras.utils import plot_model
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint
import matplotlib.pyplot as plt
import keras.backend as K

epoch = 2

result_dir = 'D:/result'
if not os.path.exists(result):
    os.mkdir(result_dir)


def plot_history(history):
    # 精度の履歴をプロット
    plt.plot(history.history['acc'], "o-", label="accuracy")
    plt.plot(history.history['val_acc'], "o-", label="val_acc")
    plt.title('model accuracy')
    plt.xlabel('epoch')
    plt.ylabel('accuracy')
    plt.legend(loc="lower right")
    plt.show()

    # 損失の履歴をプロット
    plt.plot(history.history['loss'], "o-", label="loss", )
    plt.plot(history.history['val_loss'], "o-", label="val_loss")
    plt.title('model loss')
    plt.xlabel('epoch')
    plt.ylabel('loss')
    plt.legend(loc='lower right')
    plt.show()


def save_history(history, result_file):
    loss = history.history['loss']
    acc = history.history['acc']
    val_loss = history.history['val_loss']
    val_acc = history.history['val_acc']
    nb_epoch = len(acc)

    with open(result_file, "w") as fp:
        fp.write("epoch\tloss\tacc\tval_loss\tval_acc\n")
        for i in range(nb_epoch):
            fp.write("%d\t%f\t%f\t%f\t%f\n" % (i, loss[i], acc[i], val_loss[i], val_acc[i]))


if __name__ == '__main__':
    classes = ['m', 'n', 'o', 'k']

    batch_size = 32
    nb_classes = len(classes)
    img_rows, img_cols = 299, 299

    samples_per_epoch = 600
    nb_val_samples = 99

    # CNNを構築
    # Inception v3モデルの読み込み，最終層は読み込まない
    base_model = InceptionV3(weights='imagenet', include_top=False)
    # 最終層の設定
    x = base_model.output
    x = GlobalAveragePooling2D()(x)
    predictions = Dense(nb_classes, kernel_initializer="glorot_uniform", activation="softmax",
                        kernel_regularizer=l2(.0005))(x)

    # モデルのサマリを表示
    model = Model(inputs=base_model.input, outputs=predictions)
    plot_model(model, show_shapes=True, to_file=os.path.join(result_dir, 'model.png'))
    model.summary()

    # base_modelはweightsを更新しない
    for layer in base_model.layers:
        layer.trainable = False

    model.compile(loss='categorical_crossentropy',
                  optimizer='adam',
                  metrics=['accuracy'])

    # ディレクトリの画像を使ったジェネレータ
    train_datagen = ImageDataGenerator(
        rescale=1.0 // 255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

    test_datagen = ImageDataGenerator(rescale=1.0 // 255)

    train_generator = train_datagen.flow_from_directory(
        directory='D:/s_dir/train_images',
        target_size=(img_rows, img_cols),
        color_mode='rgb',
        classes=classes,
        class_mode='categorical',
        batch_size=batch_size,
        shuffle=True)

    # 確認
    print(train_generator.class_indices)

    test_generator = test_datagen.flow_from_directory(
        directory='D:/s_dir/test_images',
        target_size=(img_rows, img_cols),
        color_mode='rgb',
        classes=classes,
        class_mode='categorical',
        batch_size=batch_size,
        shuffle=True)

    checkpointer = ModelCheckpoint(filepath='D:/result/model.{epoch:02d}-{val_loss:.2f}.hdf5', verbose=1,
                                   save_best_only=True)

    history = model.fit_generator(
        train_generator,
        steps_per_epoch=samples_per_epoch,
        epochs=epoch,
        validation_data=test_generator,
        validation_steps=nb_val_samples,
        callbacks=[checkpointer])

    save_history(history, os.path.join(result, 'history.txt'))

    # modelに学習させた時の変化の様子をplot
    plot_history(history)

    loss, acc = model.evaluate_generator(test_generator, steps=400)
    print('Test loss:', loss)
    print('Test acc:', acc)

    K.clear_session()