如何解决此Keras ValueErrors进行图像分类？

Question

我正在尝试使用keras库执行二进制图像分类，但是在检查目标时出现ValueError错误：预期density_1具有4维，但数组的形状为（32，2）

classifier.add(Conv2D(filters=32, kernel_size=(3,3), input_shape=(64,64,3), activation='relu'))
classifier.add(Conv2D(filters=32, kernel_size=(3,3), activation='relu'))
#Pooling_layers
classifier.add(MaxPooling2D(pool_size=(2,2)))
#conv_layers
classifier.add(Conv2D(filters=32, kernel_size=(3,3), activation='relu'))
classifier.add(Conv2D(filters=32, kernel_size=(3,3), activation='relu'))
#Max_pooling_layers
classifier.add(MaxPooling2D(pool_size=(2,2)))
classifier.add(Dense(units=2, activation='softmax'))
#Compile_classifier
classifier.compile(optimizer = 'adam', loss='categorical_crossentropy', metrics=['accuracy'])


from keras.preprocessing.image import ImageDataGenerator

train_datagen=ImageDataGenerator(rescale=1./255)

train_set = train_datagen.flow_from_directory(
        'dataset/train',
        target_size=(64,64),
        batch_size=32,
        class_mode='categorical')

test_datagen=ImageDataGenerator(rescale=1./255)

test_set = test_datagen.flow_from_directory(
        'dataset/test',
        target_size=(64,64),
        batch_size=32,
        class_mode='categorical')

classifier.fit_generator(
        train_set,
        steps_per_epoch=9000,
        epochs=25,
        validation_data=test_set,
        validation_steps=3000)

在执行程序时，出现此错误消息。

ValueError: Error when checking target: expected dense_1 to have 4 dimensions, but got array with shape (32, 2)