我试图构建一个简单的分类卷积神经网络（CNN），使用以下代码将1233张图像分为4个类别：

unclassified_datagen = keras.preprocessing.image.ImageDataGenerator(    rescale=1. / 255,    horizontal_flip=True)unclassified_generator = train_datagen.flow_from_directory(    'data/unclassified',    target_size=(120, 120),    batch_size=1233,    class_mode='input',    shuffle=False,)model_unclassified = keras.Sequential()model_unclassified.add(layers.Conv2D(1233, (3, 3), input_shape=(120, 120, 3), padding="SAME"))model_unclassified.add(layers.Dense(64, activation='relu'))model_unclassified.add(layers.Dense(4, activation='sigmoid'))model_unclassified.compile(loss='sparse_categorical_crossentropy',                           optimizer='rmsprop',                           metrics=['accuracy'])model_unclassified.fit_generator(unclassified_generator, epochs=1)

但我得到了以下错误： ValueError: Error when checking target: expected dense_2 to have shape (120, 120, 1) but got array with shape (120, 120, 3)

我做错了什么？

回答：

你应该添加一个Flatten层，因为Conv2D为每个样本返回一个3D数组：

model_unclassified = keras.Sequential()model_unclassified.add(layers.Conv2D(1233, (3, 3), input_shape=(120, 120, 3), padding="SAME"))model_unclassified.add(layers.Flatten())model_unclassified.add(layers.Dense(64, activation='relu'))model_unclassified.add(layers.Dense(4, activation='sigmoid'))