收到错误“ ValueError：检查目标时出错：预期density_4具有形状（3，）但形状为（2，）的数组”

Question

我正在使用CNN进行文本分类（遵循kim yoon方法） 但出现错误，我无法弄清

我查看了类似问题的帖子，但无法关注

inputs = Input(shape=(sequence_length,))

embedding = embedding_layer(inputs)

reshape = Reshape((sequence_length,embedding_dim,1))(embedding)

conv_0 = Conv2D(num_filters, (filter_sizes[0], 
embedding_dim),activation='relu',kernel_regularizer=regularizers.l2(0.01)) 
(reshape)

conv_1 = 
 Conv2D(num_filters,filter_sizes[1],embedding_dim),activation='relu',
 kernel_regularizer=regulari zers.l2(0.01))(reshape)

conv_2 = Conv2D(num_filters, 
(filter_sizes[2],embedding_dim),activation='relu',kernel_regularizer=
 regularizers.l2(0.01))(reshape)

 maxpool_0 = MaxPooling2D((sequence_length - filter_sizes[0] + 1, 1), 
 strides=(1,1))(conv_0)

 flat_0 = Flatten()(maxpool_0)

 maxpool_1 = MaxPooling2D((sequence_length - filter_sizes[1] + 1, 1), 
 strides=(1,1))(conv_1)

 flat_1 = Flatten()(maxpool_1)

 maxpool_2 = MaxPooling2D((sequence_length - filter_sizes[2] + 1, 1), 
 strides=(1,1))(conv_2)

 flat_2 = Flatten()(maxpool_2)
 merged_tensor = concatenate([flat_0,flat_1, flat_2])
 output = Dense(units=3, 
 activation='softmax',kernel_regularizer=regularizers.l2(0.01(merged_tensor)

ValueError跟踪（最近一次通话最近）  在       1个 ----> 2 model.fit（x_train，y_train，batch_size，epochs = 100，verbose = 1，callbacks = callback）       3＃开始训练

ValueError：检查目标时出错：预期density_4的形状为（3，），但数组的形状为（2，）

当然，消息中还有更多数据，如有需要，我会予以整理

dence_4是最终输出