Keras编码器解码器预计有2个维度

Keras编码器解码器返回InvalidArgumentError，因为输入的形状似乎不兼容 .

我有：

• X_numerical.shape给出（304,2500,4） input data

• y_numerical.shape给出（304,40,22） output data

Keras编码器 - 解码器如下：

# Define an input sequence and process it. 
encoder_inputs = Input(shape=(None, 4)) 
encoder = LSTM(32, return_state=True) 
encoder_outputs, state_h, state_c = encoder(encoder_inputs)

# We discard `encoder_outputs` and only keep the states. 
encoder_states = [state_h, state_c]

# Set up the decoder, using `encoder_states` as initial state. 
decoder_inputs = Input(shape=(None, 22))
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference. 
decoder_lstm = LSTM(32, return_sequences=True, return_state=True) 
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
                                     initial_state=encoder_states) 
decoder_dense = Dense(22, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)

# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data` 
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

# Run training 
model.compile(optimizer='rmsprop', loss='categorical_crossentropy') 

### THE ERROR OCCURS IN THE `.fit()` CALL
model.fit([X_numerical, y_numerical], y_numerical,
          batch_size=4,
          epochs=1)

我收到以下错误：

InvalidArgumentError Traceback（最近一次调用last）in（）25 model.fit（[X_numerical，y_numerical]，y_numerical，26 batch_size = 4，---> 27 epochs = 1）InvalidArgumentError：不兼容的形状：[4,40,22 ]与[1,22,1] [[节点：training_6 / RMSprop / gradients / dense_15 / add_grad / BroadcastGradientArgs = BroadcastGradientArgs [T = DT_INT32，class = [“loc：@ training_6 / RMSprop / gradient / dense_15 / add_grad / Sum “]， device =”/ job：localhost / replica：0 / task：0 / device：CPU：0“]（training_6 / RMSprop / gradient / dense_15 / add_grad / Shape，training_6 / RMSprop / gradient / dense_15 / add_grad / Shape_1 ）]]

我试图做的是将y_numerical重塑为（304,22,40），但是没有用 . 我也尝试了 y_numerical .squeeze() 并在model.fit（）调用中更改了batch_size，它们都返回了各种错误 .

这个维度错误的原因可能是什么？

我的模型摘要是：

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_37 (InputLayer)           (None, None, 4)      0                                            
__________________________________________________________________________________________________
input_38 (InputLayer)           (None, None, 22)     0                                            
__________________________________________________________________________________________________
lstm_39 (LSTM)                  [(None, 32), (None,  4736        input_37[0][0]                   
__________________________________________________________________________________________________
lstm_40 (LSTM)                  [(None, None, 32), ( 7040        input_38[0][0]                   
                                                                 lstm_39[0][1]                    
                                                                 lstm_39[0][2]                    
__________________________________________________________________________________________________
dense_19 (Dense)                (None, None, 22)     726         lstm_40[0][0]                    
==================================================================================================
Total params: 12,502
Trainable params: 12,502
Non-trainable params: 0
__________________________________________________________________________________________________