Python 3.x 不兼容的形状：[32]对[4536][{{{node logistic_loss/mul}}]]

我正在训练具有以下结构和参数的分类器：

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
encoder_input (InputLayer)      (None, 567, 1)       0                                            
__________________________________________________________________________________________________
conv1d_1 (Conv1D)               (None, 189, 32)      128         encoder_input[0][0]              
__________________________________________________________________________________________________
conv1d_2 (Conv1D)               (None, 63, 64)       6208        conv1d_1[0][0]                   
__________________________________________________________________________________________________
conv1d_3 (Conv1D)               (None, 21, 100)      19300       conv1d_2[0][0]                   
__________________________________________________________________________________________________
flatten_1 (Flatten)             (None, 2100)         0           conv1d_3[0][0]                   
__________________________________________________________________________________________________
z_mean (Dense)                  (None, 20)           42020       flatten_1[0][0]                  
__________________________________________________________________________________________________
z_log_var (Dense)               (None, 20)           42020       flatten_1[0][0]                  
__________________________________________________________________________________________________
z (Lambda)                      (None, 20)           0           z_mean[0][0]                     
                                                                 z_log_var[0][0]                  
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 64)           1344        z[0][0]                          
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 128)          8320        dense_1[0][0]                    
__________________________________________________________________________________________________
dense_3 (Dense)                 (None, 200)          25800       dense_2[0][0]                    
__________________________________________________________________________________________________
dense_10 (Dense)                (None, 4)            804         dense_3[0][0]                    
==================================================================================================
Total params: 145,944
Trainable params: 145,944
Non-trainable params: 0

除

密集

层以外的所有层均取自不同的模型。此处仅可训练

密集

层参数。这是用于培训的代码片段：

for layer in classifier.layers[:-4]:
  layer.trainable = False
classifier.fit(x_train, y_train,
        epochs=50,
        batch_size=8,
        validation_data=(x_val, y_val)
              )
classifier.save_weights('cnn_hhar.h5')

但是我得到了这个

invalidargumeinterror:不兼容的形状：[32]和[4536]
[{{node logistic_loss/mul}}]

这个代码有什么问题

编辑： 该代码是可用的。它基本上是改编自一个代码的变化自动编码器。我将编码器部分添加到FC层，以执行分类任务。

“此代码有什么问题？”确切的代码是什么？请添加一些，以便我们可以查看我已在此处添加了代码：。请看一下。“这个代码有什么问题？”确切的代码是什么？请添加一些，以便我们可以查看我已在此处添加了代码：。请看一看。