Neural Machine Translation Assignment: ValueErrror

Course Q&A Deep Learning Specialization Sequence Models
1

I am working on W3A1, all the test passed, but when run the
model.fit([Xoh, s0, c0], outputs, epochs=1, batch_size=100)

I got the following error. Not sure what’s going wrong. How can I debug?

ValueError: The two structures don't have the same sequence length. Input structure has length 10, while shallow structure has length 1.

And my model summery is:

Model: "functional_5"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_3 (InputLayer)            [(None, 30, 37)]     0                                            
__________________________________________________________________________________________________
s0 (InputLayer)                 [(None, 64)]         0                                            
__________________________________________________________________________________________________
bidirectional_2 (Bidirectional) (None, 30, 64)       17920       input_3[0][0]                    
__________________________________________________________________________________________________
repeat_vector (RepeatVector)    (None, 30, 64)       0           s0[0][0]                         
                                                                 lstm[20][1]                      
                                                                 lstm[21][1]                      
                                                                 lstm[22][1]                      
                                                                 lstm[23][1]                      
                                                                 lstm[24][1]                      
                                                                 lstm[25][1]                      
                                                                 lstm[26][1]                      
                                                                 lstm[27][1]                      
                                                                 lstm[28][1]                      
__________________________________________________________________________________________________
concatenate (Concatenate)       (None, 30, 128)      0           bidirectional_2[0][0]            
                                                                 repeat_vector[20][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[21][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[22][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[23][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[24][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[25][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[26][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[27][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[28][0]             
                                                                 bidirectional_2[0][0]            
                                                                 repeat_vector[29][0]             
__________________________________________________________________________________________________
dense (Dense)                   (None, 30, 10)       1290        concatenate[20][0]               
                                                                 concatenate[21][0]               
                                                                 concatenate[22][0]               
                                                                 concatenate[23][0]               
                                                                 concatenate[24][0]               
                                                                 concatenate[25][0]               
                                                                 concatenate[26][0]               
                                                                 concatenate[27][0]               
                                                                 concatenate[28][0]               
                                                                 concatenate[29][0]               
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 30, 1)        11          dense[20][0]                     
                                                                 dense[21][0]                     
                                                                 dense[22][0]                     
                                                                 dense[23][0]                     
                                                                 dense[24][0]                     
                                                                 dense[25][0]                     
                                                                 dense[26][0]                     
                                                                 dense[27][0]                     
                                                                 dense[28][0]                     
                                                                 dense[29][0]                     
__________________________________________________________________________________________________
attention_weights (Activation)  (None, 30, 1)        0           dense_1[20][0]                   
                                                                 dense_1[21][0]                   
                                                                 dense_1[22][0]                   
                                                                 dense_1[23][0]                   
                                                                 dense_1[24][0]                   
                                                                 dense_1[25][0]                   
                                                                 dense_1[26][0]                   
                                                                 dense_1[27][0]                   
                                                                 dense_1[28][0]                   
                                                                 dense_1[29][0]                   
__________________________________________________________________________________________________
dot (Dot)                       (None, 1, 64)        0           attention_weights[20][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[21][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[22][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[23][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[24][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[25][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[26][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[27][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[28][0]         
                                                                 bidirectional_2[0][0]            
                                                                 attention_weights[29][0]         
                                                                 bidirectional_2[0][0]            
__________________________________________________________________________________________________
c0 (InputLayer)                 [(None, 64)]         0                                            
__________________________________________________________________________________________________
lstm (LSTM)                     [(None, 64), (None,  33024       dot[20][0]                       
                                                                 s0[0][0]                         
                                                                 c0[0][0]                         
                                                                 dot[21][0]                       
                                                                 lstm[20][1]                      
                                                                 lstm[20][2]                      
                                                                 dot[22][0]                       
                                                                 lstm[21][1]                      
                                                                 lstm[21][2]                      
                                                                 dot[23][0]                       
                                                                 lstm[22][1]                      
                                                                 lstm[22][2]                      
                                                                 dot[24][0]                       
                                                                 lstm[23][1]                      
                                                                 lstm[23][2]                      
                                                                 dot[25][0]                       
                                                                 lstm[24][1]                      
                                                                 lstm[24][2]                      
                                                                 dot[26][0]                       
                                                                 lstm[25][1]                      
                                                                 lstm[25][2]                      
                                                                 dot[27][0]                       
                                                                 lstm[26][1]                      
                                                                 lstm[26][2]                      
                                                                 dot[28][0]                       
                                                                 lstm[27][1]                      
                                                                 lstm[27][2]                      
                                                                 dot[29][0]                       
                                                                 lstm[28][1]                      
                                                                 lstm[28][2]                      
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 11)           715         lstm[20][1]                      
                                                                 lstm[21][1]                      
                                                                 lstm[22][1]                      
                                                                 lstm[23][1]                      
                                                                 lstm[24][1]                      
                                                                 lstm[25][1]                      
                                                                 lstm[26][1]                      
                                                                 lstm[27][1]                      
                                                                 lstm[28][1]                      
                                                                 lstm[29][1]                      
==================================================================================================
Total params: 52,960
Trainable params: 52,960
Non-trainable params: 0
2

Your model summary seems correct (similar to what I got).

Are you sure your input and output data are the same as I highlighted in the image below?

Capture
Capture1044×340 70.9 KB

If so, maybe something else goes wrong with your assignment. Here is the guide to get a fresh copy of your assignment.

3

Yes. It’s same. This is a non-editable cell and I didn’t change it.

### You cannot edit this cell
s0 = np.zeros((m, n_s))
c0 = np.zeros((m, n_s))
outputs = list(Yoh.swapaxes(0,1))
4

Then getting a fresh copy might help.

5

Thanks. It does help. I just redo everything and it works. But after compare with my original work, I found that the problem is I accidentally revert the s0 and c0 in the inputs when create the model. It turn out they have same shape, so all the test would not catch the error. Only when fit the model, the input doesn’t match.

Model(inputs=[X, s0, c0], outputs=outputs)
2 Likes
6

That is a common mistake. Nice work on catching it!