Course 1 week 4, first coding assignment section 4.3

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

I’m stuck on section 4.3 L_model_forward
I get the error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-80-10fc901e800a> in <module>
      1 t_X, t_parameters = L_model_forward_test_case_2hidden()
----> 2 t_AL, t_caches = L_model_forward(t_X, t_parameters)
      3 
      4 print("AL = " + str(t_AL))
      5 

<ipython-input-79-8ad15709ebfe> in L_model_forward(X, parameters)
     41     # YOUR CODE STARTS HERE
     42 
---> 43         AL, cache = linear_activation_forward(A, parameters['W' + str(l)], parameters['b' + str(l)], 'sigmoid')
     44         caches.append(cache)
     45 #         AL, cache = linear_activation_forward(A, parameters['W' + str(l)], parameters['b' + str(l)], activation='sigmoid')

<ipython-input-61-86db2fd9a9de> in linear_activation_forward(A_prev, W, b, activation)
     22         # A, activation_cache = ...
     23         # YOUR CODE STARTS HERE
---> 24         Z, linear_cache = linear_forward(A_prev, W, b)
     25         A, activation_cache = sigmoid(Z)
     26 

<ipython-input-59-ef0b4f29e360> in linear_forward(A, W, b)
     19     # YOUR CODE STARTS HERE
     20 
---> 21     Z = np.dot(W,A) + b
     22 
     23     # YOUR CODE ENDS HERE

<__array_function__ internals> in dot(*args, **kwargs)

ValueError: shapes (4,5) and (4,4) not aligned: 5 (dim 1) != 4 (dim 0)

I know it means that my dimensions are incorrect, but it does not make any sense to me. I’ve tried to get the transpose of the weight matrix, but then I get a broadcasting error with b. This is for the sigmoid section.

Any suggestions greatly appreciated

2

Hello @cre8ture
I suggest you please check which weight matrix you are passing for the sigmoid activation.
[Hint: Is it the weight for the intermediate layer Wl or for the last layer WL]

I hope you get it.
All the best

1 Like
3

Thanks a lot! @Rajat! I got it to work

1 Like