Error of exercise 5 in Building_your_Deep_Neural_Network_Step_by_Step

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

Hi There,
I am getting an error in exercise 5. Please kindly help! Thanks very much

UnboundLocalError Traceback (most recent call last)
in
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

in L_model_forward(X, parameters)
23 for l in range(1, L):
24 A_prev = A
—> 25 A, cache = linear_activation_forward(A_prev,parameters[‘W’+str(l)],parameters[‘b’+str(l)], relu)
26
27 caches.append(cache)

in linear_activation_forward(A_prev, W, b, activation)
29
30
—> 31 cache = (linear_cache, activation_cache)
32
33 return A, cache

UnboundLocalError: local variable ‘linear_cache’ referenced before assignment

2

Take a look at the logic in linear_activation_forward. That error message means you are not taking either of the “if” branches. Why would that happen? Note that the conditions there are using the string name of the activation function. But what you passed is not a string, but actually a reference (pointer) to the function, right?

1 Like
3

got it, relu and sigmoid should be passed as ‘relu’ and ‘sigmoid’, thanks Paul!

2 Likes