Week 04 assignment 1 exercise 5

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

In function L_model_forward getting this error;

ValueError: shapes (3,4) and (3,4) not aligned: 4 (dim 1) != 3 (dim 0)

How to debug?

Code;
for l in range(1, L):
A_prev = A

    A, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)], 'relu')
    caches.append(cache)




AL,cache = linear_activation_forward(A,parameters["W"+str(l)],parameters["b"+str(l)], activation = 'sigmoid')          
caches.append(cache)
2

Dot product of 2 matrics requires that the inner dimensions match. i.e. they should be of shape (a, b) and (b,c) to produce a result of (a, c).

If you’re having trouble tracking the bug, click my name and message your notebook as an attachment.

3

Please fix computation of AL, cache (outside the for loop for the sigmoid activation function). You should use the correct layer for this.