Exercise 8 Model: Issue with shape of X_Train

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

In multiline comments of model function it states:

X_train – training set represented by a numpy array of shape (num_px * num_px * 3, m_train)

However, when I print the shape of X_train I get (4, 7)

here is the traceback after running the code:

(4, 7)

ValueError Traceback (most recent call last)
in
1 from public_tests import *
2
----> 3 model_test(model)

~/work/release/W2A2/public_tests.py in model_test(target)
123 y_test = np.array([0, 1, 0])
124
→ 125 d = target(X, Y, x_test, y_test, num_iterations=50, learning_rate=0.01)
126
127 assert type(d[‘costs’]) == list, f"Wrong type for d[‘costs’]. {type(d[‘costs’])} != list"

in model(X_train, Y_train, X_test, Y_test, num_iterations, learning_rate, print_cost)
39 w, b = initialize_with_zeros(num_px * num_px * 3)
40
—> 41 params, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)
42
43 w = params[‘w’]

in optimize(w, b, X, Y, num_iterations, learning_rate, print_cost)
36 # YOUR CODE STARTS HERE
37
—> 38 grads, cost = propagate(w, b , X, Y)
39
40 # YOUR CODE ENDS HERE

in propagate(w, b, X, Y)
31 # YOUR CODE STARTS HERE
32
—> 33 A = sigmoid(np.dot(w.T, X) + b)
34 cost = (-1/m) * (np.sum(np.dot(Y, np.log(A).T) + np.dot((1 - Y), np.log(1 - A).T)))
35

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

ValueError: shapes (1,12288) and (4,7) not aligned: 12288 (dim 1) != 4 (dim 0)

Please advise. I am unsure if I made a mistake somewhere (entirely possible), but after spending quite some time debugging, I think the error is with X_train because the shape is wrong…

Any help would be greatly appreciated!

2

Hi @Joseph_Caldwell ,

Actually, when you test the model function, the shape of the 2 tests are (4, 7) and (4, 3), so that looks fine.

It seems your error is happening when you start training your model, and at that point your X_train is the train_set_x which is created above in Exercise 2. You may want to start by checking your earlier exercises.

3

That type of error usually means you are referencing global variables from the local scope of the model function. E.g. it is a mistake to reference train_set_x directly there, since that may not be what is actually passed to the function, as we see in this case.

4

Had the same issue. It works for me:

under def model(), change the initialization code to

{moderator edit - solution code removed}

I previous wrote w, b = initialize_with_zeros(num_px*num_px*3)