Optimization part of programming assignment in week 2

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

I ran into an error when I tried to run the optimize part of my code. Here is the code I wrote:

num_features = np.shape(X_train[1])
print num_features
w, b = initialize_with_zeros(num_features)

params, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost=False)
Y_prediction_test = predict(w,b,X_test)
Y_prediction_train = predict(w,b,X_train)

And here is the error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-43-9408a3dffbf6> in <module>
      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"

<ipython-input-42-d09e9e35850c> in model(X_train, Y_train, X_test, Y_test, num_iterations, learning_rate, print_cost)
     37 
     38     num_features = np.shape(X_train[0])
---> 39     w, b = initialize_with_zeros(num_features)
     40 
     41     params, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost=False)

<ipython-input-17-f3716dfa2501> in initialize_with_zeros(dim)
     17     # b = ...
     18     # YOUR CODE STARTS HERE
---> 19     w = np.zeros((dim,1))
     20     b = 0.0
     21 

TypeError: 'tuple' object cannot be interpreted as an integer
2

image
image678×130 13.5 KB

That’s going to return a list or tuple (the shape of the first row of X_train).
That’s not what you want.

Instead, try X_train.shape[0]

That will return an int, (the first element in the ‘shape’ list).

It might work.

3

Thank you so much! I don’t why I used that syntax! Too long away from programming I guess.