[Week 2 A2 Exercise 6] Programming Assignment

[jalfvale]

Hi,

I’m getting the following error that seems not to be in the code written by me:

UnboundLocalError Traceback (most recent call last)
in
----> 1 params, grads, costs = optimize(w, b, X, Y, num_iterations=100, learning_rate=0.009, print_cost=False)
2
3 print ("w = " + str(params[“w”]))
4 print ("b = " + str(params[“b”]))
5 print ("dw = " + str(grads[“dw”]))

in optimize(w, b, X, Y, num_iterations, learning_rate, print_cost)
40
41 # Retrieve derivatives from grads
—> 42 dw = grads[“dw”]
43 db = grads[“db”]
44

UnboundLocalError: local variable ‘grads’ referenced before assignment

Could you tell me  if the root cause comes from my code or how to fix it, please?

[ace.b]

@jalfvale

optimize

Have you declared grads before calling it ?

[jalfvale]

Thank you so much for your quick answer, ace.b. The point is that grads is used not by my code but by the “external” one:

{moderator edit - solution code removed}

[ace.b]

@jalfvale

 for i in range(num_iterations):
        # (≈ 1 lines of code)
        # Cost and gradient calculation 
        # grads, cost = ...
        # YOUR CODE STARTS HERE

You have to declare grads and cost as mentioned in the tips :
1) Calculate the cost and the gradient for the current parameters. Use propagate().

[jalfvale]

   Oops, now I see it! That's been absoultely my fault. 

   Thanks again!

[pranav0809]

my code has passed all the tests but fails for the last part

model_test(model) It shows the following error AssertionError: Wrong values for d['w']. [[ 0.28154433] [-0.11519574] [ 0.13142694] [ 0.20526551]] != [[ 0.00194946] [-0.0005046 ] [ 0.00083111] [ 0.00143207]]

how do i fix it

[jalfvale]

Try removing the parameters’ values for num_iterations=100, learning_rate=0.009, print_cost=False when calling optimize, so they get values from the ones used in model:

def model(X_train, Y_train, X_test, Y_test, num_iterations=2000, learning_rate=0.5, print_cost=False):

[pranav0809]

thank you , I got it