# \[Week 2 A2 Exercise 6\] Programming Assignment **URL:** \ **Category:** Neural Networks and Deep Learning\ **Tags:** coursera-platform\ **Created:** [April 29, 2021, 3:48pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363 "2021-04-29T15:48:58Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![jalfvale](https://avatars.discourse-cdn.com/v4/letter/j/a6a055/32.png) [@jalfvale](https://community.deeplearning.ai/u/jalfvale)\ **Post date:** [April 29, 2021, 3:48pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/1 "2021-04-29T15:48:58Z")
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? ``` ---
**Author:** ![ace.b](https://avatars.discourse-cdn.com/v4/letter/a/977dab/32.png) [@ace.b](https://community.deeplearning.ai/u/ace.b)\ **Post date:** [April 29, 2021, 3:56pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/2 "2021-04-29T15:56:47Z")
> [@jalfvale](#): > > optimize Have you declared grads before calling it ? ---
**Author:** ![jalfvale](https://avatars.discourse-cdn.com/v4/letter/j/a6a055/32.png) [@jalfvale](https://community.deeplearning.ai/u/jalfvale)\ **Post date:** [April 29, 2021, 4:09pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/3 "2021-04-29T16:09:17Z")
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}_ ---
**Author:** ![ace.b](https://avatars.discourse-cdn.com/v4/letter/a/977dab/32.png) [@ace.b](https://community.deeplearning.ai/u/ace.b)\ **Post date:** [April 29, 2021, 4:24pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/4 "2021-04-29T16:24:24Z")
> [@jalfvale](#): > > ```auto > 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(). ---
**Author:** ![jalfvale](https://avatars.discourse-cdn.com/v4/letter/j/a6a055/32.png) [@jalfvale](https://community.deeplearning.ai/u/jalfvale)\ **Post date:** [April 29, 2021, 5:04pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/5 "2021-04-29T17:04:47Z")
``` Oops, now I see it! That's been absoultely my fault. Thanks again! ``` ---
**Author:** ![pranav0809](https://avatars.discourse-cdn.com/v4/letter/p/ce7236/32.png) [@pranav0809](https://community.deeplearning.ai/u/pranav0809)\ **Post date:** [April 30, 2021, 12:14pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/6 "2021-04-30T12:14:24Z")
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 ---
**Author:** ![jalfvale](https://avatars.discourse-cdn.com/v4/letter/j/a6a055/32.png) [@jalfvale](https://community.deeplearning.ai/u/jalfvale)\ **Post date:** [May 1, 2021, 10:52pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/7 "2021-05-01T22:52:21Z")
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): ---
**Author:** ![pranav0809](https://avatars.discourse-cdn.com/v4/letter/p/ce7236/32.png) [@pranav0809](https://community.deeplearning.ai/u/pranav0809)\ **Post date:** [May 2, 2021, 4:56pm UTC](https://community.deeplearning.ai/t/week-2-a2-exercise-6-programming-assignment/2363/8 "2021-05-02T16:56:20Z")
thank you , I got it