Course 2 Week 1 Gradient_Checking assigmnet

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
1

I have written and thoroughly checked my code still getting following error in Exercise 4 - gradient_check_n

There is a mistake in the backward propagation! difference = 1.0

AssertionError Traceback (most recent call last)
in
6 expected_values = [0.2850931567761623, 1.1890913024229996e-07]
7 assert not(type(difference) == np.ndarray), “You are not using np.linalg.norm for numerator or denominator”
----> 8 assert np.any(np.isclose(difference, expected_values)), “Wrong value. It is not one of the expected values”

AssertionError: Wrong value. It is not one of the expected values

2

One thing to check is that you only add and subtract \epsilon from one element at a time, not from the entire vector at once in every iteration.

3

Hi @Trupti, please be mindful about posting your queries in the right category. You are posting your query in the General Discussions category. This category is not monitored by our mentors. Your specific query belongs to DLS Course 2.

If you are unclear about how to use Discourse, we have made this guide for our learners. Hopefully reading it will help you out in posting in the appropriate categories next time.

For now, I have moved your post in the DLS Course 2 category. For future, in order to get swift responses, post in the appropriate categories.

Thank you and happy learning!
Mubsi