AssertionError for Dropout Regularization Assignment

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

{moderator edit - solution code removed}

I am am having an error when checking the Dropout portion of the Regularization assignment. I have checked my code and i don’t seem to see anything wrong with it. The first portion of the test which returns A3 computed fine, but the second portion came with an AssertionError.

I have restarted the Kernel and even reverted to the original checkpoint, and yet the error won’t go away.

Please find attached the portion of the code and the error return.

2

Your answers are wrong because your code is incorrect. You’ve made what is probably the most common error here: you are using the random Gaussian distribution to compute the “drop” masks, but that’s not what they asked you to do. Please have a more careful look at the instructions and the comments in the template code there.

1 Like
3

Thank you very much Paul. I didn’t pay attention to the type of np.random specified.