C1W4A2-wrong output for variable W1

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

Hey, I am stuck on the second exercise in this assignment. I am getting the output:

Cost after first iteration: 0.6931489045172448
Error: Wrong output for variable W1.
Error: Wrong output for variable b1.
Error: Wrong output for variable W2.
Error: Wrong output for variable b2.
Error: Wrong output for variable W3.
Error: Wrong output for variable b3.
Error: Wrong output for variable 0.
Error: Wrong output for variable W1.
Error: Wrong output for variable b1.
Error: Wrong output for variable W2.
Error: Wrong output for variable b2.
Error: Wrong output for variable W3.
Error: Wrong output for variable b3.
Error: Wrong output for variable 0.
2 Tests passed
2 Tests failed

I have revisited the code multiple times and I can’t find what is going wrong. Two of the three functions that I am adding to the code on this exercise are:

{moderator edit - solution code removed}

2

For assignment 2, you don’t need to define your own functions: L_model_forward, L_model_backward, etc. They did this for you. You just need to call them with the correct arguments.

1 Like
3

Yes, the reason “hand importing” your own functions from the previous exercise gives different answers is that they had to use a more sophisticated initialization function for the L layer case in order to get reasonable convergence. It’s a type of initialization that will be covered in Course 2 of the DLS series. My guess is that they decided not to mention that because there’s just too much to cover in Course 1, since we’re just getting started.

4

Thanks! Now it worked perfectly.

1 Like