[Week 3, Problem 4.7]

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

When creating a post, please add:

  • Week # must be added in the tags option of the post.
  • Link to the classroom item you are referring to:
  • Description (include relevant info but please do not post solution code or your entire notebook)
    Week 3, 4.7: Integration, Excercise 8: nn_model
    Program Assignment: Planar data classification with one hidden layer
    After completing the first six exercises with “All tests passed”, I ran Exercise 8: nn_model.
    However, I got an error regarding the multiplication of matrices within the function “forward_propagation.”
    The error says: ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 2 is different from 6)
    I tested the multiplication in a new cell and it works. However, the function does not work.
2

Could you please share the full error?

3

Since all your previous tests pass, the bug is probably not in forward_propagation. It is that you are passing mismatching parameters when you call it from nn_model. So how could that happen? Look at the arguments you are passing. Are you sure you are sending the output of layer 1 as the input to layer 2, for example? One common error is to use X again as the input at layer 2, instead of A1. Also check that you are not referencing global variables instead of the parameters of the function.

4

Thank you for your prompt response and valuable insights.
The problem was with the size of the input layer (n_x). I was getting the right numerical answer but did not correspond to the right procedural solution.
I have fixed it now.
Regards.