Ppol_forward Test Cases failed

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I don’t get why the two cases are failing

------OUTPUT-------
mode = max
A.shape = (2, 3, 3, 3)
A[1, 1] =
[[ 0.44497696 -0.00261695 -0.31040307]
[ 0.50811474 -0.23493734 -0.23961183]
[ 0.11872677 0.17255229 -0.22112197]]

mode = average
A.shape = (2, 3, 3, 3)
A[1, 1] =
[[0. 0. 0.]
[0. 0. 0.]
[0. 0. 0.]]
Error: Wrong output in MAX-Pool for variable in position 0.
Error: Wrong output in AVG-Pool for variable in position 0.
4 Tests passed
2 Tests failed

2

Which week?
Which assignment?

3

Week 1.
Programming Assignment: Convolutional Model, Step by Step

4

Your pool_forward() function is returning the wrong values for ‘A’.
For the “max” calculation, the values are wrong. So I suspect a_prev_slice values are wrong.
For the “average” calculation, the values should not be all-zeros. So there’s a big problem there.

Tip:
When you compute vert_start and horz_start, it is important that it includes multiplying by “stride”.