Passed all tests, but got 50/100 grade, failed

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I passed all tests of first assignment of week 1 except the non-graded part, but only got 50/100 grade

I haven’t done non-graded part.

2

Please see this other recent thread.

3

I checked the output again.and compared it with expected output for every single value, I did not see any difference.

mode = max
A.shape = (2, 2, 2, 3)
A[0] =
[[[1.74481176 0.90159072 1.65980218]
[1.74481176 1.6924546 1.65980218]]

[[1.13162939 1.51981682 2.18557541]
[1.13162939 1.6924546 2.18557541]]]

mode = average
A.shape = (2, 2, 2, 3)
A[1] =
[[[-0.17313416 0.32377198 -0.34317572]
[ 0.02030094 0.14141479 -0.01231585]]

[[ 0.42944926 0.08446996 -0.27290905]
[ 0.15077452 0.28911175 0.00123239]]]

Expected Output:

mode = max
A.shape = (2, 2, 2, 3)
A[0] =
[[[1.74481176 0.90159072 1.65980218]
[1.74481176 1.6924546 1.65980218]]

[[1.13162939 1.51981682 2.18557541]
[1.13162939 1.6924546 2.18557541]]]

mode = average
A.shape = (2, 2, 2, 3)
A[1] =
[[[-0.17313416 0.32377198 -0.34317572]
[ 0.02030094 0.14141479 -0.01231585]]

[[ 0.42944926 0.08446996 -0.27290905]
[ 0.15077452 0.28911175 0.00123239]]]

4

You’re right. I agree that your values match. So that’s just the most common error people make. Your problem must be more subtle. One other thing to check is that you did not coerce the return value to be float32 for conv_single_step: that passes the tests in the notebook, but fails the grader. But in that case, I think you end up with 75 points instead of 50, so that may not be it.

5

I checked at conv_single_step, it was float32.

Z = np.sum(s,dtype=np.float32)
Z = Z + np.sum(b,dtype=np.float32)
6

I think that causes a problem, so did you try removing that? Or coercing it to float64?