C4 W2 A1: Help! grader problem

i have finished assignment 1 of week 2 course 4 residual network, all test passed but when i submit i get 66/100 score how could that be? how to solve this problem.

training=False

[[[ 0. 0. 0. 0. ]
[ 0. 0. 0. 0. ]]

[[192.71234 192.71234 192.71234 96.85617]
[ 96.85617 96.85617 96.85617 48.92808]]

[[578.1371 578.1371 578.1371 290.5685 ]
[290.5685 290.5685 290.5685 146.78426]]]
96.85617

With training=True

[[[0. 0. 0. 0. ]
[0. 0. 0. 0. ]]

[[0.40739 0.40739 0.40739 0.40739]
[0.40739 0.40739 0.40739 0.40739]]

[[4.99991 4.99991 4.99991 3.25948]
[3.25948 3.25948 3.25948 2.40739]]]
All tests passed!
Expected value

With training=False

[[[ 0. 0. 0. 0. ]
[ 0. 0. 0. 0. ]]

[[192.71234 192.71234 192.71234 96.85617]
[ 96.85617 96.85617 96.85617 48.92808]]

[[578.1371 578.1371 578.1371 290.5685 ]
[290.5685 290.5685 290.5685 146.78426]]]
96.85617

With training=True

[[[0. 0. 0. 0. ]
[0. 0. 0. 0. ]]

[[0.40739 0.40739 0.40739 0.40739]
[0.40739 0.40739 0.40739 0.40739]]

[[4.99991 4.99991 4.99991 3.25948]
[3.25948 3.25948 3.25948 2.40739]]]
Code Cell UNQ_C1: Function ‘identity_block’ is incorrect. Check implementation.
Code Cell UNQ_C2: Function ‘convolutional_block’ is correct.
Code Cell UNQ_C3: Function ‘ResNet50’ is correct.
If you see many functions being marked as incorrect, try to trace back your steps & identify if there is an incorrect function that is being used in other steps.
This dependency may be the cause of the errors.

Sorry that this question did not get answered when you originally asked it. Your results for the identity_block do look correct. The only thing I can guess is that perhaps you “hard-coded” something, e.g. used 2 explicitly for the f value.

Did you find a solution to this or did you just move on?