Def L_model_backward issue

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

When creating a post, please add:

My code is below for this function:

{moderator edit - solution code removed}

The result is that I pass 2/3 tests. The output is:
t_AL, t_Y_assess, t_caches = L_model_backward_test_case()
grads = L_model_backward(t_AL, t_Y_assess, t_caches)

print("dA0 = " + str(grads[‘dA0’]))
print("dA1 = " + str(grads[‘dA1’]))
print("dW1 = " + str(grads[‘dW1’]))
print("dW2 = " + str(grads[‘dW2’]))
print("db1 = " + str(grads[‘db1’]))
print("db2 = " + str(grads[‘db2’]))

L_model_backward_test(L_model_backward)
dA0 = [[ 0.09649747 -1.8634927 ]
[-0.2773882 -0.35475898]
[-0.08274148 -0.62700068]
[-0.04381817 -0.47721803]]
dA1 = [[ 1.97611078 -1.24412333]
[-0.62641691 -0.80376609]
[-2.41908317 -0.92379202]]
dW1 = [[-1.31386475 0.88462238 0.88131804 1.70957306]
[ 0.05003364 -0.40467741 -0.54535995 -1.54647732]
[ 0.98236743 -1.10106763 -1.18504653 -0.2056499 ]]
dW2 = [[-1.02387576 1.12397796 -0.13191423]]
db1 = [[ 1.48614836]
[ 0.23671627]
[-1.02378514]]
db2 = [[-1.62328545]]
Error: Wrong output for variable dA1.
Error: Wrong output for variable dW2.
Error: Wrong output for variable db2.
Error: Wrong output for variable dA0.
Error: Wrong output for variable dW1.
Error: Wrong output for variable db1.
2 Tests passed
1 Tests failed

AssertionError Traceback (most recent call last)
in
9 print("db2 = " + str(grads[‘db2’]))
10
—> 11 L_model_backward_test(L_model_backward)

~/work/release/W4A1/public_tests.py in L_model_backward_test(target)
533 ]
534
→ 535 multiple_test(test_cases, target)
536
537

~/work/release/W4A1/test_utils.py in multiple_test(test_cases, target)
140 print(‘\033[92m’, success," Tests passed")
141 print(‘\033[91m’, len(test_cases) - success, " Tests failed")
→ 142 raise AssertionError(“Not all tests were passed for {}. Check your equations and avoid using global variables inside the function.”.format(target.name))
143

AssertionError: Not all tests were passed for L_model_backward. Check your equations and avoid using global variables inside the function.

Expected output:

dA0 = [[ 0. 0.52257901]
[ 0. -0.3269206 ]
[ 0. -0.32070404]
[ 0. -0.74079187]]
dA1 = [[ 0.12913162 -0.44014127]
[-0.14175655 0.48317296]
[ 0.01663708 -0.05670698]]
dW1 = [[0.41010002 0.07807203 0.13798444 0.10502167]
[0. 0. 0. 0. ]
[0.05283652 0.01005865 0.01777766 0.0135308 ]]
dW2 = [[-0.39202432 -0.13325855 -0.04601089]]
db1 = [[-0.22007063]
[ 0. ]
[-0.02835349]]
db2 = [[0.15187861]]

Please assist.
Thank you,
Ken

2

Notice that you don’t call linear_activation_backward any place in your code. Why did we write those other functions if we don’t call them?

3

Thank you Paul! I’ve got it now! i gotten a bit confused. Yes the functions must certainly be used (all the backward stuff), my bad. I saw that I had calculated the dAL and did nothing with it. Have a happy holiday!

1 Like
4

It’s great that my hint was enough to get you there. Yes, the structure is exactly analogous to the “forward” case: we build a layered structure of support functions to do the various lower level operations that are required and then build the “wrapper” routine that manages the overall process of stepping through the layers and calling the lower level functions. It’s just in the “backprop” case, we’re going … wait for it … backward, instead of forward through the layers. :laughing:

5

Paul,

You help is always greatly appreciated backwards or forwards!

Best,
Ken

1 Like