Improving Neural Networks : week2 : assignment :optimization methods

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
1

formulas for this cell:

image
image851×372 28 KB

I have written the same exact code for the formulas, but still i am getting different answers, is there anything wrong in my code?or wrong in the assertion? Please help

{Moderator Edit: Solution Code Removed}

my output:

W1 = 
[[ 1.63942888 -0.61624001 -0.54303153]
 [-1.05781906  0.85024927 -2.31663159]]
W2 = 
[[ 0.33400701 -0.23919264]
 [ 1.47721313 -2.04655625]
 [-0.33719642 -0.36907981]]
b1 = 
[[ 1.73008524]
 [-0.77629952]]
b2 = 
[[ 1.14819595]
 [-1.08492045]
 [-0.15735887]]

output error:

AssertionError                            Traceback (most recent call last)
<ipython-input-49-99ca62433443> in <module>
      7 print(f"b2 = \n{parameters['b2']}")
      8 
----> 9 update_parameters_with_adam_test(update_parameters_with_adam)

~/work/release/W2A1/public_tests.py in update_parameters_with_adam_test(target)
    280         assert type(parameters[key]) == np.ndarray, f"Wrong type for parameters['{key}']. Expected np.ndarray"
    281         assert parameters[key].shape == parametersi[key].shape, f"Wrong shape for  parameters['{key}']. The update must keep the dimensions of parameters inputs"
--> 282         assert np.allclose(parameters[key][0], expected_parameters[key]), f"Wrong values. Check you formulas for parameters['{key}']"
    283         #print(f"{key}: \n {str(parameters[key])}")
    284 

AssertionError: Wrong values. Check you formulas for parameters['W1']

expected values:

Expected values:

W1 = 
[[ 1.63937725 -0.62327448 -0.54308727]
 [-1.0578897   0.85032154 -2.31657668]]
W2 = 
[[ 0.33400549 -0.23563857]
 [ 1.47715417 -2.04561842]
 [-0.33729882 -0.36908457]]
b1 = 
[[ 1.72995096]
 [-0.7762447 ]]
b2 = 
[[ 1.14852557]
 [-1.08492339]
 [-0.15740527]]
2

Epsilon is not in the square root.
Please note that posting your code is not allowed.

3

thankyou, i noticed it before, i tried before it didnt work, but now it has worked, how to delete the post?

4

I am glad it worked. No need to delete the post as future learners may visit it.