Convolution_model_Step_by_Step_v1- Exercise 3 - conv_forward- failing

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I need help on Convolution_model_Step_by_Step_v1- exercise 3. get different results from what I need.

1 Like
2

Please move this topic to the right subcategory. Here’s the community user guide to get started.

Do share stacktrace in the post so that others can get a better context of your problem.

1 Like
3

Hello @Shanit,

I have moved your thread to the Deep Learning Specialization Course 4 Category for you, and please post in the right category next time.

That should be the Course 4 Week 1 Assignment 1. Thanks for letting us know the name of the assignment and which exercise it is about, however, as @balaji.ambresh said, another piece of very important information that we need is the full error traceback or any messages that informed you your work isn’t going right. Please reply here with those (in screenshots if possible) so that our mentors can give you suggestions accordingly.

Cheers,
Raymond

4

Hi,
Thanks!
I didn’t find where to enter my question- so thank you for moving it to the right place.
I added prints to try to where is the problem.
my code in the exercise is:

{ code removed by mentor }

and the error i get is:

pad stride 1 2
Z's mean =
 0.7983469937288112
Z[0,2,1] =
 [13.38666798  6.35203576  5.42200442  9.52027675  3.93951271  0.46764903
  6.88600633  0.7666644 ]
cache_conv[0][1][2][3] =
 [-1.1191154   1.9560789  -0.3264995  -1.34267579]
First Test: Z's mean is incorrect. Expected: 0.5511276474566768 
Your output: 0.7983469937288112 

First Test: Z[0,2,1] is incorrect. Expected: [-2.17796037, 8.07171329, -0.5772704, 3.36286738, 4.48113645, -2.89198428, 10.99288867, 3.03171932] 
Your output: [13.38666798  6.35203576  5.42200442  9.52027675  3.93951271  0.46764903
  6.88600633  0.7666644 ] 

 pad stride 3 1
5

Hello @Shanit,

Please check whether the parameter stride has properly affected the slicing of a_prev_pad in both vertical and horizontal directions, because it should. With stride > 1, you need to skip some index at slicing.

Cheers,
Raymond