Stack in the first programming exercise of course 4, week 1,graded function : 'conv_forward()'

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hello everyone,
I’m a little bit stack in the first programming exercise of course 4, week 1, graded function : ‘conv_forward()’. In fact the test keep telling me that the value I’m getting is incorrect (Z’s mean = 0.5511276474566768 instead of : 0.5329033220060434), I checked my code many times, I even rewrite the code from the beginning, but I can’t find the problem,
Can someone help me please.

2

Try searching the forum for posts that contain “conv_forward”. You’ll find lots of material to study.

1 Like
3

This is the error :

Z’s mean =
0.5329033220060434
Z[0,2,1] =
[-0.05723279 0.03991888 -6.24285862 0.53960581 -5.04059676 6.96991358
3.69509379 -0.20955895]
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: 0.5329033220060434

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: [-0.05723279 0.03991888 -6.24285862 0.53960581 -5.04059676 6.96991358
3.69509379 -0.20955895]

4

I went through the fourm posts, but I can’t find helpful things, can I put my code here if you can make a look and help me. Cause I m stack in this for days.

5

Did you read this thread?

6

Those wrong values are exactly what you get if you omit the stride in the computation of the vert_start and horiz_start values. In the first test case, the stride is 2. The way this works is that the loops are over the output space and we must touch every point in the output space. The striding operation happens in the input space: you use the stride to compute the starting point on each iteration.

I made that mistake on purpose and here are my outputs, which match yours exactly:

stride 2 pad 1
New dimensions = 3 by 4
Shape Z = (2, 3, 4, 8)
Shape A_prev_pad = (2, 7, 9, 4)
Z[0,0,0,0] = -2.651123629553914
Z[1,2,3,7] = -3.52289092000083
Z's mean =
 0.5329033220060434
Z[0,2,1] =
 [-0.05723279  0.03991888 -6.24285862  0.53960581 -5.04059676  6.96991358
  3.69509379 -0.20955895]
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: 0.5329033220060434 

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: [-0.05723279  0.03991888 -6.24285862  0.53960581 -5.04059676  6.96991358
  3.69509379 -0.20955895]
7

Thank you for your message that helped me.

8

Thank you for your help that solved my problem.