3.3 - Convolutional Neural Networks - exercise Forward Pass C4W1

Hi every one
I could not figure out the problem of my code in exercise 3.3 - Convolutional Neural Networks - Forward Pass in C4W1.
One of the problems related the “range(n_W)” in one of the for loops. It is exceeded the limit of the range. the range supposed to be between “0” and “3” but it is increased to “8” or more.
Could anyone take a look to my code to help me what exactly my mistake?

1 Like

Sorry, but we can’t see your code. It sounds like your problem may be the common one of trying to use the stride in the range of the loops. The striding happens in the “input” space, not the output space, right?

Either that or the dimensions of your Z output are incorrect.

In either case, please take a look at the information on this thread and I hope that it will shed some light on the issues you are having.

1 Like

I also added some print statements to my code for `conv_forward` to show the shapes of everything. Please compare this to what you are seeing:

``````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] = 0.4427056509973153
Z's mean =
0.5511276474566768
Z[0,2,1] =
[-2.17796037  8.07171329 -0.5772704   3.36286738  4.48113645 -2.89198428
10.99288867  3.03171932]
cache_conv[0][1][2][3] =
[-1.1191154   1.9560789  -0.3264995  -1.34267579]
First Test: All tests passed!
stride 1 pad 3
New dimensions = 9 by 11
Shape Z = (2, 9, 11, 8)
Shape A_prev_pad = (2, 11, 13, 4)
Z[0,0,0,0] = 1.4306973717089302
Z[1,8,10,7] = -0.6695027738712113
stride 2 pad 0
New dimensions = 2 by 3
Shape Z = (2, 2, 3, 8)
Shape A_prev_pad = (2, 5, 7, 4)
Z[0,0,0,0] = 8.430161780192094
Z[1,1,2,7] = -0.2674960203423288
stride 1 pad 6
New dimensions = 13 by 15
Shape Z = (2, 13, 15, 8)
Shape A_prev_pad = (2, 17, 19, 4)
Z[0,0,0,0] = 0.5619706599772282
Z[1,12,14,7] = -1.622674822605305
Second Test: All tests passed!
``````
1 Like

Thanks, I’ll check again

The dimintions are correct but may be the problem is in the striding
THanks agian