C4 Week 1 pool_forward

[Nick]

I’m trying to complete the pool_forward function but I keep getting an error for an array size along with my answers being incorrect. I’m a bit confused with it so if someone could take a look I’d appreciate it:
mode = max
A.shape = (2, 3, 3, 3)
A[1, 1] =
[[ 0.16938243 0.74055645 -0.9537006 ]
[ 0.31515939 0.84616065 -0.85951594]
[-1.61577235 1.12141771 0.40890054]]

mode = average
A.shape = (2, 3, 3, 3)
A[1, 1] =
 [[ 0.16938243  0.74055645 -0.9537006 ]
 [ 0.31515939  0.84616065 -0.85951594]
 [-1.61577235  1.12141771  0.40890054]]

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-39-dd4190c83221> in <module>
 14 print("A[1, 1] =\n", A[1, 1])
 15 
---> 16 pool_forward_test(pool_forward)

~/work/release/W1A1/public_tests.py in pool_forward_test(target)
125     # Test 1
126     A_prev = np.random.randn(2, 5, 7, 3)
--> 127     A, cache = target(A_prev, {"stride" : 2, "f": 2}, mode = "average")
128     A_shape = A.shape
129     assert A_shape[0] == A_prev.shape[0], f"Test 1 - m is wrong. Current: {A_shape[0]}.  Expected: {A_prev.shape[0]}"

<ipython-input-38-7638be32f6e5> in pool_forward(A_prev, hparameters, mode)
 67                         A[i, h, w, c] = np.max(a_prev_slice[i, h, w, c])
 68                     elif mode == 'average':
---> 69                         A[i, h, w, c] = np.mean(a_prev_slice[i, h, w, c])
 70 
 71     # YOUR CODE ENDS HERE

IndexError: index 2 is out of bounds for axis 2 with size 2

[reinoudbosch]

Hi Nick,

You want the maximum or the average value of the entire slice, so you do not want to index into the slice. Moreover, the slice does not have the same dimensions as the output matrix so you run into an out of bounds error.

[Ayesha6060]

Got assertion error in Pool forward task of Course4 Week 1 programming assignment