How to add a 2x2 matrix to a 3x2x2 matrix?

Question

I am trying to implement a very simple pooling function. The input is a 3x4x4 matrix (3 dimensions, 4 rows, 4 columns) and I want my output to be a 3x2x2 matrix

def pooling_layers(image):

    pooling_layer = np.zeros((3, 2, 2))

    for i in range(3):

        a = image[i][:][:]
        result = skimage.measure.block_reduce(a, (2, 2), np.mean)

        # now I have my result, I want to add it to the 2x2 block of `pooling_layer`
        pooling_layer = pooling_layers[i][:][:] + result

    print(pooling_layer)
    return pooling_layer

Above I manage to get the mean 2D array but I want to add it to the correct dimension of my pooling_layers matrix, how do I do this?

Ex. I have input matrix C

array([[[ 37,  41,  46,  50],
        [ 64,  68,  73,  78],
        [ 91,  96, 100, 105],
        [118, 123, 127, 132]],

       [[ 26,  30,  35,  39],
        [ 52,  56,  61,  65],
        [ 78,  83,  87,  91],
        [104, 109, 113, 117]],

       [[ 28,  31,  35,  38],
        [ 47,  50,  54,  57],
        [ 66,  70,  73,  76],
        [ 85,  89,  92,  95]]])

And my output, pooling_layer would be:

array([[[ 52.5, 61.75],
        [ 107., 116. ]],

       [[ 41.,   50. ],
        [ 93.5,  102.]],

       [[ 39. ,  46. ],
        [ 77.5,  84. ]]])

Answer 1

Instead of using a for loop, you can directly use the following line of code to get the result.

skimage.measure.block_reduce(image, (1, 2, 2), np.mean)

On the other hand, if you want to use the for loop approach, you can assign the value directly instead of addition.

def pooling_layers(image):
    pooling_layer = np.zeros((3, 2, 2))
    for i in range(3):
        a = image[i][:][:]
        result = skimage.measure.block_reduce(a, (2, 2), np.mean)
        pooling_layer[i] =  result
    return pooling_layer