Even sum pooling in a 2D array

Question

I am trying to implement a custom pooling method - aka - even sum pooling (sum of all even numbers in the kernel). I looked into the max-pooling implementation here

EDIT

For example, if my input is

A = np.array([[1, 1, 2, 4],
            [5, 6, 7, 8],
            [3, 2, 1, 0],
            [1, 2, 3, 4]])

My output should be

[[ 6 14]
 [ 4  4]]

Based on the implementation here, I did the below code, with two additional helper functions

import numpy as np from numpy.lib.stride_tricks import as_strided

def even_sum_pooling(matrix):
    n = matrix.shape[0]
    summ = 0
    for i in range(n):
        if matrix[i]% 2 == 0:
            summ +=matrix[i]
    return summ

def total(row):
    summ = 0
    for num in row:
        summ +=num
    return summ


def pool2d(A, kernel_size, stride, padding, pool_mode='max'):
    '''
    2D Pooling

    Parameters:
        A: input 2D array
        kernel_size: int, the size of the window
        stride: int, the stride of the window
        padding: int, implicit zero paddings on both sides of the input
        pool_mode: string, 'max' or 'avg'
    '''
    # Padding
    A = np.pad(A, padding, mode='constant')

    # Window view of A
    output_shape = ((A.shape[0] - kernel_size)//stride + 1,
                    (A.shape[1] - kernel_size)//stride + 1)
    kernel_size = (kernel_size, kernel_size)
    A_w = as_strided(A, shape = output_shape + kernel_size,
                        strides = (stride*A.strides[0],
                                   stride*A.strides[1]) + A.strides)
    A_w = A_w.reshape(-1, *kernel_size)

    # Return the result of pooling
    temp = np.apply_along_axis(even_sum_pooling, 2, A_w)
    return np.apply_along_axis(total,1,temp).reshape(output_shape)

This works but I am interested in how I can change the last two code lines to 1 line.

How do I do that? Please suggest.