Global Max Pool

Problem

Compute global max pooling over an H x W x C feature map.

Return the maximum activation of each channel as a list of C values.

Hint

Reduce each channel independently with a maximum.

case 1

in: [[[[1,2],[3,4]],[[5,6],[7,8]]]]

expected: [7,8]

case 2

in: [[[[10,0,5]]]]

expected: [10,0,5]

case 3

in: [[[[2,4],[6,8]],[[1,1],[1,1]]]]

expected: [6,8]

Starter codePython

def global_max_pool(feature):
    # Your code here
    pass

3 test cases · run your code against them in the editor