Bottleneck Block Param Count

Problem

Count the convolution parameters of a ResNet bottleneck block, excluding bias and batch normalization.

The three convolutions are 1x1 (cin -> mid), 3x3 (mid -> mid) and 1x1 (mid -> cout). Return the total.

case 1

in: [256,64,256]

expected: 69632

case 2

in: [64,64,256]

expected: 57344

case 3

in: [128,32,128]

expected: 17408

Starter codePython

def bottleneck_params(cin, mid, cout):
    # Your code here
    pass

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