Transposed Conv Output Size

Problem

Compute the spatial output size of a strided transposed convolution.

out = (n - 1) * stride - 2 * pad + k for each dimension, with no output padding. Given height h, width w, kernel size k, stride and pad, return [out_h, out_w].

Test cases

case 1

in: [7,7,3,2,1]

expected: [13,13]

case 2

in: [4,4,3,1,0]

expected: [6,6]

case 3

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

expected: [12,12]

case 4

in: [5,10,3,2,0]

expected: [11,21]

Starter codePython

def transposed_conv_output_size(h, w, k, stride, pad):
    # Your code here
    pass

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