[image from http://cvml.ajou.ac.kr/wiki/images/8/83/0_Transposed_convolution.pdf]
Is it the one you are finding?
If it’s the case, we can simulate it simply by using usual convolution with zero padding to its input.
When we denote input as X, kernel as W (with shape 3 X 3), the convolution of X and W as Z,
X[i][j] contribute Z[i][j] with weight W[1][1], Z[i-1][j-1] with weight W[0][0], …, etc.
1 Like