How tensorflow handle 'SAME' padding in transpose convolutiona (Deconvolutional) layer

by Desmanda   Last Updated October 04, 2018 12:19 PM - source

I would like to know how 'SAME' padding is calculated when using a transpose convolutional layer in Tensorflow. I find the way it is calculated in a convolutional layer with this formula in this link, but I wonder how it is done in the deconvolutional layer. Thanks!

Related Questions

Convolution transpose 1D in tensorflow?

Updated June 06, 2017 13:19 PM

Apply convolutional network to images of any size?

Updated September 24, 2017 17:19 PM