Here is [a post on this site][1] asking "What are deconvolutional layers?" which is the same thing. Here are two quotes from [a post by Paul-Louis Pröve][2] on different types of convolutions: > Transposed Convolutions (a.k.a. deconvolutions or fractionally strided > convolutions) and > Some sources use the name deconvolution, which is inappropriate > because it’s not a deconvolution [..] An actual deconvolution reverts the process of a convolution. And here is an animation of fractionally-strided convolution (from this [github project][3]): <img src="https://i.sstatic.net/2aSir.gif" width="300" /> where the dashed white cells are **zero** rows/columns padded between the input cells (blue). These animations are visualizations of the mathematical formulas from the article below: [A guide to convolution arithmetic for deep learning][4] Here is a quote from the article: > Figure [..] helps understand what **fractional** strides involve: zeros > are inserted between input units, which makes the kernel move around > at a **slower** pace than with **unit** strides [footnote: doing so is > inefficient and real-world implementations avoid useless > multiplications by zero, but conceptually it is how the transpose of a > strided convolution can be thought of.] [1]: https://datascience.stackexchange.com/q/6107/67328 [2]: https://towardsdatascience.com/types-of-convolutions-in-deep-learning-717013397f4d [3]: https://github.com/vdumoulin/conv_arithmetic [4]: https://arxiv.org/pdf/1603.07285.pdf