When using transposedConv2dLayer, how do you calculate the size of the output given an input?

5 次查看(过去 30 天)
Let's say you have an array of size [a b c] as input to a transposedConv2dLayer. What would be the output based on the stride, crop, and filter-size numbers?

采纳的回答

Matt J
Matt J 2023-1-12
编辑:Matt J 2023-1-13
I believe it would be
newsize = [stride.*[a-1,b-1] + filtersize - 2*crop, numFilters]
  4 个评论
Onur Kilic
Onur Kilic 2023-1-13
Thanks. Also, it seems the following edited formula gives the correct sizes for the linked example:
newsize = [stride.*[a-1,b-1] + filtersize - 2*crop, numFilters]
If you agree with this formula, can you edit your first answer so that I can accept it? Could be useful for others.

请先登录,再进行评论。

更多回答(0 个)

类别

Help CenterFile Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2022a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by