How to transform fully connected layer into convolution layer?

2 visualizaciones (últimos 30 días)
QU HAIFENG
QU HAIFENG el 11 de Jun. de 2018
Editada: Matt J el 27 de Abr. de 2022
I want to replace a fully connected layer with a convolution layer, but I don't know how to complete it. I reference help document, and find a function named "transposedConv2dLayer", but I don't believe "cropping" is helpful. So if somebody could give me any suggest, thanks a lot.

Respuestas (1)

Shounak Mitra
Shounak Mitra el 21 de Jun. de 2018
Editada: Matt J el 27 de Abr. de 2022
Hello QU,
Can you please tell me if you're using a Series or DAG network? The steps to replace a layer is different for these 2 network types.
For a Series Network, follow steps here -->
For DAG follow this -->
Also, is the motivation behind replacing the FC layer with a conv2d is to make the network deeper?
  1 comentario
Matt J
Matt J el 27 de Abr. de 2022
Editada: Matt J el 27 de Abr. de 2022
The link for the Series Network does not seem applicable. The fully connected layer in that example is replaced by another fully connected layer, not a conv2d layer. Moreover, the new layer is not equivalent to the old one.

Iniciar sesión para comentar.

Categorías

Más información sobre Image Data Workflows en Help Center y File Exchange.

Community Treasure Hunt

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

Start Hunting!

Translated by