How to add a fully connected layer to the middle of an AutoEncoder model #8384
Unanswered
karllandheer
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Does anyone have an example of adding a fully connected layer to an AutoEncoder, or any MONAI model? There's a block called "Fully connected network", but I don't think that's quite what I want. What I want is to flatten the output from the encoder, add a linear layer if inputted size, and then reshape it to the input shape required by decoder. I'm sure someone has done this before, so any help would be greatly appreciated.
Beta Was this translation helpful? Give feedback.
All reactions