Does anyone have any ideas for using Theano for other things besides
machine learning?
Do such projects already exist?
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send
Hi,
Thank you for the suggestion, actually inlining makes more sense for what I
am trying to do.
However, a casting issue arises when trying to compute the derivative wrt
to the continuous input. If I understood correctly, DisconnectedInput
should be returned as the gradient for integral
Hi everyone,
I have been trying out different Fully Convolutional Networks recently, and
is currently working on Segnet. One of the key point is the way upsampling
is performed, namely that you keep the pooling indices from the encoder
part of the network. Fine in theory, but i am struggling