Hi,
Do you have any specific question regarding Deconvolution? Could you be a 
little more specific, please? 

Ramana

On Wednesday, December 28, 2016 at 8:40:37 PM UTC+1, Feras Almasri wrote:
>
> I'm applying conv2d_grad_wrt_inputs into one feature maps (the second 
> image below) using its kernel. would interpret the third image below as a 
> correct deconvolution since I'm seeing it as repetition of the some feature 
> maps into the input. 
>
>
>
> <https://lh3.googleusercontent.com/-6c7HTwi--Lo/WGQR-YDndlI/AAAAAAAAA2U/V00_f_flHB0HNVtY1xpmnBCRZSS6ZTl8ACKgB/s1600/deconv_5.png>
>
>

-- 

--- 
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 an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to