Reverse Convolution? about mlpack HOT 6 CLOSED

Hey, If no one is having a look at it I will look into its adaptation in a day or 2

from mlpack.

Yes , currently the unadapted layers require some changes to work with the current mlpack models. You can check out the adaptation of layers pull requests like #3445 to get an idea of what should be done to adapt these layers

from mlpack.

That sums it up, thank you.

from mlpack.

Hey @IgorWojas it seems that the Reparametrization and TransposedConvolution layers have not yet been adapted to the mlpack 4 layer style(It is present in the non adapted directory).

from mlpack.

@IWNMWE Thanks for your reply. So this means its unusable in vanilla mlpack?

from mlpack.

I don't think it would be hard to adapt TransposedConvolution; since the class is so related to Convolution, I think the changes in #2777 for the Convolution class could be pretty much taken as-is. There might be some minor input/output size issues to handle, but overall it should be straightforward. I would do it if I had the time, but at the moment I don't (sorry about that).

from mlpack.