rcurtin_irc changed the topic of #mlpack to: mlpack: a scalable machine learning library (https://www.mlpack.org/) -- channel logs: https://libera.irclog.whitequark.org/mlpack -- NOTE: messages sent here might not be seen by bridged users on matrix, gitter, or slack
_whitelogger has joined #mlpack
<ShubhamAgrawal[m> rcurtin: In max pooling layer, why is there a variable named offset
<ShubhamAgrawal[m> What is its functionality?
<rcurtin[m]> Shubham Agrawal: it's possible the documentation for that member could be improved. take a look at `ComputeOutputDimensions()`, which sets its value based on the `floor` member. then, `offset` is used in the actual pooling to specify the bounds of the operation
<rcurtin[m]> in general, I believe the problem that we are trying to solve with `floor` and `offset` is, what if I have a 9x9 input image but the pooling size is 2x2---what do we do with the last row and column?
<ShubhamAgrawal[m> rcurtin[m]: I think that is governed by floor param
<ShubhamAgrawal[m> Idts offset is needed as I looked it in max pooling one forward operation
<ShubhamAgrawal[m> I think it is wrong.
<ShubhamAgrawal[m> For example take 1x1 kernel with stride 1 and floor to false
<ShubhamAgrawal[m> > <@shubhamag:matrix.org> I think that is governed by floor param... (full message at https://libera.ems.host/_matrix/media/r0/download/libera.chat/9e6e57cad789ba6fcd47acf639141bddbcd6a0f0)
<rcurtin[m]> you may be right, I am not sure---I did not write the original max pooling operation, I only adapted it in the ann-vtable branch; if you have a correct implementation, definitely we should merge a fix
<ShubhamAgrawal[m> I will see this tmrw
<ShubhamAgrawal[m> As I will try a fix with mean pooling layer first
<rcurtin[m]> 👍️ thanks! it may be good to implement some test cases that break the current implementation, and work from there 😄