You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I think the im2col (and maybe col2im) can potentially read uninitialized memory: Running Grenade.Layers.Internal.Convolution.im2col 10 10 2 2 $ (5><6) [0..] gives a bunch of small float values, which seem likely to be because of reading invalid memory locations.
The text was updated successfully, but these errors were encountered:
im2col isn't a total function, it only works where the kernel and stride "fit" for the input the matrix. So yes, it does look like that's what's happening.
This "fitting" constraint is captured in the proofs going into the convolution and deconvolution layers. I found that if I tried to push these through to the im2col function it lead to a considerable slowdown, so put them in an internal function set instead.
It could probably be better documented, and maybe even just stop with error inside im2col if these constraints are violated.
I think the
im2col
(and maybecol2im
) can potentially read uninitialized memory: RunningGrenade.Layers.Internal.Convolution.im2col 10 10 2 2 $ (5><6) [0..]
gives a bunch of small float values, which seem likely to be because of reading invalid memory locations.The text was updated successfully, but these errors were encountered: