Bug in building RegNetX
sefibk opened this issue · comments
Hi,
Thanks for a GREAT repo!
I think there might be a bug in the creation of RegnetX here:
Line 25 in 031b1b5
Why would you multiply the group_width by the bottleneck_ratio?
I will demonstrate through an example:
group_width = 16
block_width = 32
bottleneck_ratio = 2
With these set of parameters I would assume a bottleneck block will be created with 1/2 the channels in the bottleneck and 1 group convolution (i.e. standard convolution)
However: l.25 changes the groups to ls_group_width = ls_group_width.astype(np.int) * bottleneck_ratio => group_width = 32 making this block impossible and having the model FAIL!
Is this intentional or a bug?
Thank you very much