TastyPancakes/Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix for reading comprehension error (dim is not always 2 * (N-2)) Fix for ambiguous method sig

Browse Source
This commit is contained in:
DrChainsaw 2019-10-20 15:15:30 +02:00
parent 411ce5dbd8
commit 530d4edb67
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/layers/conv.jl
View File

@ -12,8 +12,8 @@ For stride > 1 the output shape depends on the type of convolution layer.
"""
struct SamePad end
calc_padding(pad, k::NTuple{N,T}, dilation, stride) where {T,N}= expand(Val(2*(N-2)), pad)
function calc_padding(::SamePad, k, dilation, stride)
calc_padding(pad, k::NTuple{N,T}, dilation, stride) where {T,N}= expand(Val(2*N), pad)
function calc_padding(::SamePad, k::NTuple{N,T}, dilation, stride) where {N,T}
#Formula from Relationship 14 in http://deeplearning.net/software/theano_versions/dev/tutorial/conv_arithmetic.html
# Effective kernel size, including dilation