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

cleaner API

Browse Source
This commit is contained in:
Dhairya Gandhi 2019-11-27 19:40:58 +05:30
parent eb41715d26
commit 245563077b
1 changed files with 29 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
src/layers/conv.jl
View File

@ -22,8 +22,7 @@ In other words, a 100×100 RGB image would be a `100×100×3×1` array,
and a batch of 50 would be a `100×100×3×50` array.
Accepts keyword arguments `weight` and `bias` to set the corresponding fields.
Setting `bias` to `Flux.Zeros()` will switch bias off for the
layer.
Setting `bias` to `Flux.Zeros()` will switch bias off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
@ -44,17 +43,15 @@ Constructs the convolutional layer with user defined weight and bias arrays.
All other behaviours of the Conv layer apply with regard to data order and
forward pass.
Setting `bias` to `nothing` or `Flux.Zeros()` would switch `bias` off for the
layer.
Setting `bias` to `Flux.Zeros()` would switch `bias` off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
function Conv(w::AbstractArray{T,N}, b::Union{Nothing, Zeros, AbstractVector{T}}, σ = identity;
function Conv(w::AbstractArray{T,N}, b::Union{Zeros, AbstractVector{T}}, σ = identity;
stride = 1, pad = 0, dilation = 1) where {T,N}
stride = expand(Val(N-2), stride)
pad = expand(Val(2*(N-2)), pad)
dilation = expand(Val(N-2), dilation)
b = b isa Nothing ? Zeros((size(w, ndims(w)), )) : b
return Conv(σ, w, b, stride, pad, dilation)
end
@ -114,8 +111,7 @@ Data should be stored in WHCN order. In other words, a 100×100 RGB image would
be a `100×100×3` array, and a batch of 50 would be a `100×100×3×50` array.
Accepts keyword arguments `weight` and `bias` to set the corresponding fields.
Setting `bias` to `Flux.Zeros()` will switch bias off for the
layer.
Setting `bias` to `Flux.Zeros()` will switch bias off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
@ -136,17 +132,15 @@ Constructs the convolutional transpose layer with user defined weight and bias a
All other behaviours of the ConvTranspose layer apply with regard to data order and
forward pass.
Setting `bias` to `nothing` or `Flux.Zeros()` would switch `bias` off for the
layer.
Setting `bias` to `Flux.Zeros()` would switch `bias` off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
function ConvTranspose(w::AbstractArray{T,N}, b::Union{Nothing, Zeros, AbstractVector{T}}, σ = identity;
function ConvTranspose(w::AbstractArray{T,N}, b::Union{Zeros, AbstractVector{T}}, σ = identity;
stride = 1, pad = 0, dilation = 1) where {T,N}
stride = expand(Val(N-2), stride)
pad = expand(Val(2*(N-2)), pad)
dilation = expand(Val(N-2), dilation)
b = b isa Nothing ? Zeros((size(w, ndims(w)), )) : b
return ConvTranspose(σ, w, b, stride, pad, dilation)
end
@ -206,8 +200,7 @@ Data should be stored in WHCN order. In other words, a 100×100 RGB image would
be a `100×100×3` array, and a batch of 50 would be a `100×100×3×50` array.
Accepts keyword arguments `weight` and `bias` to set the corresponding fields.
Setting `bias` to `Flux.Zeros()` will switch bias off for the
layer.
Setting `bias` to `Flux.Zeros()` will switch bias off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
@ -228,17 +221,15 @@ Constructs the `DepthwiseConv` layer with user defined weight and bias arrays.
All other behaviours of the `DepthwiseConv` layer apply with regard to data order and
forward pass.
Setting `bias` to `nothing` or `Flux.Zeros()` would switch `bias` off for the
layer.
Setting `bias` to `Flux.Zeros()` would switch `bias` off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
function DepthwiseConv(w::AbstractArray{T,N}, b::Union{Nothing, Zeros, AbstractVector{T}}, σ = identity;
function DepthwiseConv(w::AbstractArray{T,N}, b::Union{Zeros, AbstractVector{T}}, σ = identity;
stride = 1, pad = 0, dilation = 1) where {T,N}
stride = expand(Val(N-2), stride)
pad = expand(Val(2*(N-2)), pad)
dilation = expand(Val(N-2), dilation)
b = b isa Nothing ? Zeros((size(w, ndims(w)), )) : b
return DepthwiseConv(σ, w, b, stride, pad, dilation)
end
@ -312,8 +303,7 @@ In other words, a 100×100 RGB image would be a `100×100×3×1` array,
and a batch of 50 would be a `100×100×3×50` array.
Accepts keyword arguments `weight` and `bias` to set the corresponding fields.
Setting `bias` to `Flux.Zeros()` will switch bias off for the
layer.
Setting `bias` to `Flux.Zeros()` will switch bias off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
@ -334,17 +324,15 @@ Constructs the standard cross convolutional layer with user defined weight and b
arrays. All other behaviours of the CrossCor layer apply with regard to data order and
forward pass.
Setting `bias` to `nothing` or `Flux.Zeros()` would switch `bias` off for the
layer.
Setting `bias` to `Flux.Zeros()` would switch `bias` off for the layer.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""
function CrossCor(w::AbstractArray{T,N}, b::Union{Nothing, Zeros, AbstractVector{T}}, σ = identity;
function CrossCor(w::AbstractArray{T,N}, b::Union{Zeros, AbstractVector{T}}, σ = identity;
stride = 1, pad = 0, dilation = 1) where {T,N}
stride = expand(Val(N-2), stride)
pad = expand(Val(2*(N-2)), pad)
dilation = expand(Val(N-2), dilation)
b = b isa Nothing ? Zeros((size(w, ndims(w)), )) : b
return CrossCor(σ, w, b, stride, pad, dilation)
end