rename channels_in, channels_out add ConvTranspose cuda tests

Author: jw3126

src/layers/conv.jl

@@ -166,12 +166,12 @@ function (c::Conv)(x::AbstractArray)
   σ.(conv(x, c.weight, cdims) .+ b)
 end
 
-channels_in(l ::Conv) = size(l.weight, ndims(l.weight)-1) * l.groups
-channels_out(l::Conv) = size(l.weight, ndims(l.weight))
+_channels_in(l ::Conv) = size(l.weight, ndims(l.weight)-1) * l.groups
+_channels_out(l::Conv) = size(l.weight, ndims(l.weight))
 
 function Base.show(io::IO, l::Conv)
   print(io, "Conv(", size(l.weight)[1:ndims(l.weight)-2])
-  print(io, ", ", channels_in(l), " => ", channels_out(l))
+  print(io, ", ", _channels_in(l), " => ", _channels_out(l))
   _print_conv_opt(io, l)
   print(io, ")")
 end
@@ -228,8 +228,8 @@ struct ConvTranspose{N,M,F,A,V}
   groups::Int
 end
 
-channels_in(l::ConvTranspose)  = size(l.weight)[end]
-channels_out(l::ConvTranspose) = size(l.weight)[end-1]*l.groups
+_channels_in(l::ConvTranspose)  = size(l.weight)[end]
+_channels_out(l::ConvTranspose) = size(l.weight)[end-1]*l.groups
 
 """
     ConvTranspose(weight::AbstractArray, [bias, activation; stride, pad, dilation, groups])
@@ -285,7 +285,7 @@ end
 
 function Base.show(io::IO, l::ConvTranspose)
   print(io, "ConvTranspose(", size(l.weight)[1:ndims(l.weight)-2])
-  print(io, ", ", channels_in(l), " => ", channels_out(l))
+  print(io, ", ", _channels_in(l), " => ", _channels_out(l))
   _print_conv_opt(io, l)
   print(io, ")")
 end

test/cuda/layers.jl

@@ -48,7 +48,7 @@ function gpu_gradtest(name::String, layers::Vector, x_cpu = nothing, args...; te
           xg_cpu = gradient(x -> sum(l_cpu(x)), x_cpu)[1]
           xg_gpu = gradient(x -> sum(l_gpu(x)), x_gpu)[1]
 
-          # test 
+          # test
           if test_cpu
             @test y_gpu ≈ y_cpu rtol=1f-3 atol=1f-3
             if isnothing(xg_cpu)
@@ -80,6 +80,7 @@ ConvTransposeNoBias(args...) = ConvTranspose(args...; bias = false)
 CrossCorNoBias(args...) = CrossCor(args...; bias = false)
 DepthwiseConvNoBias(args...) = DepthwiseConv(args...; bias = false)
 GroupedConv(args...) = Conv(args..., groups = 5)
+GroupedConvTranspose(args...) = ConvTranspose(args..., groups = 5)
 
 for act in ACTIVATIONS
   r = rand(Float32, 28, 28, 1, 1)
@@ -89,16 +90,16 @@ for act in ACTIVATIONS
                  DepthwiseConv, DepthwiseConvNoBias]
   gpu_gradtest("Convolution with $act", conv_layers, r, (2,2), 1=>3, act, test_cpu = false)
 
-  groupedconv = [GroupedConv]
+  groupedconv = [GroupedConv, GroupedConvTranspose]
   gpu_gradtest("GroupedConvolution with $act", groupedconv, rand(Float32, 28, 28, 100, 2), (3,3), 100 => 25, act, test_cpu = true)
 
   batch_norm = [BatchNorm]
   gpu_gradtest("BatchNorm 1 with $act", batch_norm, rand(Float32, 28,28,3,4), 3, act, test_cpu = false) #TODO fix errors
   gpu_gradtest("BatchNorm 2 with $act", batch_norm, rand(Float32, 5,4), 5, act, test_cpu = false)
-  
+
   instancenorm = [InstanceNorm]
   gpu_gradtest("InstanceNorm with $act", instancenorm, r, 1, act, test_cpu = false)
-  
+
   groupnorm = [GroupNorm]
   gpu_gradtest("GroupNorm with $act", groupnorm, rand(Float32, 28,28,3,1), 3, 1, act, test_cpu = false)
 end
@@ -151,7 +152,7 @@ end
   else
     @test sum(l(ip)) ≈ 0.f0
     gs = gradient(() -> sum(l(ip)), Flux.params(l))
-    @test l.bias ∉ gs.params 
+    @test l.bias ∉ gs.params
   end
 end