Merge #950

950: added GlobalMaxPool, GlobalMeanPool, and flatten layers r=CarloLucibello a=gartangh



Co-authored-by: Garben Tanghe <garben.tanghe@gmail.com>

docs/src/models/layers.md

@@ -14,10 +14,13 @@ These layers are used to build convolutional neural networks (CNNs).
 ```@docs
 Conv
 MaxPool
+GlobalMaxPool
 MeanPool
+GlobalMeanPool
 DepthwiseConv
 ConvTranspose
 CrossCor
+flatten
 ```
 
 ## Recurrent Layers

src/Flux.jl

@@ -10,7 +10,8 @@ using Zygote: Params, @adjoint, gradient, pullback, @nograd
 
 export gradient
 
-export Chain, Dense, Maxout, RNN, LSTM, GRU, Conv, CrossCor, ConvTranspose, MaxPool, MeanPool,
+export Chain, Dense, Maxout, RNN, LSTM, GRU, Conv, CrossCor, ConvTranspose,
+       GlobalMaxPool, GlobalMeanPool, MaxPool, MeanPool, flatten,
        DepthwiseConv, Dropout, AlphaDropout, LayerNorm, BatchNorm, InstanceNorm, GroupNorm,
        SkipConnection, params, fmap, cpu, gpu, f32, f64, testmode!, trainmode!
 

src/layers/conv.jl

@@ -95,8 +95,9 @@ outdims(l::Conv, isize) =
 Standard convolutional transpose layer. `size` should be a tuple like `(2, 2)`.
 `in` and `out` specify the number of input and output channels respectively.
 
-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.
+Data should be stored in WHCN order (width, height, # channels, # batches).
+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.
 
 Takes the keyword arguments `pad`, `stride` and `dilation`.
 """
@@ -171,8 +172,9 @@ Depthwise convolutional layer. `size` should be a tuple like `(2, 2)`.
 `in` and `out` specify the number of input and output channels respectively.
 Note that `out` must be an integer multiple of `in`.
 
-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.
+Data should be stored in WHCN order (width, height, # channels, # batches).
+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.
 
 Takes the keyword arguments `pad`, `stride` and `dilation`.
 """
@@ -304,6 +306,56 @@ end
 outdims(l::CrossCor, isize) =
   output_size(DenseConvDims(_paddims(isize, size(l.weight)), size(l.weight); stride = l.stride, padding = l.pad, dilation = l.dilation))
 
+"""
+    GlobalMaxPool()
+
+Global max pooling layer.
+
+Transforms (w,h,c,b)-shaped input into (1,1,c,b)-shaped output,
+by performing max pooling on the complete (w,h)-shaped feature maps.
+"""
+struct GlobalMaxPool end
+
+function (g::GlobalMaxPool)(x)
+  # Input size
+  x_size = size(x)
+  # Kernel size
+  k = x_size[1:end-2]
+  # Pooling dimensions
+  pdims = PoolDims(x, k)
+
+  return maxpool(x, pdims)
+end
+
+function Base.show(io::IO, g::GlobalMaxPool)
+  print(io, "GlobalMaxPool()")
+end
+
+"""
+    GlobalMeanPool()
+
+Global mean pooling layer.
+
+Transforms (w,h,c,b)-shaped input into (1,1,c,b)-shaped output,
+by performing mean pooling on the complete (w,h)-shaped feature maps.
+"""
+struct GlobalMeanPool end
+
+function (g::GlobalMeanPool)(x)
+  # Input size
+  x_size = size(x)
+  # Kernel size
+  k = x_size[1:end-2]
+  # Pooling dimensions
+  pdims = PoolDims(x, k)
+
+  return meanpool(x, pdims)
+end
+
+function Base.show(io::IO, g::GlobalMeanPool)
+  print(io, "GlobalMeanPool()")
+end
+
 """
     MaxPool(k)
 

src/layers/stateless.jl

@@ -200,3 +200,13 @@ Returns `1 - sum(|y .* ŷ| + 1) / (sum(y .* ŷ + β*(1 .- y) .* ŷ + (1 - β)
 [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://arxiv.org/pdf/1706.05721.pdf)
 """
 tversky_loss(ŷ, y; β=eltype(ŷ)(0.7)) = 1 - (sum(y .* ŷ) + 1) / (sum(y .* ŷ + β*(1 .- y) .* ŷ + (1 - β)*y .* (1 .- ŷ)) + 1)
+
+"""
+    flatten(x::AbstractArray)
+
+Transforms (w,h,c,b)-shaped input into (w x h x c,b)-shaped output,
+by linearizing all values for each element in the batch.
+"""
+function flatten(x::AbstractArray)
+  return reshape(x, :, size(x)[end])
+end

test/layers/conv.jl

@@ -4,6 +4,10 @@ using Flux: gradient
 
 @testset "Pooling" begin
   x = randn(Float32, 10, 10, 3, 2)
+  gmp = GlobalMaxPool()
+  @test size(gmp(x)) == (1, 1, 3, 2)
+  gmp = GlobalMeanPool()
+  @test size(gmp(x)) == (1, 1, 3, 2)
   mp = MaxPool((2, 2))
   @test mp(x) == maxpool(x, PoolDims(x, 2))
   mp = MeanPool((2, 2))

test/layers/stateless.jl

@@ -1,6 +1,6 @@
 using Test
 using Flux: onehotbatch, mse, crossentropy, logitcrossentropy,
-            σ, binarycrossentropy, logitbinarycrossentropy
+            σ, binarycrossentropy, logitbinarycrossentropy, flatten
 
 const ϵ = 1e-7
 
@@ -116,3 +116,10 @@ const ϵ = 1e-7
     end
   end
 end
+
+@testset "helpers" begin
+  @testset "flatten" begin
+    x = randn(Float32, 10, 10, 3, 2)
+    @test size(flatten(x)) == (300, 2)
+  end
+end