working model for regression

Author: codeboy5

FastTimeSeries/Project.toml

@@ -4,6 +4,7 @@ authors = ["FluxML Community"]
 version = "0.1.0"
 
 [deps]
+ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
 DataDeps = "124859b0-ceae-595e-8997-d05f6a7a8dfe"
 FastAI = "5d0beca9-ade8-49ae-ad0b-a3cf890e669f"
 FilePathsBase = "48062228-2e41-5def-b9a4-89aafe57970f"

FastTimeSeries/src/FastTimeSeries.jl

@@ -33,6 +33,7 @@ include("blocks/timeseriesrow.jl")
 
 # Encodings
 include("encodings/tspreprocessing.jl")
+include("encodings/continuouspreprocessing.jl")
 
 # Models
 include("models/Models.jl")

FastTimeSeries/src/encodings/continuouspreprocessing.jl

@@ -0,0 +1,15 @@
+struct ContinuousPreprocessing <: Encoding
+    numlabels::Int
+end
+
+ContinuousPreprocessing() = ContinuousPreprocessing(1)
+
+decodedblock(c::ContinuousPreprocessing, block::AbstractArray) = Continuous(c.numlabels)
+
+function encode(::ContinuousPreprocessing, _, block::Continuous, obs)
+    return [obs]
+end
+
+function decode(::ContinuousPreprocessing, _, block::AbstractArray, obs)
+    return obs[1]
+end

FastTimeSeries/src/models.jl

@@ -7,9 +7,9 @@ Construct a model for time-series classification.
 function blockmodel(inblock::TimeSeriesRow,
                 outblock::OneHotTensor{0}, 
                 backbone)
-    #TODO: Use Flux.outputsize here.
-    data   = rand(Float32, inblock.nfeatures, 32, inblock.obslength)
+    data   = zeros(Float32, inblock.nfeatures, 1, 1)
     output = backbone(data)
+    Flux.reset!(backbone)
     return Models.RNNModel(backbone, outsize = length(outblock.classes), recout = size(output, 1))
 end
 

FastTimeSeries/src/models/Models.jl

@@ -6,6 +6,7 @@ using Flux
 using Zygote
 using DataDeps
 using InlineTest
+using ChainRulesCore
 
 # include("StackedLSTM.jl")
 include("layers.jl")

FastTimeSeries/src/models/RNN.jl

@@ -28,10 +28,9 @@ end
 
 function (m::RNNModel)(X)
     X = tabular2rnn(X)
-    Flux.reset!(m.recbackbone)
-    # ChainRulesCore.ignore_derivatives() do
-    #     Flux.reset!(m.recbackbone)
-    # end
+    ChainRulesCore.ignore_derivatives() do
+        Flux.reset!(m.recbackbone)
+    end
     X = m.recbackbone(X)[:, :, end]
     return m.finalclassifier(X)
 end

FastTimeSeries/src/tasks/regression.jl

@@ -8,6 +8,7 @@ function TSRegression(blocks::Tuple{<:TimeSeriesRow, <:Continuous}, data)
     return SupervisedTask(
         blocks,
         (
+            ContinuousPreprocessing(),
             setup(TSPreprocessing, blocks[1], data[1].table),
         ),
         ŷblock = blocks[2]