lazy init

DilipA · Feb 9, 2016 · 4696a46 · 4696a46
1 parent 948ac6a
commit 4696a46
Show file tree

Hide file tree

Showing 17 changed files with 35 additions and 46 deletions.
diff --git a/BCECriterion.lua b/BCECriterion.lua
@@ -30,7 +30,7 @@ function BCECriterion:updateOutput(input, target)
     assert( input:nElement() == target:nElement(),
     "input and target size mismatch")
 
-    self.buffer = self.buffer or torch.Tensor():typeAs(input)
+    self.buffer = self.buffer or input.new()
 
     local buffer = self.buffer
     local weights = self.weights
@@ -74,7 +74,7 @@ function BCECriterion:updateGradInput(input, target)
     assert( input:nElement() == target:nElement(),
     "input and target size mismatch")
 
-    self.buffer = self.buffer or torch.Tensor():typeAs(input)
+    self.buffer = self.buffer or input.new()
 
     local buffer = self.buffer
     local weights = self.weights

diff --git a/LogSigmoid.lua b/LogSigmoid.lua
@@ -1,11 +1,7 @@
 local LogSigmoid, parent = torch.class('nn.LogSigmoid', 'nn.Module')
 
-function LogSigmoid:__init()
-   parent.__init(self)
-   self.buffer = torch.Tensor()
-end
-
 function LogSigmoid:updateOutput(input)
+   self.buffer = self.buffer or input.new()
    input.THNN.LogSigmoid_updateOutput(
       input:cdata(),
       self.output:cdata(),

diff --git a/PReLU.lua b/PReLU.lua
@@ -6,8 +6,6 @@ function PReLU:__init(nOutputPlane)
    self.nOutputPlane = nOutputPlane or 0
    self.weight = torch.Tensor(nOutputPlane or 1):fill(0.25)
    self.gradWeight = torch.Tensor(nOutputPlane or 1)
-   self.gradWeightBuf = torch.Tensor()
-   self.gradWeightBuf2 = torch.Tensor()
 end
 
 function PReLU:updateOutput(input)
@@ -32,6 +30,8 @@ function PReLU:updateGradInput(input, gradOutput)
 end
 
 function PReLU:accGradParameters(input, gradOutput, scale)
+   self.gradWeightBuf = self.gradWeightBuf or input.new()
+   self.gradWeightBuf2 = self.gradWeightBuf2 or input.new()
    input.THNN.PReLU_accGradParameters(
       input:cdata(),
       gradOutput:cdata(),

diff --git a/Reshape.lua b/Reshape.lua
@@ -26,14 +26,12 @@ function Reshape:__init(...)
       self.nelement = self.nelement * self.size[i]
       self.batchsize[i+1] = self.size[i]
    end
-
-   -- only used for non-contiguous input or gradOutput
-   self._input = torch.Tensor()
-   self._gradOutput = torch.Tensor()
 end
 
 function Reshape:updateOutput(input)
    if not input:isContiguous() then
+      self._input = self._input or input.new()
+      self._gradOutput = self._gradOutput or input.new()
       self._input:resizeAs(input)
       self._input:copy(input)
       input = self._input

diff --git a/SpatialAdaptiveMaxPooling.lua b/SpatialAdaptiveMaxPooling.lua
@@ -5,11 +5,10 @@ function SpatialAdaptiveMaxPooling:__init(W, H)
 
    self.W = W
    self.H = H
-
-   self.indices = torch.Tensor()
 end
 
 function SpatialAdaptiveMaxPooling:updateOutput(input)
+   self.indices = self.indices or input.new()
    input.THNN.SpatialAdaptiveMaxPooling_updateOutput(
       input:cdata(),
       self.output:cdata(),

diff --git a/SpatialConvolution.lua b/SpatialConvolution.lua
@@ -155,8 +155,8 @@ function SpatialConvolution:accGradParameters(input, gradOutput, scale)
 end
 
 function SpatialConvolution:type(type,tensorCache)
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
+   self.finput = self.finput and torch.Tensor()
+   self.fgradInput = self.fgradInput and torch.Tensor()
    return parent.type(self,type,tensorCache)
 end
 

diff --git a/SpatialConvolutionLocal.lua b/SpatialConvolutionLocal.lua
@@ -26,9 +26,6 @@ function SpatialConvolutionLocal:__init(nInputPlane, nOutputPlane, iW, iH ,kW, k
    self.gradWeight = torch.Tensor():resizeAs(self.weight)
    self.gradBias = torch.Tensor():resizeAs(self.bias)
 
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
-
    self:reset()
 end
 
@@ -117,6 +114,8 @@ local function checkOutputSize(self, input, output)
 end
 
 function SpatialConvolutionLocal:updateOutput(input)
+   self.finput = self.finput or input.new()
+   self.fgradInput = self.fgradInput or input.new()
    checkInputSize(self, input)
    viewWeight(self)
    input = makeContiguous(self, input)
@@ -148,8 +147,8 @@ function SpatialConvolutionLocal:accGradParameters(input, gradOutput, scale)
 end
 
 function SpatialConvolutionLocal:type(type,tensorCache)
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
+   self.finput = self.finput and torch.Tensor()
+   self.fgradInput = self.fgradInput and torch.Tensor()
    return parent.type(self,type,tensorCache)
 end
 

diff --git a/SpatialConvolutionMM.lua b/SpatialConvolutionMM.lua
@@ -21,9 +21,6 @@ function SpatialConvolutionMM:__init(nInputPlane, nOutputPlane, kW, kH, dW, dH,
    self.gradWeight = torch.Tensor(nOutputPlane, nInputPlane*kH*kW)
    self.gradBias = torch.Tensor(nOutputPlane)
 
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
-
    self:reset()
 end
 
@@ -63,6 +60,8 @@ local function makeContiguous(self, input, gradOutput)
 end
 
 function SpatialConvolutionMM:updateOutput(input)
+   self.finput = self.finput or input.new()
+   self.fgradInput = self.fgradInput or input.new()
    -- backward compatibility
    if self.padding then
       self.padW = self.padding
@@ -121,8 +120,8 @@ function SpatialConvolutionMM:accGradParameters(input, gradOutput, scale)
 end
 
 function SpatialConvolutionMM:type(type,tensorCache)
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
+   self.finput = self.finput and torch.Tensor()
+   self.fgradInput = self.fgradInput and torch.Tensor()
    return parent.type(self,type,tensorCache)
 end
 

diff --git a/SpatialCrossMapLRN.lua b/SpatialCrossMapLRN.lua
@@ -7,14 +7,14 @@ function SpatialCrossMapLRN:__init(size, alpha, beta, k)
   self.alpha = alpha or 0.0001
   self.beta = beta or 0.75
   self.k = k or 1
-
-  self.scale = torch.Tensor()
 end
 
 function SpatialCrossMapLRN:updateOutput(input)
   assert(input:dim() == 3 or input:dim() == 4,
          'Input must be 3D or 4D')
 
+  self.scale = self.scale or input.new()
+
   if torch.type(input) == 'torch.CudaTensor' then
      input.nn.SpatialCrossMapLRN_updateOutput(self, input)
   else

diff --git a/SpatialFractionalMaxPooling.lua b/SpatialFractionalMaxPooling.lua
@@ -15,7 +15,6 @@ function SpatialFractionalMaxPooling:__init(poolSizeW, poolSizeH, arg1, arg2)
    -- Pool size (how wide the pooling for each output unit is)
    self.poolSizeW = poolSizeW
    self.poolSizeH = poolSizeH
-   self.indices = torch.Tensor()
 
    -- Random samples are drawn for all
    -- batch * plane * (height, width; i.e., 2) points. This determines
@@ -115,6 +114,7 @@ function SpatialFractionalMaxPooling:fixPoolingRegions(val)
 end
 
 function SpatialFractionalMaxPooling:updateOutput(input)
+   self.indices = self.indices or input.new()
    self:initSampleBuffer_(input)
    local outW, outH = self:getOutputSizes_(input)
 

diff --git a/SpatialFullConvolution.lua b/SpatialFullConvolution.lua
@@ -28,9 +28,6 @@ function SpatialFullConvolution:__init(nInputPlane, nOutputPlane,
    self.bias = torch.Tensor(self.nOutputPlane)
    self.gradBias = torch.Tensor(self.nOutputPlane)
 
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
-
    self:reset()
 end
 
@@ -69,6 +66,8 @@ function SpatialFullConvolution:backCompatibility()
 end
 
 function SpatialFullConvolution:updateOutput(input)
+  self.finput = self.finput or input.new()
+  self.fgradInput = self.fgradInput or input.new()
   self:backCompatibility()
 
   input = makeContiguous(self, input)
@@ -92,8 +91,8 @@ function SpatialFullConvolution:accGradParameters(input, gradOutput, scale)
 end
 
 function SpatialFullConvolution:type(type, tensorCache)
-  self.finput = torch.Tensor()
-  self.fgradInput = torch.Tensor()
+  self.finput = self.finput and torch.Tensor()
+  self.fgradInput = self.fgradInput and torch.Tensor()
   return parent.type(self, type, tensorCache)
 end
 

diff --git a/SpatialMaxPooling.lua b/SpatialMaxPooling.lua
@@ -29,6 +29,7 @@ function SpatialMaxPooling:floor()
 end
 
 function SpatialMaxPooling:updateOutput(input)
+   self.indices = self.indices or input.new()
    -- backward compatibility
    self.ceil_mode = self.ceil_mode or false
    self.padW = self.padW or 0

diff --git a/TemporalMaxPooling.lua b/TemporalMaxPooling.lua
@@ -7,11 +7,10 @@ function TemporalMaxPooling:__init(kW, dW)
 
    self.kW = kW
    self.dW = dW
-
-   self.indices = torch.Tensor()
 end
 
 function TemporalMaxPooling:updateOutput(input)
+   self.indices = self.indices or input.new()
    input.nn.TemporalMaxPooling_updateOutput(self, input)
    return self.output
 end

diff --git a/VolumetricConvolution.lua b/VolumetricConvolution.lua
@@ -23,9 +23,6 @@ function VolumetricConvolution:__init(nInputPlane, nOutputPlane, kT, kW, kH, dT,
    self.bias = torch.Tensor(nOutputPlane)
    self.gradWeight = torch.Tensor(nOutputPlane, nInputPlane, kT, kH, kW)
    self.gradBias = torch.Tensor(nOutputPlane)
-   -- temporary buffers for unfolding (CUDA)
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
    self:reset()
 end
 
@@ -80,6 +77,8 @@ local function unviewWeight(self)
 end
 
 function VolumetricConvolution:updateOutput(input)
+   self.finput = self.finput or input.new()
+   self.fgradInput = self.fgradInput or input.new()
    if input:type() == 'torch.CudaTensor' then
       input.THNN.VolumetricConvolution_updateOutput(
         input:cdata(),
@@ -171,8 +170,8 @@ function VolumetricConvolution:accGradParameters(input, gradOutput, scale)
 end
 
 function VolumetricConvolution:type(type, tensorCache)
-   self.finput:set()
-   self.fgradInput:set()
+   if self.finput then self.finput:set() end
+   if self.fgradInput then self.fgradInput:set() end
    return parent.type(self, type, tensorCache)
 end
 

diff --git a/VolumetricFullConvolution.lua b/VolumetricFullConvolution.lua
@@ -27,9 +27,6 @@ function VolumetricFullConvolution:__init(nInputPlane, nOutputPlane, kT, kH, kW,
    self.bias = torch.Tensor(nOutputPlane)
    self.gradWeight = torch.Tensor(nOutputPlane, nInputPlane, kT, kH, kW)
    self.gradBias = torch.Tensor(nOutputPlane)
-   -- temporary buffers for unfolding (CUDA)
-   self.finput = torch.Tensor()
-   self.fgradInput = torch.Tensor()
    self:reset()
 end
 
@@ -54,6 +51,8 @@ function VolumetricFullConvolution:reset(stdv)
 end
 
 function VolumetricFullConvolution:updateOutput(input)
+   self.finput = self.finput or input.new()
+   self.fgradInput = self.fgradInput or input.new()
    input.THNN.VolumetricFullConvolution_updateOutput(
       input:cdata(),
       self.output:cdata(),

diff --git a/VolumetricMaxPooling.lua b/VolumetricMaxPooling.lua
@@ -36,6 +36,7 @@ function VolumetricMaxPooling:floor()
 end
 
 function VolumetricMaxPooling:updateOutput(input)
+   self.indices = self.indices or input.new()
    input.THNN.VolumetricMaxPooling_updateOutput(
       input:cdata(),
       self.output:cdata(),

diff --git a/WeightedMSECriterion.lua b/WeightedMSECriterion.lua
@@ -3,10 +3,10 @@ local WeightedMSECriterion, parent = torch.class('nn.WeightedMSECriterion','nn.M
 function WeightedMSECriterion:__init(w)
    parent.__init(self)
    self.weight = w:clone()
-   self.buffer = torch.Tensor()
 end
 
 function WeightedMSECriterion:updateOutput(input,target)
+   self.buffer = self.buffer or input.new()
    self.buffer:resizeAs(input):copy(target)
    if input:dim() - 1 == self.weight:dim() then
       for i=1,input:size(1) do