diff options
| -rw-r--r-- | SpatialContrastiveNormalization.lua | 42 | ||||
| -rw-r--r-- | SpatialDivisiveNormalization.lua | 5 | ||||
| -rw-r--r-- | init.lua | 1 |
3 files changed, 45 insertions, 3 deletions
diff --git a/SpatialContrastiveNormalization.lua b/SpatialContrastiveNormalization.lua new file mode 100644 index 0000000..262d3b1 --- /dev/null +++ b/SpatialContrastiveNormalization.lua @@ -0,0 +1,42 @@ +local SpatialContrastiveNormalization, parent = torch.class('nn.SpatialContrastiveNormalization','nn.Module') + +function SpatialContrastiveNormalization:__init(nInputPlane, kernel, threshold, thresval) + parent.__init(self) + + -- get args + self.nInputPlane = nInputPlane or 1 + self.kernel = kernel or torch.Tensor(9,9):fill(1) + self.threshold = threshold or 1e-4 + self.thresval = thresval or 1e-4 + local kdim = self.kernel:nDimension() + + -- check args + if kdim ~= 2 and kdim ~= 1 then + error('<SpatialContrastiveNormalization> averaging kernel must be 2D or 1D') + end + if (self.kernel:size(1) % 2) == 0 or (kdim == 2 and (self.kernel:size(2) % 2) == 0) then + error('<SpatialContrastiveNormalization> averaging kernel must have ODD dimensions') + end + + -- instantiate sub+div normalization + self.normalizer = nn.Sequential() + self.normalizer:add(nn.SpatialSubtractiveNormalization(self.nInputPlane, self.kernel)) + self.normalizer:add(nn.SpatialDivisiveNormalization(self.nInputPlane, self.kernel, + self.threshold, self.threshval)) +end + +function SpatialContrastiveNormalization:updateOutput(input) + self.output = self.normalizer:forward(input) + return self.output +end + +function SpatialContrastiveNormalization:updateGradInput(input, gradOutput) + self.gradInput = self.normalizer:backward(input, gradOutput) + return self.gradInput +end + +function SpatialContrastiveNormalization:type(type) + parent.type(self,type) + self.normalizer:type(type) + return self +end diff --git a/SpatialDivisiveNormalization.lua b/SpatialDivisiveNormalization.lua index eaf7465..33668e9 100644 --- a/SpatialDivisiveNormalization.lua +++ b/SpatialDivisiveNormalization.lua @@ -18,9 +18,6 @@ function SpatialDivisiveNormalization:__init(nInputPlane, kernel, threshold, thr error('<SpatialDivisiveNormalization> averaging kernel must have ODD dimensions') end - -- normalize kernel - self.kernel:div(self.kernel:sum() * self.nInputPlane) - -- padding values local padH = math.floor(self.kernel:size(1)/2) local padW = padH @@ -62,6 +59,7 @@ function SpatialDivisiveNormalization:__init(nInputPlane, kernel, threshold, thr -- set kernel and bias if kdim == 2 then + self.kernel:div(self.kernel:sum() * self.nInputPlane) for i = 1,self.nInputPlane do self.meanestimator.modules[2].weight[i] = self.kernel self.stdestimator.modules[3].weight[i] = self.kernel @@ -69,6 +67,7 @@ function SpatialDivisiveNormalization:__init(nInputPlane, kernel, threshold, thr self.meanestimator.modules[2].bias:zero() self.stdestimator.modules[3].bias:zero() else + self.kernel:div(self.kernel:sum() * math.sqrt(self.nInputPlane)) for i = 1,self.nInputPlane do self.meanestimator.modules[2].weight[i]:copy(self.kernel) self.meanestimator.modules[3].weight[i]:copy(self.kernel) @@ -63,6 +63,7 @@ torch.include('nn', 'TemporalConvolution.lua') torch.include('nn', 'TemporalSubSampling.lua') torch.include('nn', 'SpatialSubtractiveNormalization.lua') torch.include('nn', 'SpatialDivisiveNormalization.lua') +torch.include('nn', 'SpatialContrastiveNormalization.lua') torch.include('nn', 'SpatialZeroPadding.lua') torch.include('nn', 'VolumetricConvolution.lua') |