face-alignment-training icon indicating copy to clipboard operation
face-alignment-training copied to clipboard

Batchnorm parameter

Open zhengge opened this issue 6 years ago • 1 comments

local function convBlock(numIn, numOut, order)
    local cnet = nn.Sequential()
        :add(batchnorm(numIn,1e-5,false))
        :add(relu(true))
        :add(conv(numIn,numOut/2,3,3,1,1,1,1):noBias())
        :add(nn.ConcatTable()
            :add(nn.Identity())
            :add(nn.Sequential()
                :add(nn.Sequential()
                    :add(batchnorm(numOut/2,1e-5,false))
                    :add(relu(true))
                    :add(conv(numOut/2,numOut/4,3,3,1,1,1,1):noBias())
                )

batchnorm(numIn,1e-5,false) Dose this statement want to set affine = false? But in fact, four parameters (nOutput, eps, momentum, affine) are needed. The batchnorm will have wight and bias.

zhengge avatar Feb 03 '18 06:02 zhengge

Same question as above

lippman1125 avatar Feb 20 '19 04:02 lippman1125