Brian Broll
09b6ca0ad0
WIP #3. Added import tests WIP #3 Added more test-cases WIP #3 Added more tests WIP #3. Fixed concat.lua test WIP #3 minor changes WIP #3 Fixed concat-parallel.lua WIP #3 Added check-model helper WIP #3 Added more tests for model checker WIP #3 Added extra tests WIP #3 Changed check-model to GraphChecker WIP #3. multiple cases fail for ImportTorch... WIP #3 Fixed ImportTorch batch test case running WIP #3 Changed graph checker to use gme path for id WIP #3 Updated tests WIP #3. Tweaked to get all examples working locally w/ 'th' WIP #3 Fixed tests
31 linhas
1.3 KiB
Lua
31 linhas
1.3 KiB
Lua
require 'nn'
|
|
-- a typical convolutional network, with locally-normalized hidden
|
|
-- units, and L2-pooling
|
|
|
|
-- Note: the architecture of this convnet is loosely based on Pierre Sermanet's
|
|
-- work on this dataset (http://arxiv.org/abs/1204.3968). In particular
|
|
-- the use of LP-pooling (with P=2) has a very positive impact on
|
|
-- generalization. Normalization is not done exactly as proposed in
|
|
-- the paper, and low-level (first layer) features are not fed to
|
|
-- the classifier.
|
|
|
|
model = nn.Sequential()
|
|
|
|
-- stage 1 : filter bank -> squashing -> L2 pooling -> normalization
|
|
model:add(nn.SpatialConvolutionMM(nfeats, nstates[1], filtsize, filtsize))
|
|
model:add(nn.Tanh())
|
|
model:add(nn.SpatialLPPooling(nstates[1],2,poolsize,poolsize,poolsize,poolsize))
|
|
model:add(nn.SpatialSubtractiveNormalization(nstates[1], normkernel))
|
|
|
|
-- stage 2 : filter bank -> squashing -> L2 pooling -> normalization
|
|
model:add(nn.SpatialConvolutionMM(nstates[1], nstates[2], filtsize, filtsize))
|
|
model:add(nn.Tanh())
|
|
model:add(nn.SpatialLPPooling(nstates[2],2,poolsize,poolsize,poolsize,poolsize))
|
|
model:add(nn.SpatialSubtractiveNormalization(nstates[2], normkernel))
|
|
|
|
-- stage 3 : standard 2-layer neural network
|
|
model:add(nn.Reshape(nstates[2]*filtsize*filtsize))
|
|
model:add(nn.Linear(nstates[2]*filtsize*filtsize, nstates[3]))
|
|
model:add(nn.Tanh())
|
|
model:add(nn.Linear(nstates[3], noutputs))
|