From b5b6b57751d6bc3379c7379cc0ec5164fade8e3c Mon Sep 17 00:00:00 2001 From: tan tian Date: Mon, 18 Apr 2016 18:47:57 +0800 Subject: add projection layer and lstmp layer --- nerv/Makefile | 1 + nerv/layer/init.lua | 2 ++ nerv/layer/lstmp.lua | 91 +++++++++++++++++++++++++++++++++++++++++++++++ nerv/layer/projection.lua | 64 +++++++++++++++++++++++++++++++++ 4 files changed, 158 insertions(+) create mode 100644 nerv/layer/lstmp.lua create mode 100644 nerv/layer/projection.lua diff --git a/nerv/Makefile b/nerv/Makefile index dde8fe7..f74a92f 100644 --- a/nerv/Makefile +++ b/nerv/Makefile @@ -40,6 +40,7 @@ OBJS := $(CORE_OBJS) $(NERV_OBJS) $(LUAT_OBJS) LIBS := $(INST_LIBDIR)/libnerv.so $(LIB_PATH)/libnervcore.so $(LIB_PATH)/libluaT.so LUA_LIBS := matrix/init.lua io/init.lua init.lua \ layer/init.lua layer/affine.lua layer/sigmoid.lua layer/tanh.lua layer/softmax_ce.lua layer/softmax.lua \ + layer/lstmp.lua layer/projection.lua \ layer/window.lua layer/bias.lua layer/combiner.lua layer/mse.lua \ layer/elem_mul.lua layer/lstm.lua layer/lstm_gate.lua layer/dropout.lua layer/gru.lua \ layer/graph.lua layer/rnn.lua layer/duplicate.lua layer/identity.lua \ diff --git a/nerv/layer/init.lua b/nerv/layer/init.lua index 3a6cbcd..c893df3 100644 --- a/nerv/layer/init.lua +++ b/nerv/layer/init.lua @@ -152,6 +152,8 @@ nerv.include('gru.lua') nerv.include('rnn.lua') nerv.include('duplicate.lua') nerv.include('identity.lua') +nerv.include('projection.lua') +nerv.include('lstmp.lua') -- The following lines are for backward compatibility, and will be removed in -- the future. The use of these names are deprecated. diff --git a/nerv/layer/lstmp.lua b/nerv/layer/lstmp.lua new file mode 100644 index 0000000..bbb2091 --- /dev/null +++ b/nerv/layer/lstmp.lua @@ -0,0 +1,91 @@ +local LSTMPLayer = nerv.class('nerv.LSTMPLayer', 'nerv.GraphLayer') + +function LSTMPLayer:__init(id, global_conf, layer_conf) + nerv.Layer.__init(self, id, global_conf, layer_conf) + self:check_dim_len(1, 1) + + local din = layer_conf.dim_in[1] + local dcell = layer_conf.cell_dim + local dout = layer_conf.dim_out[1] + + local pr = layer_conf.pr + if pr == nil then + pr = nerv.ParamRepo({}, self.loc_type) + end + + local layers = { + ['nerv.CombinerLayer'] = { + mainCombine = {dim_in = {dcell, dcell}, dim_out = {dcell}, lambda = {1, 1}}, + }, + ['nerv.DuplicateLayer'] = { + inputDup = {dim_in = {din}, dim_out = {din, din, din, din}}, + outputDup = {dim_in = {dout}, dim_out = {dout, dout, dout, dout, dout}}, + cellDup = {dim_in = {dcell}, dim_out = {dcell, dcell, dcell, dcell, dcell}}, + }, + ['nerv.AffineLayer'] = { + mainAffine = {dim_in = {din, dout}, dim_out = {dcell}, pr = pr}, + }, + ['nerv.TanhLayer'] = { + mainTanh = {dim_in = {dcell}, dim_out = {dcell}}, + outputTanh = {dim_in = {dcell}, dim_out = {dcell}}, + }, + ['nerv.LSTMGateLayer'] = { + forgetGate = {dim_in = {din, dout, dcell}, dim_out = {dcell}, param_type = {'N', 'N', 'D'}, pr = pr}, + inputGate = {dim_in = {din, dout, dcell}, dim_out = {dcell}, param_type = {'N', 'N', 'D'}, pr = pr}, + outputGate = {dim_in = {din, dout, dcell}, dim_out = {dcell}, param_type = {'N', 'N', 'D'}, pr = pr}, + }, + ['nerv.ElemMulLayer'] = { + inputGateMul = {dim_in = {dcell, dcell}, dim_out = {dcell}}, + forgetGateMul = {dim_in = {dcell, dcell}, dim_out = {dcell}}, + outputGateMul = {dim_in = {dcell, dcell}, dim_out = {dcell}}, + }, + ['nerv.ProjectionLayer'] = { + projection = {dim_in = {dcell}, dim_out = {dout}, pr = pr}, + }, + } + + local connections = { + -- lstm input + {'[1]', 'inputDup[1]', 0}, + + -- input gate + {'inputDup[1]', 'inputGate[1]', 0}, + {'outputDup[1]', 'inputGate[2]', 1}, + {'cellDup[1]', 'inputGate[3]', 1}, + + -- forget gate + {'inputDup[2]', 'forgetGate[1]', 0}, + {'outputDup[2]', 'forgetGate[2]', 1}, + {'cellDup[2]', 'forgetGate[3]', 1}, + + -- lstm cell + {'forgetGate[1]', 'forgetGateMul[1]', 0}, + {'cellDup[3]', 'forgetGateMul[2]', 1}, + {'inputDup[3]', 'mainAffine[1]', 0}, + {'outputDup[3]', 'mainAffine[2]', 1}, + {'mainAffine[1]', 'mainTanh[1]', 0}, + {'inputGate[1]', 'inputGateMul[1]', 0}, + {'mainTanh[1]', 'inputGateMul[2]', 0}, + {'inputGateMul[1]', 'mainCombine[1]', 0}, + {'forgetGateMul[1]', 'mainCombine[2]', 0}, + {'mainCombine[1]', 'cellDup[1]', 0}, + + -- forget gate + {'inputDup[4]', 'outputGate[1]', 0}, + {'outputDup[4]', 'outputGate[2]', 1}, + {'cellDup[4]', 'outputGate[3]', 0}, + + -- lstm output + {'cellDup[5]', 'outputTanh[1]', 0}, + {'outputGate[1]', 'outputGateMul[1]', 0}, + {'outputTanh[1]', 'outputGateMul[2]', 0}, + {'outputGateMul[1]', 'projection[1]', 0}, + {'projection[1]', 'outputDup[1]', 0}, + {'outputDup[5]', '[1]', 0}, + } + + self:add_prefix(layers, connections) + local layer_repo = nerv.LayerRepo(layers, pr, global_conf) + self.lrepo = layer_repo + self:graph_init(layer_repo, connections) +end diff --git a/nerv/layer/projection.lua b/nerv/layer/projection.lua new file mode 100644 index 0000000..d99401c --- /dev/null +++ b/nerv/layer/projection.lua @@ -0,0 +1,64 @@ +local ProjectionLayer = nerv.class('nerv.ProjectionLayer', 'nerv.Layer') + +--- The constructor. +function ProjectionLayer:__init(id, global_conf, layer_conf) + nerv.Layer.__init(self, id, global_conf, layer_conf) + self:check_dim_len(-1, 1) -- exactly one output, allow multiple inputs + self:bind_params() +end + +function ProjectionLayer:bind_params() + for i = 1, #self.dim_in do + local pid = "ltp" .. i + local pid_list = i == 1 and {pid, "ltp"} or pid + self["ltp" .. i] = self:find_param(pid_list, self.lconf, self.gconf, + nerv.LinearTransParam, + {self.dim_in[i], self.dim_out[1]}) + end + self.ltp = self.ltp1 -- alias of ltp1 +end + +function ProjectionLayer:init(batch_size) + for i = 1, #self.dim_in do + if self.dim_in[i] ~= self["ltp" .. i].trans:nrow() then + nerv.error("mismatching dimensions of linear transform parameter and input") + end + if self.dim_out[1] ~= self["ltp" .. i].trans:ncol() then + nerv.error("mismatching dimensions of linear transform parameter and output") + end + self["ltp" .. i]:train_init() + end +end + +function ProjectionLayer:batch_resize(batch_size) + -- do nothing +end + +function ProjectionLayer:update() + for i = 1, #self.dim_in do + self["ltp" .. i]:update_by_err_input() + end +end + +function ProjectionLayer:propagate(input, output) + -- apply linear transform + output[1]:mul(input[1], self.ltp1.trans, 1.0, 0.0, 'N', 'N') + for i = 2, #self.dim_in do + output[1]:mul(input[i], self["ltp" .. i].trans, 1.0, 1.0, 'N', 'N') + end +end + +function ProjectionLayer:back_propagate(bp_err, next_bp_err, input, output) + for i = 1, #self.dim_in do + next_bp_err[i]:mul(bp_err[1], self["ltp" .. i].trans, 1.0, 0.0, 'N', 'T') + self["ltp" .. i]:back_propagate_by_err_input(bp_err[1], input[i]) + end +end + +function ProjectionLayer:get_params() + local pr = nerv.ParamRepo({self.ltp1}, self.loc_type) + for i = 2, #self.dim_in do + pr:add(self["ltp" .. i].id, self["ltp" .. i]) + end + return pr +end -- cgit v1.2.3