require 'lmptb.lmvocab'
require 'lmptb.lmfeeder'
require 'lmptb.lmutil'
require 'lmptb.layer.init'
--require 'tnn.init'
require 'lmptb.lmseqreader'
require 'lm_trainer'
require 'lm_sampler'
--[[global function rename]]--
--local printf = nerv.printf
local LMTrainer = nerv.LMTrainer
--[[global function rename ends]]--
function prepare_parameters(global_conf, fn)
nerv.printf("%s preparing parameters...\n", global_conf.sche_log_pre)
global_conf.paramRepo = nerv.ParamRepo()
local paramRepo = global_conf.paramRepo
nerv.printf("%s loading parameter from file %s...\n", global_conf.sche_log_pre, fn)
paramRepo:import({fn}, nil, global_conf)
nerv.printf("%s preparing parameters end.\n", global_conf.sche_log_pre)
return nil
end
--global_conf: table
--Returns: nerv.LayerRepo
function prepare_layers(global_conf)
nerv.printf("%s preparing layers...\n", global_conf.sche_log_pre)
local pr = global_conf.paramRepo
local du = false
--local recurrentLconfig = {{["bp"] = "bp_h", ["ltp_hh"] = "ltp_hh"}, {["dim_in"] = {global_conf.hidden_size, global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}, ["break_id"] = global_conf.vocab:get_sen_entry().id, ["independent"] = global_conf.independent, ["clip"] = 10}}
--local recurrentLconfig = {{}, {["dim_in"] = {global_conf.hidden_size, global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}, ["clip"] = 10, ["direct_update"] = du, ["pr"] = pr}}
local layers = {
["nerv.GRULayerT"] = {
["gruL1"] = {{}, {["dim_in"] = {global_conf.hidden_size, global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}, ["pr"] = pr}},
},
["nerv.DropoutLayerT"] = {
["dropoutL1"] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}}},
},
["nerv.SelectLinearLayer"] = {
["selectL1"] = {{}, {["dim_in"] = {1}, ["dim_out"] = {global_conf.hidden_size}, ["vocab"] = global_conf.vocab, ["pr"] = pr}},
},
["nerv.CombinerLayer"] = {
["combinerL1"] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size, global_conf.hidden_size}, ["lambda"] = {1}}},
},
["nerv.AffineLayer"] = {
["outputL"] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.vocab:size()}, ["direct_update"] = du, ["pr"] = pr}},
},
["nerv.SoftmaxCELayerT"] = {
["softmaxL"] = {{}, {["dim_in"] = {global_conf.vocab:size(), global_conf.vocab:size()}, ["dim_out"] = {1}}},
},
}
for l = 2, global_conf.layer_num do
layers["nerv.DropoutLayerT"]["dropoutL" .. l] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}}}
layers["nerv.GRULayerT"]["gruL" .. l] = {{}, {["dim_in"] = {global_conf.hidden_size, global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}, ["pr"] = pr}}
layers["nerv.CombinerLayer"]["combinerL" .. l] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size, global_conf.hidden_size}, ["lambda"] = {1}}}
end
--[[ --we do not need those in the new tnn framework
printf("%s adding %d bptt layers...\n", global_conf.sche_log_pre, global_conf.bptt)
for i = 1, global_conf.bptt do
layers["nerv.IndRecurrentLayer"]["recurrentL" .. (i + 1)] = recurrentLconfig
layers["nerv.SigmoidLayer"]["sigmoidL" .. (i + 1)] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}}}
layers["nerv.SelectLinearLayer"]["selectL" .. (i + 1)] = {{["ltp"] = "ltp_ih"}, {["dim_in"] = {1}, ["dim_out"] = {global_conf.hidden_size}}}
end
--]]
local layerRepo = nerv.LayerRepo(layers, pr, global_conf)
nerv.printf("%s preparing layers end.\n", global_conf.sche_log_pre)
return layerRepo