From c1eb74539cf31f966176a17cb27797b1fb69461a Mon Sep 17 00:00:00 2001 From: txh18 Date: Fri, 30 Oct 2015 17:00:13 +0800 Subject: start implementing tdag_layer --- nerv/examples/lmptb/m-tests/dagl_test.lua | 164 +++++++++++++++++ nerv/examples/lmptb/rnn/layer_tdag.lua | 291 ++++++++++++++++++++++++++++++ 2 files changed, 455 insertions(+) create mode 100644 nerv/examples/lmptb/m-tests/dagl_test.lua create mode 100644 nerv/examples/lmptb/rnn/layer_tdag.lua diff --git a/nerv/examples/lmptb/m-tests/dagl_test.lua b/nerv/examples/lmptb/m-tests/dagl_test.lua new file mode 100644 index 0000000..02e9c49 --- /dev/null +++ b/nerv/examples/lmptb/m-tests/dagl_test.lua @@ -0,0 +1,164 @@ +require 'lmptb.lmvocab' +require 'lmptb.lmfeeder' +require 'lmptb.lmutil' +require 'lmptb.layer.init' +require 'rnn.layer_tdag' + +--[[global function rename]]-- +printf = nerv.printf +--[[global function rename ends]]-- + +--global_conf: table +--first_time: bool +--Returns: a ParamRepo +function prepare_parameters(global_conf, first_time) + printf("%s preparing parameters...\n", global_conf.sche_log_pre) + + if (first_time) then + ltp_ih = nerv.LinearTransParam("ltp_ih", global_conf) + ltp_ih.trans = global_conf.cumat_type(global_conf.vocab:size() + 1, global_conf.hidden_size) --index 0 is for zero, others correspond to vocab index(starting from 1) + ltp_ih.trans:generate(global_conf.param_random) + ltp_ih.trans[0]:fill(0) + + ltp_hh = nerv.LinearTransParam("ltp_hh", global_conf) + ltp_hh.trans = global_conf.cumat_type(global_conf.hidden_size, global_conf.hidden_size) + ltp_hh.trans:generate(global_conf.param_random) + + ltp_ho = nerv.LinearTransParam("ltp_ho", global_conf) + ltp_ho.trans = global_conf.cumat_type(global_conf.hidden_size, global_conf.vocab:size()) + ltp_ho.trans:generate(global_conf.param_random) + + bp_h = nerv.BiasParam("bp_h", global_conf) + bp_h.trans = global_conf.cumat_type(1, global_conf.hidden_size) + bp_h.trans:generate(global_conf.param_random) + + bp_o = nerv.BiasParam("bp_o", global_conf) + bp_o.trans = global_conf.cumat_type(1, global_conf.vocab:size()) + bp_o.trans:generate(global_conf.param_random) + + local f = nerv.ChunkFile(global_conf.param_fn, 'w') + f:write_chunk(ltp_ih) + f:write_chunk(ltp_hh) + f:write_chunk(ltp_ho) + f:write_chunk(bp_h) + f:write_chunk(bp_o) + f:close() + end + + local paramRepo = nerv.ParamRepo() + paramRepo:import({global_conf.param_fn}, nil, global_conf) + + printf("%s preparing parameters end.\n", global_conf.sche_log_pre) + + return paramRepo +end + +--global_conf: table +--Returns: nerv.LayerRepo +function prepare_layers(global_conf, paramRepo) + printf("%s preparing layers...\n", global_conf.sche_log_pre) + + 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 layers = { + ["nerv.IndRecurrentLayer"] = { + ["recurrentL1"] = recurrentLconfig, + }, + + ["nerv.SelectLinearLayer"] = { + ["selectL1"] = {{["ltp"] = "ltp_ih"}, {["dim_in"] = {1}, ["dim_out"] = {global_conf.hidden_size}}}, + }, + + ["nerv.SigmoidLayer"] = { + ["sigmoidL1"] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}}} + }, + + ["nerv.AffineLayer"] = { + ["outputL"] = {{["ltp"] = "ltp_ho", ["bp"] = "bp_o"}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.vocab:size()}}}, + }, + + ["nerv.SoftmaxCELayer"] = { + ["softmaxL"] = {{}, {["dim_in"] = {global_conf.vocab:size(), global_conf.vocab:size()}, ["dim_out"] = {1}}}, + }, + } + + --[[ --we do not need those in the new rnn 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, paramRepo, global_conf) + printf("%s preparing layers end.\n", global_conf.sche_log_pre) + return layerRepo +end + +--global_conf: table +--layerRepo: nerv.LayerRepo +--Returns: a nerv.DAGLayer +function prepare_dagLayer(global_conf, layerRepo) + printf("%s Initing daglayer ...\n", global_conf.sche_log_pre) + + --input: input_w, input_w, ... input_w_now, last_activation + local dim_in_t = {} + dim_in_t[1] = 1 --input to select_linear layer + dim_in_t[2] = global_conf.vocab:size() --input to softmax label + local connections_t = { + ["[1]"] = "selectL1[1],0", + ["selectL1[1]"] = "recurrentL1[1],0", + ["recurrentL1[1]"] = "sigmoidL1[1],0", + ["sigmoidL1[1]"] = "outputL[1],0", + ["sigmoidL1[1]"] = "recurrentL1[2],1", + ["outputL[1]"] = "softmaxL[1],0", + ["[2]"] = "softmaxL[2],0", + ["softmaxL[1]"] = "[1],0" + } + + --[[ + printf("%s printing DAG connections:\n", global_conf.sche_log_pre) + for key, value in pairs(connections_t) do + printf("\t%s->%s\n", key, value) + end + ]]-- + + local dagL = nerv.TDAGLayer("dagL", global_conf, {["dim_in"] = dim_in_t, ["dim_out"] = {1}, ["sub_layers"] = layerRepo, + ["connections"] = connections_t, + }) + dagL:init(global_conf.batch_size) + printf("%s Initing DAGLayer end.\n", global_conf.sche_log_pre) + return dagL +end + +train_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text' +test_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text' + +global_conf = { + lrate = 1, wcost = 1e-6, momentum = 0, + cumat_type = nerv.CuMatrixFloat, + mmat_type = nerv.CuMatrixFloat, + + hidden_size = 20, + batch_size = 5, + seq_size = 3, + max_iter = 18, + param_random = function() return (math.random() / 5 - 0.1) end, + independent = true, + + train_fn = train_fn, + test_fn = test_fn, + sche_log_pre = "[SCHEDULER]:", + log_w_num = 10, --give a message when log_w_num words have been processed + timer = nerv.Timer() +} +global_conf.work_dir = '/home/slhome/txh18/workspace/nerv/play/dagL_test' +global_conf.param_fn = global_conf.work_dir.."/params" + +local vocab = nerv.LMVocab() +global_conf["vocab"] = vocab +global_conf.vocab:build_file(global_conf.train_fn, false) +local paramRepo = prepare_parameters(global_conf, true) +local layerRepo = prepare_layers(global_conf, paramRepo) +local dagL = prepare_dagLayer(global_conf, layerRepo) diff --git a/nerv/examples/lmptb/rnn/layer_tdag.lua b/nerv/examples/lmptb/rnn/layer_tdag.lua new file mode 100644 index 0000000..296e2e6 --- /dev/null +++ b/nerv/examples/lmptb/rnn/layer_tdag.lua @@ -0,0 +1,291 @@ +local DAGLayer = nerv.class("nerv.TDAGLayer", "nerv.Layer") + +local function parse_id(str) + local id, port, time, _ + _, _, id, port, time = string.find(str, "([a-zA-Z0-9_]+)%[([0-9]+)%][,]*([0-9]*)") + if id == nil or port == nil then + _, _, id, port, time = string.find(str, "(.+)%[([0-9]+)%][,]*([0-9]*)") + if not (id == "" or id == "") then + nerv.error("wrong format of connection id") + end + end + print(str, id, port, time) + port = tonumber(port) + if (time == nil) then + time = 0 + else + time = tonumber(time) + end + return id, port, time +end + +local function discover(id, layers, layer_repo) + local ref = layers[id] + if id == "" or id == "" then + return nil + end + if ref == nil then + local layer = layer_repo:get_layer(id) + local dim_in, dim_out = layer:get_dim() + ref = { + layer = layer, + inputs = {}, + outputs = {}, + err_inputs = {}, + err_outputs = {}, + next_layers = {}, + input_len = #dim_in, + output_len = #dim_out, + in_deg = 0, + visited = false + } + layers[id] = ref + end + return ref +end + +function DAGLayer:__init(id, global_conf, layer_conf) + local layers = {} + local inputs = {} + local outputs = {} + local dim_in = layer_conf.dim_in + local dim_out = layer_conf.dim_out + local parsed_conn = {} + local _ + local time_to + + for from, to in pairs(layer_conf.connections) do + + local id_from, port_from, _ = parse_id(from) + local id_to, port_to, time_to = parse_id(to) + + local ref_from = discover(id_from, layers, layer_conf.sub_layers) + local ref_to = discover(id_to, layers, layer_conf.sub_layers) + + local input_dim, output_dim, _ + + if ref_from and ref_from.outputs[port_from] ~= nil then + nerv.error("%s has already been attached", from) + end + if ref_to and ref_to.inputs[port_to] ~= nil then + nerv.error("%s has already been attached", to) + end + if id_from == "" then + input_dim, _ = ref_to.layer:get_dim() + if dim_in[port_from] ~= input_dim[port_to] then + nerv.error("mismatching data dimension between %s and %s", from, to) + end + inputs[port_from] = {ref_to, port_to} + ref_to.inputs[port_to] = inputs -- just a place holder + elseif id_to == "" then + _, output_dim = ref_from.layer:get_dim() + if output_dim[port_from] ~= dim_out[port_to] then + nerv.error("mismatching data dimension between %s and %s", from, to) + end + outputs[port_to] = {ref_from, port_from} + ref_from.outputs[port_from] = outputs -- just a place holder + else + _, output_dim = ref_from.layer:get_dim() + input_dim, _ = ref_to.layer:get_dim() + if output_dim[port_from] ~= input_dim[port_to] then + nerv.error("mismatching data dimension between %s and %s", from, to) + end + + table.insert(parsed_conn, + {{ref_from, port_from}, {ref_to, port_to}}) + table.insert(ref_from.next_layers, ref_to) -- add edge + ref_to.in_deg = ref_to.in_deg + 1 -- increase the in-degree of the target layer + end + end + + self.layers = layers + self.inputs = inputs + self.outputs = outputs + self.id = id + self.dim_in = dim_in + self.dim_out = dim_out + self.parsed_conn = parsed_conn + self.queue = queue + self.gconf = global_conf +end + +function DAGLayer:init(batch_size) + for i, conn in ipairs(self.parsed_conn) do + local _, output_dim + local ref_from, port_from, ref_to, port_to + ref_from, port_from = unpack(conn[1]) + ref_to, port_to = unpack(conn[2]) + _, output_dim = ref_from.layer:get_dim() + local dim = 1 + if output_dim[port_from] > 0 then + dim = output_dim[port_from] + end + local mid = self.gconf.cumat_type(batch_size, dim) + local err_mid = mid:create() + + ref_from.outputs[port_from] = mid + ref_to.inputs[port_to] = mid + + ref_from.err_inputs[port_from] = err_mid + ref_to.err_outputs[port_to] = err_mid + end + for id, ref in pairs(self.layers) do + for i = 1, ref.input_len do + if ref.inputs[i] == nil then + nerv.error("dangling input port %d of layer %s", i, id) + end + end + for i = 1, ref.output_len do + if ref.outputs[i] == nil then + nerv.error("dangling output port %d of layer %s", i, id) + end + end + -- initialize sub layers + ref.layer:init(batch_size) + end + for i = 1, #self.dim_in do + if self.inputs[i] == nil then + nerv.error("dangling port %d of layer ", i) + end + end + for i = 1, #self.dim_out do + if self.outputs[i] == nil then + nerv.error("dangling port %d of layer ", i) + end + end +end + +function DAGLayer:batch_resize(batch_size) + self.gconf.batch_size = batch_size + + for i, conn in ipairs(self.parsed_conn) do + local _, output_dim + local ref_from, port_from, ref_to, port_to + ref_from, port_from = unpack(conn[1]) + ref_to, port_to = unpack(conn[2]) + _, output_dim = ref_from.layer:get_dim() + + if ref_from.outputs[port_from]:nrow() ~= batch_size and output_dim[port_from] > 0 then + local mid = self.gconf.cumat_type(batch_size, output_dim[port_from]) + local err_mid = mid:create() + + ref_from.outputs[port_from] = mid + ref_to.inputs[port_to] = mid + + ref_from.err_inputs[port_from] = err_mid + ref_to.err_outputs[port_to] = err_mid + end + end + for id, ref in pairs(self.layers) do + ref.layer:batch_resize(batch_size) + end + collectgarbage("collect") +end + +function DAGLayer:set_inputs(input) + for i = 1, #self.dim_in do + if input[i] == nil then + nerv.error("some input is not provided"); + end + local layer = self.inputs[i][1] + local port = self.inputs[i][2] + layer.inputs[port] = input[i] + end +end + +function DAGLayer:set_outputs(output) + for i = 1, #self.dim_out do + if output[i] == nil then + nerv.error("some output is not provided"); + end + local layer = self.outputs[i][1] + local port = self.outputs[i][2] + layer.outputs[port] = output[i] + end +end + +function DAGLayer:set_err_inputs(bp_err) + for i = 1, #self.dim_out do + local layer = self.outputs[i][1] + local port = self.outputs[i][2] + layer.err_inputs[port] = bp_err[i] + end +end + +function DAGLayer:set_err_outputs(next_bp_err) + for i = 1, #self.dim_in do + local layer = self.inputs[i][1] + local port = self.inputs[i][2] + layer.err_outputs[port] = next_bp_err[i] + end +end + +function DAGLayer:update(bp_err, input, output) + self:set_err_inputs(bp_err) + self:set_inputs(input) + self:set_outputs(output) + -- print("update") + for id, ref in pairs(self.queue) do + -- print(ref.layer.id) + ref.layer:update(ref.err_inputs, ref.inputs, ref.outputs) + end +end + +function DAGLayer:propagate(input, output) + self:set_inputs(input) + self:set_outputs(output) + local ret = false + for i = 1, #self.queue do + local ref = self.queue[i] + -- print(ref.layer.id) + ret = ref.layer:propagate(ref.inputs, ref.outputs) + end + return ret +end + +function DAGLayer:back_propagate(bp_err, next_bp_err, input, output) + self:set_err_outputs(next_bp_err) + self:set_err_inputs(bp_err) + self:set_inputs(input) + self:set_outputs(output) + for i = #self.queue, 1, -1 do + local ref = self.queue[i] + -- print(ref.layer.id) + ref.layer:back_propagate(ref.err_inputs, ref.err_outputs, ref.inputs, ref.outputs) + end +end + +function DAGLayer:get_params() + local param_repos = {} + for id, ref in pairs(self.queue) do + table.insert(param_repos, ref.layer:get_params()) + end + return nerv.ParamRepo.merge(param_repos) +end + +DAGLayer.PORT_TYPES = { + INPUT = {}, + OUTPUT = {}, + ERR_INPUT = {}, + ERR_OUTPUT = {} +} + +function DAGLayer:get_intermediate(id, port_type) + if id == "" or id == "" then + nerv.error("an actual real layer id is expected") + end + local layer = self.layers[id] + if layer == nil then + nerv.error("layer id %s not found", id) + end + if port_type == DAGLayer.PORT_TYPES.INPUT then + return layer.inputs + elseif port_type == DAGLayer.PORT_TYPES.OUTPUT then + return layer.outputs + elseif port_type == DAGLayer.PORT_TYPES.ERR_INPUT then + return layer.err_inputs + elseif port_type == DAGLayer.PORT_TYPES.ERR_OUTPUT then + return layer.err_outputs + end + nerv.error("unrecognized port type") +end -- cgit v1.2.3-70-g09d2