diff options
Diffstat (limited to 'nerv/examples/lmptb/lstmlm_ptb_main.lua')
| -rw-r--r-- | nerv/examples/lmptb/lstmlm_ptb_main.lua | 127 |
1 files changed, 94 insertions, 33 deletions
diff --git a/nerv/examples/lmptb/lstmlm_ptb_main.lua b/nerv/examples/lmptb/lstmlm_ptb_main.lua index 681c308..6e3fab9 100644 --- a/nerv/examples/lmptb/lstmlm_ptb_main.lua +++ b/nerv/examples/lmptb/lstmlm_ptb_main.lua @@ -77,10 +77,6 @@ function prepare_layers(global_conf) --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.AffineRecurrentLayer"] = { - -- ["recurrentL1"] = recurrentLconfig, - --}, - ["nerv.LSTMLayerT"] = { ["lstmL1"] = {{}, {["dim_in"] = {global_conf.hidden_size, global_conf.hidden_size, global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size, global_conf.hidden_size}, ["pr"] = pr}}, }, @@ -93,10 +89,6 @@ function prepare_layers(global_conf) ["selectL1"] = {{}, {["dim_in"] = {1}, ["dim_out"] = {global_conf.hidden_size}, ["vocab"] = global_conf.vocab, ["pr"] = pr}}, }, - --["nerv.SigmoidLayer"] = { - -- ["sigmoidL1"] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}}} - --}, - ["nerv.CombinerLayer"] = { ["combinerL1"] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size, global_conf.hidden_size}, ["lambda"] = {1}}}, }, @@ -195,23 +187,26 @@ local set = arg[1] --"test" if (set == "ptb") then -data_dir = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/PTBdata' +root_dir = '/home/slhome/txh18/workspace' +data_dir = root_dir .. '/ptb/DATA' train_fn = data_dir .. '/ptb.train.txt.adds' valid_fn = data_dir .. '/ptb.valid.txt.adds' test_fn = data_dir .. '/ptb.test.txt.adds' vocab_fn = data_dir .. '/vocab' +qdata_dir = root_dir .. '/ptb/questionGen/gen' + global_conf = { - lrate = 0.15, wcost = 1e-5, momentum = 0, clip_t = 2, + lrate = 0.15, wcost = 1e-5, momentum = 0, clip_t = 5, cumat_type = nerv.CuMatrixFloat, mmat_type = nerv.MMatrixFloat, nn_act_default = 0, - hidden_size = 650, - layer_num = 2, + hidden_size = 300, + layer_num = 1, chunk_size = 15, batch_size = 20, - max_iter = 45, + max_iter = 35, lr_decay = 1.003, decay_iter = 10, param_random = function() return (math.random() / 5 - 0.1) end, @@ -221,10 +216,11 @@ global_conf = { valid_fn = valid_fn, test_fn = test_fn, vocab_fn = vocab_fn, + max_sen_len = 90, sche_log_pre = "[SCHEDULER]:", log_w_num = 40000, --give a message when log_w_num words have been processed timer = nerv.Timer(), - work_dir_base = '/home/slhome/txh18/workspace/nerv/play/ptbEXP/tnn_lstm_test' + work_dir_base = '/home/slhome/txh18/workspace/ptb/EXP-nerv/lstmlm_v1.0' } elseif (set == "msr_sc") then @@ -261,12 +257,50 @@ global_conf = { work_dir_base = '/home/slhome/txh18/workspace/sentenceCompletion/EXP-Nerv/rnnlm_test' } +elseif (set == "twitter") then + +root_dir = '/home/slhome/txh18/workspace' +data_dir = root_dir .. '/twitter_new/DATA' +train_fn = data_dir .. '/twitter.choose.adds' +valid_fn = data_dir .. '/twitter.valid.adds' +test_fn = data_dir .. '/comm.test.choose-ppl.adds' +vocab_fn = data_dir .. '/twitter.choose.train.vocab' + +--qdata_dir = root_dir .. '/ptb/questionGen/gen' + +global_conf = { + lrate = 0.15, wcost = 1e-5, momentum = 0, clip_t = 5, + cumat_type = nerv.CuMatrixFloat, + mmat_type = nerv.MMatrixFloat, + nn_act_default = 0, + + hidden_size = 300, + layer_num = 1, + chunk_size = 15, + batch_size = 20, + max_iter = 35, + lr_decay = 1.003, + decay_iter = 10, + param_random = function() return (math.random() / 5 - 0.1) end, + dropout_str = "0", + + train_fn = train_fn, + valid_fn = valid_fn, + test_fn = test_fn, + vocab_fn = vocab_fn, + max_sen_len = 90, + sche_log_pre = "[SCHEDULER]:", + log_w_num = 40000, --give a message when log_w_num words have been processed + timer = nerv.Timer(), + work_dir_base = root_dir .. '/twitter_new/EXP-nerv/lstmlm_v1.0' +} + else -valid_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text' -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' -vocab_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text' +valid_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text-chn' +train_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text-chn' +test_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text-chn' +vocab_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text-chn' global_conf = { lrate = 0.01, wcost = 1e-5, momentum = 0, @@ -285,6 +319,7 @@ global_conf = { train_fn = train_fn, valid_fn = valid_fn, test_fn = test_fn, + max_sen_len = 80, lr_decay = 1.003, decay_iter = 10, vocab_fn = vocab_fn, @@ -296,12 +331,15 @@ global_conf = { end -local lr_half = false --can not be local, to be set by loadstring -local start_iter = -1 -local ppl_last = 100000 -local commands_str = "train:test" -local commands = {} -local test_iter = -1 +lr_half = false --can not be local, to be set by loadstring +start_iter = -1 +start_lr = global_conf.lrate +ppl_last = 100000 +commands_str = "train:test" +commands = {} +test_iter = -1 +--for testout(question) +q_file = "/home/slhome/txh18/workspace/ptb/questionGen/gen/ptb.test.txt.q10rs1_Msss.adds" if arg[2] ~= nil then nerv.printf("%s applying arg[2](%s)...\n", global_conf.sche_log_pre, arg[2]) @@ -311,21 +349,25 @@ else nerv.printf("%s no user setting, all default...\n", global_conf.sche_log_pre) end -global_conf.work_dir = global_conf.work_dir_base .. 'h' .. global_conf.hidden_size .. 'l' .. global_conf.layer_num --.. 'ch' .. global_conf.chunk_size .. 'ba' .. global_conf.batch_size .. 'slr' .. global_conf.lrate .. 'wc' .. global_conf.wcost +global_conf.work_dir = global_conf.work_dir_base .. 'h' .. global_conf.hidden_size .. 'l' .. global_conf.layer_num .. 'ch' .. global_conf.chunk_size .. 'ba' .. global_conf.batch_size .. 'slr' .. global_conf.lrate .. 'wc' .. global_conf.wcost .. 'dr' .. global_conf.dropout_str global_conf.train_fn_shuf = global_conf.work_dir .. '/train_fn_shuf' global_conf.train_fn_shuf_bak = global_conf.train_fn_shuf .. '_bak' global_conf.param_fn = global_conf.work_dir .. "/params" global_conf.dropout_list = nerv.SUtil.parse_schedule(global_conf.dropout_str) -global_conf.log_fn = global_conf.work_dir .. '/lstm_tnn_' .. commands_str .. '_log' +global_conf.log_fn = global_conf.work_dir .. '/log_lstm_tnn_' .. commands_str ..os.date("_TT%m_%d_%X",os.time()) +global_conf.log_fn, _ = string.gsub(global_conf.log_fn, ':', '-') commands = nerv.SUtil.parse_commands_set(commands_str) -nerv.printf("%s creating work_dir...\n", global_conf.sche_log_pre) -nerv.LMUtil.wait(1) +global_conf.lrate = start_lr + +nerv.printf("%s creating work_dir(%s)...\n", global_conf.sche_log_pre, global_conf.work_dir) +nerv.LMUtil.wait(2) os.execute("mkdir -p "..global_conf.work_dir) os.execute("cp " .. global_conf.train_fn .. " " .. global_conf.train_fn_shuf) --redirecting log outputs! nerv.SUtil.log_redirect(global_conf.log_fn) +nerv.LMUtil.wait(2) ----------------printing options--------------------------------- nerv.printf("%s printing global_conf...\n", global_conf.sche_log_pre) @@ -335,11 +377,11 @@ end nerv.LMUtil.wait(2) nerv.printf("%s printing training scheduling options...\n", global_conf.sche_log_pre) -nerv.printf("lr_half:%s\n", tostring(lr_half)) -nerv.printf("start_iter:%s\n", tostring(start_iter)) -nerv.printf("ppl_last:%s\n", tostring(ppl_last)) -nerv.printf("commds_str:%s\n", commands_str) -nerv.printf("test_iter:%s\n", tostring(test_iter)) +nerv.printf("lr_half:\t%s\n", tostring(lr_half)) +nerv.printf("start_iter:\t%s\n", tostring(start_iter)) +nerv.printf("ppl_last:\t%s\n", tostring(ppl_last)) +nerv.printf("commands_str:\t%s\n", commands_str) +nerv.printf("test_iter:\t%s\n", tostring(test_iter)) nerv.printf("%s printing training scheduling end.\n", global_conf.sche_log_pre) nerv.LMUtil.wait(2) ------------------printing options end------------------------------ @@ -441,3 +483,22 @@ if commands["test"] == 1 then global_conf.dropout_rate = 0 LMTrainer.lm_process_file_rnn(global_conf, global_conf.test_fn, tnn, false) --false update! end --if commands["test"] + +if commands["testout"] == 1 then + nerv.printf("===TEST OUT===\n") + nerv.printf("q_file:\t%s\n", q_file) + local q_fn = q_file --qdata_dir .. '/' .. q_file + global_conf.sche_log_pre = "[SCHEDULER TESTOUT]:" + if final_iter ~= -1 and test_iter == -1 then + test_iter = final_iter + end + if test_iter == -1 then + test_iter = "final" + end + tnn = load_net(global_conf, test_iter) + global_conf.dropout_rate = 0 + LMTrainer.lm_process_file_rnn(global_conf, q_fn, tnn, false, + {["one_sen_report"] = true}) --false update! +end --if commands["testout"] + + |