print("Dev file:", dev_file)
print("Test file:", test_file)
print("Char emb:", char_emb)
print("Bichar emb:", bichar_emb)
print("Gaz file:", gaz_file)
if status == 'train':
print("Model saved to:", save_model_dir)
# 立即把stdout缓存内容输出
sys.stdout.flush()
if status == 'train':
data = Data()
data.model_name = model_name
data.HP_gpu = gpu
data.use_bichar = conf_dict['use_bichar']
data.HP_batch_size = conf_dict['HP_batch_size'] # 1
data.HP_iteration = conf_dict['HP_iteration'] # 100
data.HP_lr = conf_dict['HP_lr'] # 0.015
data.HP_lr_decay = conf_dict['HP_lr_decay'] # 0.5
data.HP_hidden_dim = conf_dict['HP_hidden_dim']
data.MAX_SENTENCE_LENGTH = conf_dict['MAX_SENTENCE_LENGTH']
data.HP_lstm_layer = conf_dict['HP_lstm_layer']
data_initialization(data, gaz_file, train_file, dev_file, test_file)
if data.model_name in ['CNN_model', 'LSTM_model']:
data.generate_instance_with_gaz_2(train_file, 'train')
data.generate_instance_with_gaz_2(dev_file, 'dev')
data.generate_instance_with_gaz_2(test_file, 'test')
elif data.model_name in ['WC-LSTM_model']:
data.generate_instance_with_gaz_3(train_file, 'train')
data.generate_instance_with_gaz_3(dev_file, 'dev')
data.test_dir = args.test
data.model_dir = args.savemodel
data.dset_dir = args.savedset
print("aaa", data.dset_dir)
status = args.status.lower()
save_model_dir = args.savemodel
data.HP_gpu = torch.cuda.is_available()
print("Seed num:", seed_num)
data.number_normalized = True
data.word_emb_dir = "../data/glove.6B.100d.txt"
if status == 'train':
print("MODEL: train")
data_initialization(data)
data.use_char = True
data.HP_batch_size = 10
data.HP_lr = 0.015
data.char_seq_feature = "CNN"
data.generate_instance('train')
data.generate_instance('dev')
data.generate_instance('test')
data.build_pretrain_emb()
train(data)
elif status == 'decode':
print("MODEL: decode")
data.load(data.dset_dir)
data.raw_dir = args.raw
data.decode_dir = args.output
data.load_model_dir = args.loadmodel
data.show_data_summary()
data.generate_instance('raw')
print ("Train file:", train_file)
print ("Dev file:", dev_file)
print ("Test file:", test_file)
print ("Raw file:", raw_file)
print ("Char emb:", char_emb)
print ("Bichar emb:", bichar_emb)
print ("Gaz file:",gaz_file)
if status == 'train':
print ("Model saved to:", save_model_dir)
sys.stdout.flush()
if status == 'train':
data = Data()
data.HP_gpu = gpu
data.HP_use_char = False
data.HP_batch_size = 10
data.use_bigram = False
data.gaz_dropout = 0.5
data.norm_gaz_emb = False
data.HP_fix_gaz_emb = False
data_initialization(data, gaz_file, train_file, dev_file, test_file)
data.generate_instance_with_gaz(train_file,'train')
data.generate_instance_with_gaz(dev_file,'dev')
data.generate_instance_with_gaz(test_file,'test')
data.build_word_pretrain_emb(char_emb)
data.build_biword_pretrain_emb(bichar_emb)
data.build_gaz_pretrain_emb(gaz_file)
train(data, save_model_dir,dset_dir, seg)
elif status == 'test':
def main():
parser = argparse.ArgumentParser(description='Tuning with NCRF++')
# parser.add_argument('--status', choices=['train', 'decode'], help='update algorithm', default='train')
parser.add_argument('--config', help='Configuration File', default='None')
parser.add_argument('--wordemb',
help='Embedding for words',
default='None')
parser.add_argument('--charemb',
help='Embedding for chars',
default='None')
parser.add_argument('--status',
choices=['train', 'decode'],
help='update algorithm',
default='train')
parser.add_argument('--savemodel',
default="data/model/saved_model.lstmcrf.")
parser.add_argument('--savedset', help='Dir of saved data setting')
parser.add_argument('--train', default="data/conll03/train.bmes")
parser.add_argument('--dev', default="data/conll03/dev.bmes")
parser.add_argument('--test', default="data/conll03/test.bmes")
parser.add_argument('--seg', default="True")
parser.add_argument('--random-seed', type=int, default=42)
parser.add_argument('--lr', type=float)
parser.add_argument('--batch-size', type=int)
parser.add_argument('--raw')
parser.add_argument('--loadmodel')
parser.add_argument('--output')
parser.add_argument('--output-tsv')
parser.add_argument('--model-prefix')
parser.add_argument('--cpu', action='store_true')
args = parser.parse_args()
# Set random seed
seed_num = args.random_seed
random.seed(seed_num)
torch.manual_seed(seed_num)
np.random.seed(seed_num)
data = Data()
data.random_seed = seed_num
data.HP_gpu = torch.cuda.is_available()
if args.config == 'None':
data.train_dir = args.train
data.dev_dir = args.dev
data.test_dir = args.test
data.model_dir = args.savemodel
data.dset_dir = args.savedset
print("Save dset directory:", data.dset_dir)
save_model_dir = args.savemodel
data.word_emb_dir = args.wordemb
data.char_emb_dir = args.charemb
if args.seg.lower() == 'true':
data.seg = True
else:
data.seg = False
print("Seed num:", seed_num)
else:
data.read_config(args.config)
if args.lr:
data.HP_lr = args.lr
if args.batch_size:
data.HP_batch_size = args.batch_size
data.output_tsv_path = args.output_tsv
if args.cpu:
data.HP_gpu = False
if args.model_prefix:
data.model_dir = args.model_prefix
# data.show_data_summary()
status = data.status.lower()
print("Seed num:", seed_num)
if status == 'train':
print("MODEL: train")
data_initialization(data)
data.generate_instance('train')
data.generate_instance('dev')
data.generate_instance('test')
data.build_pretrain_emb()
train(data)
elif status == 'decode':
print("MODEL: decode")
data.load(data.dset_dir)
data.read_config(args.config)
print(data.raw_dir)
# exit(0)
data.show_data_summary()
data.generate_instance('raw')
print("nbest: %s" % (data.nbest))
decode_results, pred_scores = load_model_decode(data, 'raw')
if data.nbest and not data.sentence_classification:
data.write_nbest_decoded_results(decode_results, pred_scores,
'raw')
else:
data.write_decoded_results(decode_results, 'raw')
else:
print(
"Invalid argument! Please use valid arguments! (train/test/decode)"
)
emb_file = "../data/joint4.all.b10c1.2h.iter17.mchar" ### catner
else:
emb_file = None
char_emb_file = args.charemb.lower()
print "Char Embedding:", char_emb_file
if char_emb_file == "rich":
char_emb_file = "../data/joint4.all.b10c1.2h.iter17.mchar" ### catner
elif char_emb_file == "normal":
char_emb_file = "../data/gigaword_chn.all.a2b.uni.ite50.vec" ### catner
data = Data()
data.number_normalized = True
data_initialization(data, train_file, dev_file, test_file)
data.HP_gpu = gpu
data.HP_use_char = True
data.HP_batch_size = 10 ## catner
data.HP_lr = 0.015
# data.char_features = "CNN"
data.generate_instance(train_file,'train')
data.generate_instance(dev_file,'dev')
data.generate_instance(test_file,'test')
if emb_file:
print "load word emb file... norm:", data.norm_word_emb
data.build_word_pretrain_emb(emb_file)
if char_emb_file != "none":
print "load char emb file... norm:", data.norm_char_emb
data.build_char_pretrain_emb(char_emb_file)
train(data, save_model_dir, seg)
elif status == 'test':
data = load_data_setting(dset_dir)
data.generate_instance(dev_file,'dev')
data = pickle.load(fp)
data.HP_num_layer = args.num_layer
data.HP_batch_size = args.batch_size
data.HP_iteration = args.num_iter
data.label_comment = args.labelcomment
data.result_file = args.resultfile
data.HP_lr = args.lr
data.use_bigram = args.use_biword
data.HP_hidden_dim = args.hidden_dim
data.HP_use_posi = args.use_posi
data.HP_rethink_iter = args.rethink_iter
else:
data = Data()
data.HP_gpu = gpu
data.HP_batch_size = args.batch_size
data.HP_num_layer = args.num_layer
data.HP_iteration = args.num_iter
data.use_bigram = args.use_biword
data.gaz_dropout = 0.5
data.norm_gaz_emb = False
data.HP_fix_gaz_emb = False
data.label_comment = args.labelcomment
data.result_file = args.resultfile
data.HP_lr = args.lr
data.HP_hidden_dim = args.hidden_dim
data.HP_use_posi = args.use_posi
data.HP_rethink_iter = args.rethink_iter
data_initialization(data, gaz_file, train_file, dev_file,
test_file)
data.generate_instance_with_gaz(train_file, 'train')
# -*- coding: utf-8 -*- # @Author: Jie # @Date: 2017-06-15 14:11:08 # @Last Modified by: Jie Yang, Contact: [email protected] # @Last Modified time: 2018-07-06 11:08:27 import time import sys import argparse import random import copy import torch import gc import pickle as pickle import torch.autograd as autograd import torch.nn as nn import torch.nn.functional as F import torch.optim as optim import numpy as np from utils.metric import get_ner_fmeasure from model.bilstmcrf import BiLSTM_CRF as SeqModel from utils.data import Data seed_num = 100 random.seed(seed_num) torch.manual_seed(seed_num) np.random.seed(seed_num) def data_initialization(data, gaz_file, train_file, dev_file, test_file): data.build_alphabet(train_file) data.build_alphabet(dev_file) data.build_alphabet(test_file)
