print ("Seg: ", seg)
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)
print "Seg: ", seg
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 = 1
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, seg)
elif status == 'test':
data = load_data_setting(dset_dir)
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_use_char = args.use_char
data.HP_hidden_dim = args.hidden_dim
data.HP_dropout = args.drop
data.HP_use_count = args.use_count
data.model_type = args.model_type
data.use_bert = args.use_bert
else:
data = Data()
data.HP_gpu = gpu
data.HP_use_char = args.use_char
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.HP_dropout = args.drop
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_count = args.use_count
data.model_type = args.model_type
data.use_bert = args.use_bert
data_initialization(data, gaz_file, train_file, dev_file,
# emb_file = "../data/gigaword_chn.all.a2b.uni.ite50.vec"
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)
# -*- 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)
