def load(path, model_class, suffix=''):
with io.open(path + '.config', 'r', encoding='utf8') as f:
config = json.load(f)
word_voca = Vocabulary()
word_voca.__dict__ = config['word_voca']
config['word_voca'] = word_voca
entity_voca = Vocabulary()
entity_voca.__dict__ = config['entity_voca']
config['entity_voca'] = entity_voca
if 'snd_word_voca' in config:
snd_word_voca = Vocabulary()
snd_word_voca.__dict__ = config['snd_word_voca']
config['snd_word_voca'] = snd_word_voca
model = model_class(config)
model.load_state_dict(torch.load(path + '.state_dict' + suffix, map_location=torch.device('cpu')))
return model
def load_voca_embs(voca_path, embs_path):
voca = Vocabulary.load(voca_path)
embs = np.load(embs_path)
# check if sizes are matched
if embs.shape[0] == voca.size() - 1:
print(embs.shape)
unk_emb = np.mean(embs, axis=0, keepdims=True)
embs = np.append(embs, unk_emb, axis=0)
elif embs.shape[0] != voca.size():
print(embs.shape, voca.size())
raise Exception("embeddings and vocabulary have differnt number of items ")
return voca, embs
def read_ent2id(ent_dic_path):
print('load ent dic from', ent_dic_path)
ent_dic = Vocabulary.load(ent_dic_path)
ent2id = ent_dic.word2id
return ent2id
import sys
from nel.vocabulary import Vocabulary
import nel.utils as utils
import numpy as np
if __name__ == "__main__":
core_voca_path = sys.argv[1]
word_embs_dir = sys.argv[2]
print('load core voca from', core_voca_path)
core_voca = Vocabulary.load(core_voca_path)
print('load full voca and embs')
full_voca, full_embs = utils.load_voca_embs(
word_embs_dir + '/all_dict.word',
word_embs_dir + '/all_word_embeddings.npy')
print('select word ids')
selected = []
for word in core_voca.id2word:
word_id = full_voca.word2id.get(word, -1)
if word_id >= 0:
selected.append(word_id)
print('save...')
selected_embs = full_embs[selected, :]
np.save(word_embs_dir + '/word_embeddings', selected_embs)
with open(word_embs_dir + '/dict.word', 'w', encoding='utf8') as f:
for i in selected:
f.write(full_voca.id2word[i] + '\t1000\n')