def _load_all(src):
model_path = src
src = os.path.dirname(src)
word_v = _load(src + '/word_v.pkl')
pos_v = _load(src + '/pos_v.pkl')
tag_v = _load(src + '/tag_v.pkl')
pos_pp = torch.load(src + '/pos_pp.pkl')['pipeline']
model_args = ConfigSection()
ConfigLoader.load_config('cfg.cfg', {'model': model_args})
model_args['word_vocab_size'] = len(word_v)
model_args['pos_vocab_size'] = len(pos_v)
model_args['num_label'] = len(tag_v)
model = BiaffineParser(**model_args.data)
model.load_state_dict(torch.load(model_path))
return {
'word_v': word_v,
'pos_v': pos_v,
'tag_v': tag_v,
'model': model,
'pos_pp': pos_pp,
}
emb_file_name = "/home/yfshao/workdir/parser-data/word_OOVthr_30_100v.txt"
# emb_file_name = "/home/yfshao/workdir/word_vector/cc.zh.300.vec"
loader = CTBDataLoader()
cfgfile = './cfg.cfg'
processed_datadir = './save'
# Config Loader
train_args = ConfigSection()
test_args = ConfigSection()
model_args = ConfigSection()
optim_args = ConfigSection()
ConfigLoader.load_config(
cfgfile, {
"train": train_args,
"test": test_args,
"model": model_args,
"optim": optim_args
})
print('trainre Args:', train_args.data)
print('test Args:', test_args.data)
print('optim Args:', optim_args.data)
# Pickle Loader
def save_data(dirpath, **kwargs):
import _pickle
if not os.path.exists(dirpath):
os.mkdir(dirpath)
for name, data in kwargs.items():
with open(os.path.join(dirpath, name + '.pkl'), 'wb') as f: