pickle.dump(vocab, open(config.save_vocab_path, 'wb'))
pickle.dump(char_vocab, open(config.save_char_vocab_path, 'wb'))
args, extra_args = argparser.parse_known_args()
config = Configurable(args.config_file, extra_args)
torch.set_num_threads(args.thread)
config.use_cuda = False
if gpu and args.use_cuda: config.use_cuda = True
print("\nGPU using status: ", config.use_cuda)
# print(config.use_cuda)
model = ParserModel(vocab, config, vec)
classifier_model = ClassifierModel(config)
char_emb_model = CharEmbModel(char_vocab, config)
if args.use_pretrain:
model.load_state_dict(torch.load(config.load_model_path))
classifier_model.load_state_dict(
torch.load(config.load_classifier_model_path))
char_emb_model.load_state_dict(torch.load(config.load_char_model_path))
print("###Load pretrain parser ok.###")
if config.use_cuda:
torch.backends.cudnn.enabled = True
model = model.cuda()
classifier_model = classifier_model.cuda()
char_emb_model = char_emb_model.cuda()
print(model)
config = Configurable(args.config_file, extra_args)
torch.set_num_threads(args.thread)
config.use_cuda = False
if gpu and args.use_cuda: config.use_cuda = True
print("\nGPU using status: ", config.use_cuda)
# print(config.use_cuda)
model = ParserModel(vocab, config, vec)
if args.use_pretrain:
model.load_state_dict(torch.load(config.load_model_path))
print("###Load pretrain parser ok.###")
classifier_model = ClassifierModel(config)
char_emb_model = CharEmbModel(char_vocab, config)
if config.use_cuda:
torch.backends.cudnn.enabled = True
model = model.cuda()
classifier_model = classifier_model.cuda()
char_emb_model = char_emb_model.cuda()
print(model)
print(classifier_model)
print(char_emb_model)
parser = BiaffineParser(model, vocab.ROOT)
classifier = DomainClassifier(classifier_model)
charEmbedding = CharEmb(char_emb_model)
data = read_corpus(config.train_file, vocab)