self.ends: list
self.labels: list
"""
def __init__(self, words, starts, ends, labels):
self.words = words
self.starts = starts
self.ends = ends
self.labels = labels
self.predict_labels = []
if __name__ == '__main__':
# parameters
config_file = 'default.ini'
config = Configurable(config_file)
# model
model = CompanyPredict()
# load data
train_data = read_pkl(config.train_pkl)
dev_data = None
if config.para_dev_file:
dev_data = read_pkl(config.dev_pkl)
test_data = read_pkl(config.test_pkl)
word_list = read_pkl(config.load_feature_voc)
p_label_list, s_label_list = read_pkl(config.load_label_voc)
word_voc = VocabSrc(word_list)
p_label_voc = VocabTgt(p_label_list)
s_label_voc = VocabTgt(s_label_list)
help=
'The maximum total input sequence length after WordPiece tokenization.'
)
parse.add_argument(
'-warmup_proportion',
type=float,
default=0.1,
help='Proportion of training to perform linear learning rate warmup for '
'E.g., 0.1 = 10% of training.')
parse.add_argument('-do_lower_case',
type=bool,
default=True,
help='Whether to lower case the input text.')
args, extra_args = parse.parse_known_args()
config = Configurable(args.config_file, extra_args)
bert_config = modeling.BertConfig.from_json_file(args.bert_config_file)
if args.max_seq_length > bert_config.max_position_embeddings:
raise ValueError(
"Cannot use sequence length %d because the BERT model "
"was only trained up to sequence length %d" %
(args.max_seq_length, bert_config.max_position_embeddings))
tokenizer = tokenization.FullTokenizer(vocab_file=args.vocab_file,
do_lower_case=args.do_lower_case)
if config.decode:
path = './data/test.txt'
dev_data, sentence_length = dataLoader.decoder_sentence(path)
with open(config.save_dirs + '/' + config.word_path, 'rb') as f:
# 'gateNoDilateRicherContextRefine',
# 'gateDilateNoRicherContextRefine',
'noneofall',
# 'gatedilatericherRefine',
'dilate',
'gatedilate',
# 'gatedilateNoricherNoSkipRefine',
'gatedilatericher',
# 'gateDilateNoRicherNoSkipRefineContext'
])
argparser.add_argument('--dis',
type=str,
default='none',
choices=[
'Kumar_discriminator', 'Dakai_discriminator',
'PatchGANDiscriminator', 'PatchGAN'
])
argparser.add_argument('--split', type=str, default='0.6')
argparser.add_argument('--batch-size', type=str, default='4')
args, extra_args = argparser.parse_known_args()
config = Configurable(args, extra_args)
torch.set_num_threads((config.workers + 1) * len(config.gpu_count))
config.train = args.train
config.use_cuda = False
if gpu and args.use_cuda: config.use_cuda = True
print("\nGPU using status: ", config.use_cuda)
main(config)
numpy.random.seed(666)
# gpu
gpu = torch.cuda.is_available()
print("GPU available: ", gpu)
print("CuDNN: ", torch.backends.cudnn.enabled)
# parameters
parse = argparse.ArgumentParser('Attention Target Classifier')
parse.add_argument('--config_file', type=str, default='default.ini')
parse.add_argument('--thread', type=int, default=1)
parse.add_argument('--use_cuda', action='store_true', default=False)
parse.add_argument('--model', type=str, default='model.742')
args, extra_args = parse.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)
# load vocab and model
feature_list = read_pkl(config.load_feature_voc)
label_list = read_pkl(config.load_label_voc)
feature_vec = VocabSrc(feature_list)
label_vec = VocabTgt(label_list)
# model
if config.which_model == 'Vanilla':
model = Vanilla(config, feature_vec.size, config.embed_dim, PAD,
del optimizer
empty_cache()
return {'train/seg_acc': results.avg[0]}
if __name__ == '__main__':
torch.manual_seed(6666)
torch.cuda.manual_seed(6666)
random.seed(6666)
np.random.seed(6666)
gpu = torch.cuda.is_available()
print("GPU available: ", gpu)
torch.backends.cudnn.benchmark = True # cudn
print("CuDNN: \n", torch.backends.cudnn.enabled)
argparser = argparse.ArgumentParser()
argparser.add_argument('--config_file', default='da_seg_configuration.txt')
argparser.add_argument('--use-cuda', action='store_true', default=True)
argparser.add_argument('--train', help='test not need write', default=True)
args, extra_args = argparser.parse_known_args()
config = Configurable(args.config_file, extra_args, isTrain=args.train)
torch.set_num_threads(config.workers + 1)
config.train = args.train
config.use_cuda = False
if gpu and args.use_cuda: config.use_cuda = True
print("\nGPU using status: ", config.use_cuda)
main(config)
