def main():
# load settings for training
opt = init_opt(description='train.py')
logging = init_logging(logger_name='train.py', log_file=opt.log_file, redirect_to_stdout=False)
logging.info('EXP_PATH : ' + opt.exp_path)
logging.info('Parameters:')
[logging.info('%s : %s' % (k, str(v))) for k, v in opt.__dict__.items()]
logging.info('====================== Checking GPU Availability =========================')
if torch.cuda.is_available():
if isinstance(opt.device_ids, int):
opt.device_ids = [opt.device_ids]
logging.info('Running on %s! devices=%s' % ('MULTIPLE GPUs' if len(opt.device_ids) > 1 else '1 GPU', str(opt.device_ids)))
else:
logging.info('Running on CPU!')
try:
train_data_loader, valid_data_loader, test_data_loader, word2id, id2word, vocab = load_data_vocab(opt)
model = init_model(opt)
optimizer_ml, optimizer_rl, criterion = init_optimizer_criterion(model, opt)
train_model(model, optimizer_ml, optimizer_rl, criterion, train_data_loader, valid_data_loader, test_data_loader, opt)
except Exception as e:
logging.error(e, exc_info=True)
raise
def __init__(self):
super(KeyphrasePredictor, self).__init__()
self.model_opts = config.init_opt(description='predictor')
# self.vocab_path = self.model_opts.vocab#os.path.join(self.model_opts.data, 'kp20k', 'kp20k.vocab.pt')
# parser = argparse.ArgumentParser(description='predictor',formatter_class=argparse.ArgumentDefaultsHelpFormatter)
# config.preprocess_opts(parser)
# self.opt = parser.parse_args([])
self.load()
def main():
opt = config.init_opt(description='predict_keyphrase.py')
logger = config.init_logging('predict_keyphrase',
opt.exp_path + '/output.log',
redirect_to_stdout=False)
logger.info('EXP_PATH : ' + opt.exp_path)
logger.info('Parameters:')
[
logger.info('%s : %s' % (k, str(v)))
for k, v in opt.__dict__.items()
]
logger.info(
'====================== Checking GPU Availability ========================='
)
if torch.cuda.is_available():
if isinstance(opt.device_ids, int):
opt.device_ids = [opt.device_ids]
logger.info('Running on %s! devices=%s' %
('MULTIPLE GPUs' if len(opt.device_ids) > 1 else '1 GPU',
str(opt.device_ids)))
else:
logger.info('Running on CPU!')
try:
one2one, one2many = generate_dataset()
test_data_loaders, word2id, id2word, vocab = load_vocab_and_testsets(
opt, one2one, one2many)
model = init_model(opt)
generator = SequenceGenerator(model,
eos_id=opt.word2id[pykp.io.EOS_WORD],
beam_size=opt.beam_size,
max_sequence_length=opt.max_sent_length)
for testset_name, test_data_loader in zip(['kp20k'],
test_data_loaders):
logger.info('Evaluating %s' % testset_name)
output = predict_beam_search(
generator,
test_data_loader,
opt,
title='test_%s' % testset_name,
predict_save_path=None
) #opt.pred_path + '/%s_test_result/' % (testset_name))
print(output)
except Exception as e:
logger.error(e, exc_info=True)
def main():
# load settings for training
opt = init_opt(description='train.py')
logging = init_logging(logger_name='train.py',
log_file=opt.log_file,
redirect_to_stdout=False)
logging.info('EXP_PATH : ' + opt.exp_path)
logging.info('Parameters:')
[
logging.info('%s : %s' % (k, str(v)))
for k, v in opt.__dict__.items()
]
logging.info(
'====================== Checking GPU Availability ========================='
)
logger.info("torch.cuda.is_available()={}".format(
torch.cuda.is_available()))
if torch.cuda.is_available():
if isinstance(opt.gpuid, int):
opt.gpuid = [opt.gpuid]
logging.info('Running on %s! devices=%s' %
('MULTIPLE GPUs' if len(opt.gpuid) > 1 else '1 GPU',
str(opt.gpuid)))
else:
logging.info('Running on CPU!')
try:
train_data_loader, valid_data_loader, _, _, _, _ = load_data_vocab_for_training(
opt)
# ignore the previous test_data_loader
valid_data_loaders, _, _, _ = load_vocab_and_datasets_for_testing(
dataset_names=opt.test_dataset_names, type='valid', opt=opt)
test_data_loaders, _, _, _ = load_vocab_and_datasets_for_testing(
dataset_names=opt.test_dataset_names, type='test', opt=opt)
model = init_model(opt)
optimizer_ml, optimizer_rl, criterion = init_optimizer_criterion(
model, opt)
train_model(model, optimizer_ml, optimizer_rl, criterion,
train_data_loader, valid_data_loaders, test_data_loaders,
opt)
except Exception as e:
logging.error(e, exc_info=True)
raise
def main():
# load settings for training
opt = init_opt(description='train.py')
opt.useGpu = 1
opt.encoder_type = 'bert'
opt.useCLF = True
opt.data = 'data/kp20k/kp20k'
opt.vocab = 'data/kp20k/kp20k.vocab.pt'
if opt.encoder_type == 'transformer':
opt.batch_size = 32
opt.d_inner = 2048
opt.enc_n_layers = 4
opt.dec_n_layers = 2
opt.n_head = 8
opt.d_k = 64
opt.d_v = 64
opt.d_model = 512
opt.word_vec_size = 512
opt.run_valid_every = 5000000
opt.save_model_every = 20000
opt.decode_old = True
#opt.copy_attention = False
elif opt.encoder_type == 'bert':
opt.useOnlyTwo = False
opt.avgHidden = False
opt.useZeroDecodeHidden = True
opt.useSameEmbeding = False
opt.batch_size = 10
opt.max_sent_length = 10
opt.run_valid_every = 40000
opt.decode_old = False
opt.beam_search_batch_size = 10
opt.bert_model = 'bert-base-uncased'
opt.tokenizer = BertTokenizer.from_pretrained(opt.bert_model)
else:
opt.enc_layers = 2
opt.bidirectional = True
opt.decode_old = True
opt.run_valid_every = 2
opt.onlyTest = False
if opt.onlyTest:
opt.train_ml = False
opt.run_valid_every = 5
opt.beam_size = 64
opt.beam_search_batch_size = 128
#opt.train_from = 'exp/kp20k.ml.copy.20181129-193506/model/kp20k.ml.copy.epoch=1.batch=20000.total_batch=20000.model'
opt.train_from = 'exp/kp20k.ml.copy.20181128-153121/model/kp20k.ml.copy.epoch=2.batch=15495.total_batch=38000.model'
#opt.train_from = 'exp/kp20k.ml.copy.20181117-190121/model/kp20k.ml.copy.epoch=3.batch=14172.total_batch=56000.model'
logging = init_logging(logger_name='train.py',
log_file=opt.log_file,
redirect_to_stdout=False)
logging.info('EXP_PATH : ' + opt.exp_path)
logging.info('Parameters:')
[
logging.info('%s : %s' % (k, str(v)))
for k, v in opt.__dict__.items()
]
logging.info(
'====================== Checking GPU Availability ========================='
)
if torch.cuda.is_available() and opt.useGpu:
if isinstance(opt.gpuid, int):
opt.gpuid = [opt.gpuid]
logging.info('Running on %s! devices=%s' %
('MULTIPLE GPUs' if len(opt.gpuid) > 1 else '1 GPU',
str(opt.gpuid)))
else:
logging.info('Running on CPU!')
try:
train_data_loader, valid_data_loader, test_data_loader, word2id, id2word, vocab = load_data_vocab(
opt)
model = init_model(opt)
if torch.cuda.is_available() and opt.useGpu:
model.cuda()
print("model:")
print(model)
print()
optimizer_ml, optimizer_rl, criterion = init_optimizer_criterion(
model, opt)
if torch.cuda.is_available() and opt.useGpu:
criterion.cuda()
train_model(model, optimizer_ml, optimizer_rl, criterion,
train_data_loader, valid_data_loader, test_data_loader,
opt)
except Exception as e:
logging.error(e, exc_info=True)
raise
def main():
opt = config.init_opt(description='predict.py')
logger = config.init_logging('predict',
opt.exp_path + '/output.log',
redirect_to_stdout=False)
logger.info('EXP_PATH : ' + opt.exp_path)
logger.info('Parameters:')
[
logger.info('%s : %s' % (k, str(v)))
for k, v in opt.__dict__.items()
]
logger.info(
'====================== Checking GPU Availability ========================='
)
if torch.cuda.is_available():
if isinstance(opt.device_ids, int):
opt.device_ids = [opt.device_ids]
logger.info('Running on %s! devices=%s' %
('MULTIPLE GPUs' if len(opt.device_ids) > 1 else '1 GPU',
str(opt.device_ids)))
else:
logger.info('Running on CPU!')
try:
valid_data_loaders, word2id, id2word, vocab = load_vocab_and_datasets_for_testing(
dataset_names=opt.test_dataset_names, type='valid', opt=opt)
test_data_loaders, _, _, _ = load_vocab_and_datasets_for_testing(
dataset_names=opt.test_dataset_names, type='test', opt=opt)
opt.word2id = word2id
opt.id2word = id2word
opt.vocab = vocab
model = init_model(opt)
generator = SequenceGenerator(model,
eos_id=opt.word2id[pykp.io.EOS_WORD],
beam_size=opt.beam_size,
max_sequence_length=opt.max_sent_length)
valid_score_dict = evaluate_multiple_datasets(
generator,
valid_data_loaders,
opt,
title='valid',
predict_save_path=opt.pred_path)
test_score_dict = evaluate_multiple_datasets(
generator,
test_data_loaders,
opt,
title='test',
predict_save_path=opt.pred_path)
# test_data_loaders, word2id, id2word, vocab = load_vocab_and_datasets(opt)
# for testset_name, test_data_loader in zip(opt.test_dataset_names, test_data_loaders):
# logger.info('Evaluating %s' % testset_name)
# evaluate_beam_search(generator, test_data_loader, opt,
# title='test_%s' % testset_name,
# predict_save_path=opt.pred_path + '/%s_test_result/' % (testset_name))
except Exception as e:
logger.error(e, exc_info=True)
def main():
opt = config.init_opt(description='predict.py')
opt.data = 'data3/kp20k/kp20k'
opt.vocab = 'data3/kp20k/kp20k.vocab.pt'
#opt.train_from = 'exp/kp20k.ml.copy.20181129-193506/model/kp20k.ml.copy.epoch=1.batch=20000.total_batch=20000.model'
opt.train_from = 'exp/kp20k.ml.copy.20181128-153121/model/kp20k.ml.copy.epoch=2.batch=15495.total_batch=38000.model'
opt.useGpu = 0
opt.encoder_type = 'rnn'
opt.useCLF = False
if opt.encoder_type.startswith('transformer'):
opt.batch_size = 32
opt.d_inner = 2048
opt.enc_n_layers = 4
opt.dec_n_layers = 2
opt.n_head = 8
opt.d_k = 64
opt.d_v = 64
opt.d_model = 512
opt.word_vec_size = 512
opt.run_valid_every = 5000000
opt.save_model_every = 20000
opt.decode_old = True
# opt.copy_attention = False
elif opt.encoder_type.startswith('bert'):
opt.useOnlyTwo = False
opt.avgHidden = True
opt.useZeroDecodeHidden = False
opt.useSameEmbeding = False
opt.batch_size = 10
opt.max_sent_length = 10
opt.run_valid_every = 20000
opt.decode_old = False
opt.beam_search_batch_size = 10
opt.bert_model = 'bert-base-uncased'
opt.tokenizer = BertTokenizer.from_pretrained(opt.bert_model)
if opt.encoder_type == 'bert_low':
opt.copy_attention = False
else:
opt.enc_layers = 2
opt.bidirectional = True
opt.decode_old = True
logger = config.init_logging('predict',
opt.exp_path + '/output.log',
redirect_to_stdout=False)
logger.info('EXP_PATH : ' + opt.exp_path)
logger.info('Parameters:')
[
logger.info('%s : %s' % (k, str(v)))
for k, v in opt.__dict__.items()
]
logger.info(
'====================== Checking GPU Availability ========================='
)
if torch.cuda.is_available() and opt.useGpu:
if isinstance(opt.gpuid, int):
opt.gpuid = [opt.gpuid]
logger.info('Running on %s! devices=%s' %
('MULTIPLE GPUs' if len(opt.gpuid) > 1 else '1 GPU',
str(opt.gpuid)))
else:
logger.info('Running on CPU!')
try:
test_data_loaders, word2id, id2word, vocab = load_vocab_and_testsets(
opt)
model = init_model(opt)
if torch.cuda.is_available() and opt.useGpu:
model.cuda()
generator = SequenceGenerator(model,
opt.word_vec_size if opt.encoder_type
== 'transformer' else opt.vocab_size,
eos_id=opt.word2id[pykp.io.EOS_WORD],
beam_size=opt.beam_size,
max_sequence_length=opt.max_sent_length,
useGpu=opt.useGpu)
for testset_name, test_data_loader in zip(opt.test_dataset_names,
test_data_loaders):
logger.info('Evaluating %s' % testset_name)
evaluate_beam_search(generator,
test_data_loader,
opt,
title='test_%s' % testset_name,
predict_save_path=opt.pred_path +
'/%s_test_result/' % (testset_name))
except Exception as e:
logger.error(e, exc_info=True)
