def main():
"""Main function that trains and/or evaluates a model."""
params = interpret_args()
# Prepare the dataset into the proper form.
data = atis_data.ATISDataset(params)
params.num_db = len(data.db2id)
# Construct the model object.
if params.interaction_level:
model_type = SchemaInteractionATISModel
else:
print('not implemented')
exit()
model = model_type(
params,
data.input_vocabulary,
data.output_vocabulary,
data.output_vocabulary_schema,
data.anonymizer if params.anonymize and params.anonymization_scoring else None)
model = model.cuda()
print('=====================Model Parameters=====================')
for name, param in model.named_parameters():
print(name, param.requires_grad, param.is_cuda, param.size())
assert param.is_cuda
model.build_optim()
print('=====================Parameters in Optimizer==============')
for param_group in model.trainer.param_groups:
print(param_group.keys())
for param in param_group['params']:
print(param.size())
if params.fine_tune_bert:
print('=====================Parameters in BERT Optimizer==============')
for param_group in model.bert_trainer.param_groups:
print(param_group.keys())
for param in param_group['params']:
print(param.size())
sys.stdout.flush()
last_save_file = ""
if params.train:
last_save_file = train(model, data, params)
if params.evaluate and 'valid' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='valid')
if params.evaluate and 'dev' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='dev')
if params.evaluate and 'test' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='test')
def main():
f = open('first.txt', 'r', encoding='utf-8')
all_pre = []
sourceInLine = f.readlines()
for line in sourceInLine:
temp1 = line.strip('\n')
all_pre.append(temp1.split())
"""Main function that trains and/or evaluates a model."""
params = interpret_args()
# Prepare the dataset into the proper form.
data = atis_data.ATISDataset(params)
# Construct the model object.
if params.interaction_level:
model_type = SchemaInteractionATISModel
else:
print('not implemented')
exit()
model = model_type(
params, data.input_vocabulary, data.output_vocabulary,
data.output_vocabulary_schema, data.anonymizer
if params.anonymize and params.anonymization_scoring else None)
model = model.cuda()
print('=====================Model Parameters=====================')
for name, param in model.named_parameters():
print(name, param.requires_grad, param.is_cuda, param.size())
assert param.is_cuda
model.build_optim()
print('=====================Parameters in Optimizer==============')
for param_group in model.trainer.param_groups:
print(param_group.keys())
for param in param_group['params']:
print(param.size())
sys.stdout.flush()
last_save_file = ""
if params.train:
last_save_file = train(all_pre, model, data, params)
if params.evaluate and 'valid' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='valid')
if params.evaluate and 'dev' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='dev')
if params.evaluate and 'test' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='test')
def __init__(self, db_info_path, max_gen_len=1000):
self.history = [] # (utterance, sql query)
# Construct the model
# TODO: see if data object is necessary
# TODO: what if vocab needs to be updated based on db_info?
conf = Configs()
data = atis_data.ATISDataset(conf)
self.model = OnlineModel(
conf, data.input_vocabulary, data.output_vocabulary,
data.output_vocabulary_schema, data.anonymizer
if conf.anonymize and conf.anonymization_scoring else None)
self.model.load(MODEL_LOC)
self.max_gen_len = max_gen_len
database_schema, _, _ = read_database_schema(db_info_path)
self.input_schema = Schema(next(iter(database_schema.values())))
print('DB Info is loaded')
print('DB Meta data is blah')
def main():
"""Main function that trains and/or evaluates a model."""
params = interpret_args()
init_env(params)
# Prepare the dataset into the proper form.
data = atis_data.ATISDataset(params)
# Construct the model object.
if params.interaction_level:
model_type = SchemaInteractionATISModel
else:
print('not implemented')
exit()
model = model_type(
params,
data.input_vocabulary,
data.output_vocabulary,
data.output_vocabulary_schema,
data.anonymizer if params.anonymize and params.anonymization_scoring else None)
model = model.cuda()
model.build_optim()
sys.stdout.flush()
last_save_file = ""
if params.train:
last_save_file = train(model, data, params)
if params.evaluate and 'train' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='train')
if params.evaluate and 'valid' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='valid')
if params.evaluate and 'dev' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='dev')
if params.evaluate and 'test' in params.evaluate_split:
evaluate(model, data, params, last_save_file, split='test')
use_predicted_queries=params.use_predicted_queries,
max_generation_length=params.eval_maximum_sql_length,
write_results=True,
use_gpu=True,
compute_metrics=params.compute_metrics,
step=step,
first=first)
if __name__ == '__main__':
if os.path.exists('logs_sparc_pg_gsql/args.log'):
os.remove('logs_sparc_pg_gsql/args.log')
"""Main function that trains and/or evaluates a model."""
params = interpret_args()
data = atis_data.ATISDataset(params)
# Construct the model object.
if params.interaction_level:
model_type = SchemaInteractionATISModel
else:
print('not implemented')
exit()
if params.use_query_attention == 1:
params.use_query_attention = 1
model = model_type(
params, data.input_vocabulary, data.output_vocabulary,
data.output_vocabulary_schema, data.anonymizer
if params.anonymize and params.anonymization_scoring else None)
model = model.cuda()
evaluate(model,
def main():
"""Main function that trains and/or evaluates a model."""
params = interpret_args()
if params.gan:
assert params.max_gen_len == params.train_maximum_sql_length \
== params.eval_maximum_sql_length
data = atis_data.ATISDataset(params)
generator = SchemaInteractionATISModel(params, data.input_vocabulary,
data.output_vocabulary,
data.output_vocabulary_schema,
None)
generator = generator.cuda()
generator.build_optim()
if params.gen_from_ckp:
gen_ckp_path = os.path.join(params.logdir, params.gen_pretrain_ckp)
if params.fine_tune_bert:
gen_epoch, generator, generator.trainer, \
generator.bert_trainer = \
load_ckp(
gen_ckp_path,
generator,
generator.trainer,
generator.bert_trainer
)
else:
gen_epoch, generator, generator.trainer, _ = \
load_ckp(
gen_ckp_path,
generator,
generator.trainer
)
else:
gen_epoch = 0
print('====================Model Parameters====================')
print('=======================Generator========================')
for name, param in generator.named_parameters():
print(name, param.requires_grad, param.is_cuda, param.size())
assert param.is_cuda
print('==================Optimizer Parameters==================')
print('=======================Generator========================')
for param_group in generator.trainer.param_groups:
print(param_group.keys())
for param in param_group['params']:
print(param.size())
if params.fine_tune_bert:
print('=========================BERT===========================')
for param_group in generator.bert_trainer.param_groups:
print(param_group.keys())
for param in param_group['params']:
print(param.size())
sys.stdout.flush()
# Pre-train generator with MLE
if params.train:
print('=============== Pre-training generator! ================')
train(generator, data, params, gen_epoch)
print('=========== Pre-training generator complete! ===========')
dis_filter_sizes = [i for i in range(1, params.max_gen_len, 4)]
dis_num_filters = [(100 + i * 10)
for i in range(1, params.max_gen_len, 4)]
discriminator = Discriminator(params, data.dis_src_vocab,
data.dis_tgt_vocab, params.max_gen_len,
params.num_dis_classes, dis_filter_sizes,
dis_num_filters, params.max_pos_emb,
params.num_tok_type, params.dis_dropout)
discriminator = discriminator.cuda()
dis_criterion = nn.NLLLoss(reduction='mean')
dis_criterion = dis_criterion.cuda()
dis_optimizer = optim.Adam(discriminator.parameters())
if params.dis_from_ckp:
dis_ckp_path = os.path.join(params.logdir, params.dis_pretrain_ckp)
dis_epoch, discriminator, dis_optimizer, _ = load_ckp(
dis_ckp_path, discriminator, dis_optimizer)
else:
dis_epoch = 0
print('====================Model Parameters====================')
print('=====================Discriminator======================')
for name, param in discriminator.named_parameters():
print(name, param.requires_grad, param.is_cuda, param.size())
assert param.is_cuda
print('==================Optimizer Parameters==================')
print('=====================Discriminator======================')
for param_group in dis_optimizer.param_groups:
print(param_group.keys())
for param in param_group['params']:
print(param.size())
sys.stdout.flush()
# Pre-train discriminator
if params.pretrain_discriminator:
print('============= Pre-training discriminator! ==============')
pretrain_discriminator(params,
generator,
discriminator,
dis_criterion,
dis_optimizer,
data,
start_epoch=dis_epoch)
print('========= Pre-training discriminator complete! =========')
# Adversarial Training
if params.adversarial_training:
print('================ Adversarial training! =================')
generator.build_optim()
dis_criterion = nn.NLLLoss(reduction='mean')
dis_optimizer = optim.Adam(discriminator.parameters())
dis_criterion = dis_criterion.cuda()
if params.adv_from_ckp and params.mle is not "mixed_mle":
adv_ckp_path = os.path.join(params.logdir, params.adv_ckp)
if params.fine_tune_bert:
epoch, batches, pos_in_batch, generator, discriminator, \
generator.trainer, dis_optimizer, \
generator.bert_trainer, _, _ = \
load_adv_ckp(
adv_ckp_path,
generator,
discriminator,
generator.trainer,
dis_optimizer,
generator.bert_trainer)
else:
epoch, batches, pos_in_batch, generator, discriminator, \
generator.trainer, dis_optimizer, _, _, _ = \
load_adv_ckp(
adv_ckp_path,
generator,
discriminator,
generator.trainer,
dis_optimizer)
adv_train(generator,
discriminator,
dis_criterion,
dis_optimizer,
data,
params,
start_epoch=epoch,
start_batches=batches,
start_pos_in_batch=pos_in_batch)
elif params.adv_from_ckp and params.mle == "mixed_mle":
adv_ckp_path = os.path.join(params.logdir, params.adv_ckp)
if params.fine_tune_bert:
epoch, batches, pos_in_batch, generator, discriminator, \
generator.trainer, dis_optimizer, \
generator.bert_trainer, clamp, length = \
load_adv_ckp(
adv_ckp_path,
generator,
discriminator,
generator.trainer,
dis_optimizer,
generator.bert_trainer,
mle=True)
else:
epoch, batches, pos_in_batch, generator, discriminator, \
generator.trainer, dis_optimizer, _, clamp, length = \
load_adv_ckp(
adv_ckp_path,
generator,
discriminator,
generator.trainer,
dis_optimizer,
mle=True)
mixed_mle(generator,
discriminator,
dis_criterion,
dis_optimizer,
data,
params,
start_epoch=epoch,
start_batches=batches,
start_pos_in_batch=pos_in_batch,
start_clamp=clamp,
start_len=length)
else:
if params.mle == 'mixed_mle':
mixed_mle(generator, discriminator, dis_criterion,
dis_optimizer, data, params)
else:
adv_train(generator, discriminator, dis_criterion,
dis_optimizer, data, params)
if params.evaluate and 'valid' in params.evaluate_split:
print("================== Evaluating! ===================")
evaluate(generator, data, params, split='valid')
print("============= Evaluation finished! ===============")