def train_embed(data_dir, params, model_name):
# ハイパラ読み込み
embedding_dim = params['embedding_dim']
batch_size = params['batch_size']
lr = params['lr']
weight_decay = params['weight_decay']
#warmup = params['warmup']
warmup = 350
#lr_decay_every = params['lr_decay_every']
lr_decay_every = 2
lr_decay_rate = params['lr_decay_rate']
if model_name == 'SparseTransE':
alpha = params['alpha']
# dataload
dataset = AmazonDataset(data_dir, model_name='TransE')
relation_size = len(set(list(dataset.triplet_df['relation'].values)))
entity_size = len(dataset.entity_list)
if model_name == 'TransE':
model = TransE(int(embedding_dim), relation_size, entity_size).to(device)
elif model_name == 'SparseTransE':
model = SparseTransE(int(embedding_dim), relation_size, entity_size, alpha=alpha).to(device)
iterater = TrainIterater(batch_size=int(batch_size), data_dir=data_dir, model_name=model_name)
#iterater.iterate_epoch(model, lr=lr, epoch=3000, weight_decay=weight_decay, warmup=warmup,
# lr_decay_rate=lr_decay_rate, lr_decay_every=lr_decay_every, eval_every=1e+5)
iterater.iterate_epoch(model, lr=lr, epoch=3000, weight_decay=weight_decay, warmup=warmup,
lr_decay_rate=lr_decay_rate, lr_decay_every=lr_decay_every, eval_every=1e+5,
early_stop=True)
return model
def objective(trial):
start = time.time()
import gc
gc.collect()
data_dir = ['../' + data_path + '/valid1', '../' + data_path + '/valid2']
score_sum = 0
# hyper para
embedding_dim = trial.suggest_discrete_uniform('embedding_dim', 16, 128,
16)
alpha = trial.suggest_loguniform('alpha', 1e-6, 1e-2) #SparseTransEの時だけ
batch_size = trial.suggest_int('batch_size', 128, 512, 128)
lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)
weight_decay = trial.suggest_loguniform('weight_decay', 1e-6, 1e-2)
#warmup = trial.suggest_int('warmup', 100, 500)
warmup = trial.suggest_int('warmup', 10, 100)
#warmup = 350
#lr_decay_every = trial.suggest_int('lr_decay_every', 1, 10)
lr_decay_every = 2
lr_decay_rate = trial.suggest_uniform('lr_decay_rate', 0.5, 1)
for dir_path in data_dir:
# データ読み込み
dataset = AmazonDataset(dir_path, model_name='SparseTransE')
relation_size = len(set(list(dataset.triplet_df['relation'].values)))
entity_size = len(dataset.entity_list)
model = SparseTransE(int(embedding_dim),
relation_size,
entity_size,
alpha=alpha).to(device)
iterater = TrainIterater(batch_size=int(batch_size),
data_dir=dir_path,
model_name='SparseTransE')
score = iterater.iterate_epoch(model,
lr=lr,
epoch=3000,
weight_decay=weight_decay,
warmup=warmup,
lr_decay_rate=lr_decay_rate,
lr_decay_every=lr_decay_every,
eval_every=1e+5,
early_stop=False)
score_sum += score
torch.cuda.empty_cache()
mi, sec = time_since(time.time() - start)
print('{}m{}sec'.format(mi, sec))
return -1 * score_sum / 2
params = load_params()
print(params)
import gc
gc.collect()
# dataload
data_dir = '../' + data_path + '/test/'
dataset = AmazonDataset(data_dir, model_name='SparseTransE')
relation_size = len(set(list(dataset.triplet_df['relation'].values)))
entity_size = len(dataset.entity_list)
embedding_dim = params['embedding_dim']
alpha = params['alpha']
model = SparseTransE(int(embedding_dim),
relation_size,
entity_size,
alpha=alpha).to(device)
batch_size = params['batch_size']
iterater = TrainIterater(batch_size=int(batch_size),
data_dir=data_dir,
model_name=model_name)
lr = params['lr']
weight_decay = params['weight_decay']
warmup = 350
lr_decay_every = 2
lr_decay_rate = params['lr_decay_rate']
score = iterater.iterate_epoch(model,