if __name__ == '__main__':
EP = 100
SAVING_DIR = '../models/'
tokenizer = BertTokenizer.from_pretrained(
'/home/zydq/.torch/models/bert/chinese-bert_chinese_wwm_pytorch',
do_lower_case=True)
train_loader, val_loader = get_data_loaders(
rv_path='../data/TRAIN/Train_reviews.csv',
lb_path='../data/TRAIN/Train_labels.csv',
tokenizer=tokenizer,
batch_size=12,
val_split=0.15)
model = OpinioNet.from_pretrained(
'/home/zydq/.torch/models/bert/chinese-bert_chinese_wwm_pytorch')
model.cuda()
optimizer = Adam(model.parameters(), lr=5e-6)
scheduler = GradualWarmupScheduler(optimizer, total_epoch=2)
best_val_f1 = 0
best_val_loss = float('inf')
for e in range(EP):
print('Epoch [%d/%d] train:' % (e, EP))
train_loss, train_f1, train_pr, train_rc = train_epoch(
model, train_loader, optimizer, scheduler)
print("loss %.5f, f1 %.5f, pr %.5f, rc %.5f" %
(train_loss, train_f1, train_pr, train_rc))
print('Epoch [%d/%d] eval:' % (e, EP))
val_loss, val_f1, val_pr, val_rc = eval_epoch(model, val_loader)
tokenizer = BertTokenizer.from_pretrained(model_config['path'],
do_lower_case=True)
cv_loaders = get_data_loaders_cv(
rv_path='../data/TRAIN/Train_laptop_reviews.csv',
lb_path='../data/TRAIN/Train_laptop_labels.csv',
tokenizer=tokenizer,
batch_size=args.bs,
type='laptop',
folds=FOLDS)
BEST_THRESHS = [0.1] * FOLDS
BEST_F1 = [0] * FOLDS
for cv_idx, (train_loader, val_loader) in enumerate(cv_loaders):
model = OpinioNet.from_pretrained(model_config['path'],
version=model_config['version'],
focal=model_config['focal'])
model.load_state_dict(
torch.load('../models/pretrained_' + model_config['name']))
model.cuda()
optimizer = Adam(model.parameters(), lr=model_config['lr'])
scheduler = GradualWarmupScheduler(optimizer,
total_epoch=10 * len(train_loader))
best_val_f1 = 0
best_val_loss = float('inf')
for e in range(EP):
print('Epoch [%d/%d] train:' % (e, EP))
train_loss, train_f1, train_pr, train_rc = train_epoch(
model, train_loader, optimizer, scheduler, type='laptop')
return total_loss, total_f1, total_pr, total_rc
if __name__ == '__main__':
EP = 100
SAVING_DIR = '../models/'
tokenizer = BertTokenizer.from_pretrained('/home/zydq/.torch/models/bert/chinese_roberta_wwm_ext_L-12_H-768_A-12',
do_lower_case=True)
# tokenizer = BertTokenizer.from_pretrained('/home/zydq/.tf/bert/chinese_roberta_wwm_ext_L-12_H-768_A-12',
# do_lower_case=True)
makeup_train_loader, makeup_val_loader, laptop_train_loader, laptop_val_loader, corpus_loader = \
get_data_loaders_round2(tokenizer, batch_size=12)
model = OpinioNet.from_pretrained('/home/zydq/.torch/models/bert/chinese_roberta_wwm_ext_L-12_H-768_A-12')
# model = OpinioNet.from_pretrained('/home/zydq/.tf/bert/chinese_roberta_wwm_ext_L-12_H-768_A-12', from_tf=True)
model.cuda()
optimizer = Adam(model.parameters(), lr=6e-6)
scheduler = GradualWarmupScheduler(optimizer, total_epoch=2*max(len(makeup_train_loader), len(corpus_loader)))
best_val_f1 = 0
best_val_loss = float('inf')
for e in range(EP):
print('Epoch [%d/%d] train:' % (e, EP))
train_loss, train_lm_loss, train_f1, train_pr, train_rc = train_epoch(model, makeup_train_loader, laptop_train_loader, corpus_loader, optimizer, scheduler)
print("loss %.5f, lm loss %.5f f1 %.5f, pr %.5f, rc %.5f" % (train_loss, train_lm_loss, train_f1, train_pr, train_rc))
print('Epoch [%d/%d] makeup eval:' % (e, EP))
val_loss, val_f1, val_pr, val_rc = eval_epoch(model, makeup_val_loader, type='makeup')
print("makeup_val: loss %.5f, f1 %.5f, pr %.5f, rc %.5f" % (val_loss, val_f1, val_pr, val_rc))