def train(parameters):
# 模型保存的目录 eg: './results/docred-dev/docred_basebert_full/'
model_folder = setup_log(parameters, parameters['save_pred'] + '_train')
set_seed(parameters['seed'])
###################################
# Data Loading
###################################
# if parameters['re_train']:
# print('\nLoading mappings ...')
# train_loader = load_mappings(parameters['remodelfile'])
# else:
print('加载训练数据 ...')
train_loader = DataLoader(parameters['train_data'], parameters)
train_loader(embeds=parameters['embeds'], parameters=parameters)
train_data, _ = DocRelationDataset(train_loader, 'train', parameters,
train_loader).__call__()
print('\nLoading testing data ...')
test_loader = DataLoader(parameters['test_data'], parameters, train_loader)
test_loader(parameters=parameters)
test_data, prune_recall = DocRelationDataset(test_loader, 'test',
parameters,
train_loader).__call__()
# print("prune_recall-->", str(prune_recall))
###################################
# Training
###################################
trainer = Trainer(train_loader, parameters, {
'train': train_data,
'test': test_data
}, model_folder, prune_recall)
trainer.run()
def train(parameters):
model_folder = setup_log(parameters, 'train')
set_seed(parameters['seed'])
###################################
# Data Loading
###################################
print('Loading training data ...')
train_loader = DataLoader(parameters['train_data'], parameters)
train_loader(embeds=parameters['embeds'])
train_data = DocRelationDataset(train_loader, 'train', parameters, train_loader).__call__()
print('\nLoading testing data ...')
test_loader = DataLoader(parameters['test_data'], parameters)
test_loader()
test_data = DocRelationDataset(test_loader, 'test', parameters, train_loader).__call__()
###################################
# Training
###################################
trainer = Trainer(train_loader, parameters, {'train': train_data, 'test': test_data}, model_folder)
trainer.run()
if parameters['plot']:
plot_learning_curve(trainer, model_folder)
if parameters['save_model']:
save_model(model_folder, trainer, train_loader)
def train(parameters):
model_folder = setup_log(parameters, parameters['save_pred'] + '_train')
set_seed(parameters['seed'])
###################################
# Data Loading
###################################
# if parameters['re_train']:
# print('\nLoading mappings ...')
# train_loader = load_mappings(parameters['remodelfile'])
# else:
flag=False
processed_dataset=parameters['remodelfile']
if flag and os.path.exists(os.path.join(processed_dataset, 'train_loader.pkl')):
with open(os.path.join(processed_dataset, 'train_loader.pkl'), 'rb') as f:
train_loader = pkl.load(f)
with open(os.path.join(processed_dataset, 'train_data.pkl'), 'rb') as f:
train_data = pkl.load(f)
with open(os.path.join(processed_dataset, 'test_data.pkl'), 'rb') as f:
test_data = pkl.load(f)
with open(os.path.join(processed_dataset, 'prune_recall.pkl'), 'rb') as f:
prune_recall = pkl.load(f)
# print('Loading training data ...')
else:
train_loader = DataLoader(parameters['train_data'], parameters)
train_loader(embeds=parameters['embeds'], parameters=parameters)
train_data, _ = DocRelationDataset(train_loader, 'train', parameters, train_loader).__call__()
# operate_data(train_data, "train_data.json")
print('\nLoading testing data ...')
test_loader = DataLoader(parameters['test_data'], parameters, train_loader)
test_loader(parameters=parameters)
test_data, prune_recall = DocRelationDataset(test_loader, 'test', parameters, train_loader).__call__()
with open(os.path.join(processed_dataset, 'train_loader.pkl'), 'wb') as f:
pkl.dump(train_loader, f, pkl.HIGHEST_PROTOCOL)
with open(os.path.join(processed_dataset, 'train_data.pkl'), 'wb') as f:
pkl.dump(train_data, f, pkl.HIGHEST_PROTOCOL)
with open(os.path.join(processed_dataset, 'test_data.pkl'), 'wb') as f:
pkl.dump(test_data, f, pkl.HIGHEST_PROTOCOL)
with open(os.path.join(processed_dataset, 'prune_recall.pkl'), 'wb') as f:
pkl.dump(prune_recall, f, pkl.HIGHEST_PROTOCOL)
#
###################################
# Training
###################################
trainer = Trainer(train_loader, parameters, {'train': train_data, 'test': test_data}, model_folder, prune_recall)
trainer.run()
write_metrics(trainer,model_folder)
if parameters['plot']:
plot_learning_curve(trainer, model_folder)
plot_P_R(trainer, model_folder)
def _test(parameters):
model_folder = setup_log(parameters, parameters['save_pred'] + '_test')
print('\nLoading mappings ...')
train_loader = load_mappings(parameters['remodelfile'])
flag=True
print('\nLoading testing data ...')
processed_dataset=parameters['remodelfile']
if flag and os.path.exists(os.path.join(processed_dataset, 'test_test_data.pkl')):
with open(os.path.join(processed_dataset, 'test_test_data.pkl'), 'rb') as f:
test_data = pkl.load(f)
with open(os.path.join(processed_dataset, 'test_prune_recall.pkl'), 'rb') as f:
prune_recall = pkl.load(f)
else:
test_loader = DataLoader(parameters['test_data'], parameters, train_loader)
test_loader(parameters=parameters)
test_data, prune_recall = DocRelationDataset(test_loader, 'test', parameters, train_loader).__call__()
with open(os.path.join(processed_dataset, 'test_test_data.pkl'), 'wb') as f:
pkl.dump(test_data, f, pkl.HIGHEST_PROTOCOL)
with open(os.path.join(processed_dataset, 'test_prune_recall.pkl'), 'wb') as f:
pkl.dump(prune_recall, f, pkl.HIGHEST_PROTOCOL)
m = Trainer(train_loader, parameters, {'train': [], 'test': test_data}, model_folder, prune_recall)
trainer = load_model(parameters['remodelfile'], m)
_, _,_,p,r=trainer.eval_epoch(final=True, save_predictions=True)
print('Saving test metrics ... ', end="")
np.savetxt(parameters['remodelfile']+"/p.txt", p)
np.savetxt(parameters['remodelfile']+"/r.txt", r)
# b = numpy.loadtxt("filename.txt", delimiter=',')
print('DONE')
def train(parameters):
model_folder = setup_log(parameters, 'train')
set_seed(0)
###################################
# Data Loading
###################################
print('\nLoading training data ...')
train_loader = DataLoader(parameters['train_data'], parameters)
train_loader(embeds=parameters['embeds'])
train_data = RelationDataset(train_loader, 'train',
parameters['unk_w_prob'],
train_loader).__call__()
print('\nLoading testing data ...')
test_loader = DataLoader(parameters['test_data'], parameters)
test_loader()
test_data = RelationDataset(test_loader, 'test', parameters['unk_w_prob'],
train_loader).__call__()
###################################
# TRAINING
###################################
trainer = Trainer({
'train': train_data,
'test': test_data
}, parameters, train_loader, model_folder)
trainer.run()
trainer.eval_epoch(final=True, save_predictions=True)
if parameters['plot']:
plot_learning_curve(trainer, model_folder)
def test(parameters):
model_folder = setup_log(parameters, 'test')
print('\nLoading mappings ...')
train_loader = load_mappings(model_folder)
print('\nLoading testing data ...')
test_loader = DataLoader(parameters['test_data'], parameters)
test_loader()
test_data = DocRelationDataset(test_loader, 'test', parameters, train_loader).__call__()
m = Trainer(train_loader, parameters, {'train': [], 'test': test_data}, model_folder)
trainer = load_model(model_folder, m)
trainer.eval_epoch(final=True, save_predictions=True)
def _test(parameters):
model_folder = setup_log(parameters, parameters['save_pred'] + '_test')
print('\nLoading mappings ...')
train_loader = load_mappings(parameters['remodelfile'])
print('\nLoading testing data ...')
test_loader = DataLoader(parameters['test_data'], parameters, train_loader)
test_loader(parameters=parameters)
test_data, prune_recall = DocRelationDataset(test_loader, 'test',
parameters,
train_loader).__call__()
m = Trainer(train_loader, parameters, {
'train': [],
'test': test_data
}, model_folder, prune_recall)
trainer = load_model(parameters['remodelfile'], m)
trainer.eval_epoch(final=True, save_predictions=True)
def train(self):
###################################
# TRAINING
###################################
trainer = Trainer({'train': self.train_data, 'test': self.test_data},
self.parameters, self.train_loader, self.model_folder)
trainer.run()
trainer.eval_epoch(final=True, save_predictions=True)
save_model(model_folder, trainer.model, train_loader)
if parameters['plot']:
plot_learning_curve(trainer, model_folder)
return float(trainer.best_score)
def test(parameters):
print('*** Testing Model ***')
model_folder = setup_log(parameters, 'test')
print('Loading mappings ...')
with open(os.path.join(model_folder, 'mappings.pkl'), 'rb') as f:
loader = pkl.load(f)
print('Loading testing data ...')
test_loader = DataLoader(parameters['test_data'], parameters)
test_loader.__call__()
test_data = RelationDataset(test_loader, 'test', parameters['unk_w_prob'],
loader).__call__()
m = Trainer({
'train': [],
'test': test_data
}, parameters, loader, model_folder)
trainer = load_model(model_folder, m)
trainer.eval_epoch(final=True, save_predictions=True)