opt['model_save_dir'] = model_save_dir
helper.ensure_dir(model_save_dir, verbose=True)
# save config
helper.save_config(opt, model_save_dir + '/config.json', verbose=True)
vocab.save(model_save_dir + '/vocab.pkl')
file_logger = helper.FileLogger(
model_save_dir + '/' + opt['log'],
header="# epoch\ttrain_loss\tdev_loss\tdev_score\tbest_dev_score")
# print model info
helper.print_config(opt)
# model
if not opt['load']:
trainer = GCNTrainer(opt, emb_matrix=emb_matrix)
else:
# load pretrained model
model_file = opt['model_file']
print("Loading model from {}".format(model_file))
model_opt = torch_utils.load_config(model_file)
model_opt['optim'] = opt['optim']
trainer = GCNTrainer(model_opt)
trainer.load(model_file)
id2label = dict([(v, k) for k, v in label2id.items()])
dev_score_history = []
current_lr = opt['lr']
global_step = 0
global_start_time = time.time()
parser.add_argument('--cuda', type=bool, default=torch.cuda.is_available())
parser.add_argument('--cpu', action='store_true')
args = parser.parse_args()
torch.manual_seed(args.seed)
random.seed(1234)
if args.cpu:
args.cuda = False
elif args.cuda:
torch.cuda.manual_seed(args.seed)
# load opt
model_file = args.model_dir + '/' + args.model
print("Loading model from {}".format(model_file))
opt = torch_utils.load_config(model_file)
trainer = GCNTrainer(opt)
trainer.load(model_file)
# load vocab
vocab_file = args.model_dir + '/vocab.pkl'
vocab = Vocab(vocab_file, load=True)
assert opt[
'vocab_size'] == vocab.size, "Vocab size must match that in the saved model."
# load data
data_file = opt['data_dir'] + '/{}.json'.format(args.dataset)
print("Loading data from {} with batch size {}...".format(
data_file, opt['batch_size']))
batch = DataLoader(data_file, opt['batch_size'], opt, vocab, evaluation=True)
helper.print_config(opt)
# print(torch.cuda.device_count())
# with torch.cuda.device(1):
# for subj in SUBJ_LIST:
# for obj in OBJ_LIST:
# print("eval samples of subj:"+subj+" obj:"+obj)
# args.model_dir = 'saved_models/02'
# if os.path.exists(args.model_dir+'/'+subj+"_"+obj+"_"+"best_model.pt"):
# model_file = args.model_dir +'/'+subj+"_"+obj+"_"+"best_model.pt"
# else:
# model_file = args.model_dir + '/best_model.pt'
model_file=args.model_dir+'/best_model' \
'.pt'
print("Loading model from {}".format(model_file))
opt = torch_utils.load_config(model_file)
data_file = opt['data_dir'] + '/{}.json'.format(args.dataset)
trainer = GCNTrainer(opt, lbstokens=lbstokens)
trainer.load(model_file)
batch = DataLoader([data_file],
opt['batch_size'],
opt,
vocab,
evaluation=True,
corefresolve=True)
batch_iter = tqdm(batch)
all_probs = []
samples = []
for i, b in enumerate(batch_iter):
preds, probs, _, sample = trainer.predict(b)
predictions += preds
all_probs += probs
if args.cpu:
args.cuda = False
elif args.cuda:
torch.cuda.manual_seed(args.seed)
model_file_list = [
'saved_models/01', 'saved_models/02', 'saved_models/03', 'saved_models/04',
'saved_models/00'
]
prob_list = []
for j in range(len(model_file_list)):
model_file = model_file_list[j] + '/' + args.model
print("Loading model from {}".format(model_file))
opt = torch_utils.load_config(model_file) # 加载超参数
trainer = GCNTrainer(opt) # 定义模型
trainer.load(model_file) # 加载最好模型
# load vocab
vocab_file = model_file_list[j] + '/vocab.pkl'
vocab = Vocab(vocab_file, load=True)
assert opt[
'vocab_size'] == vocab.size, "Vocab size must match that in the saved model."
# load data
data_file = opt['data_dir'] + '/{}.json'.format(args.dataset)
print("Loading data from {} with batch size {}...".format(
data_file, opt['batch_size']))
batch = DataLoader(data_file,
opt['batch_size'],
opt,
vocab,
# if not os.path.exists(model_file):
# model_file="saved_models/02/"+"best_model_aug.pt"
train_batch = DataLoader([opt['data_dir'] + '/train_coref.json'], opt['batch_size'], opt, vocab, evaluation=False,is_aug=False,corefresolve=True)
dev_batch = DataLoader([opt['data_dir'] + '/dev_rev_coref.json'], opt['batch_size'], opt, vocab, evaluation=True,corefresolve=True)
test_batch = DataLoader([opt['data_dir'] + '/test_rev_coref.json'], opt['batch_size'], opt, vocab, evaluation=True,corefresolve=True)
# if dev_batch.num_examples==0 or test_batch.num_examples==0:
# continue
max_steps = len(train_batch) * opt['num_epoch']
global_step = 0
global_start_time = time.time()
format_str = '{}: step {}/{} (epoch {}/{}), loss = {:.6f} ({:.3f} sec/batch), lr: {:.6f}'
score_history = []
test_score_history=[]
current_lr = opt['lr']
if not opt['load']:
trainer = GCNTrainer(opt, lbstokens=lbstokens,emb_matrix=emb_matrix)
else:
#load pretrained model
model_file = opt['model_file']
print("Loading model from {}".format(model_file))
model_opt = torch_utils.load_config(model_file)
model_opt['optim'] = opt['optim']
model_opt['lr'] = opt['lr']
model_opt['lr_decay'] = opt['lr_decay']
trainer = GCNTrainer(model_opt,lbstokens=lbstokens)
trainer.load(model_file)
# print("Evaluating on dev set...")
# predictions = []
# dev_loss = 0
# for i, batch in enumerate(dev_batch):
# preds, probs, loss, samples = trainer.predict(batch)
model_save_dir = opt['save_dir'] + '/' + model_id
opt['model_save_dir'] = model_save_dir
helper.ensure_dir(model_save_dir, verbose=True)
# save config
helper.save_config(opt, model_save_dir + '/config.json', verbose=True)
vocab.save(model_save_dir + '/vocab.pkl')
file_logger = helper.FileLogger(
model_save_dir + '/' + opt['log'],
header="# epoch\ttrain_loss\tdev_loss\tdev_score\tbest_dev_score")
# print model info
helper.print_config(opt)
# model
trainer = GCNTrainer(opt, emb_matrix=emb_matrix)
id2label = dict([(v, k) for k, v in label2id.items()])
dev_score_history = []
current_lr = opt['lr']
global_step = 0
global_start_time = time.time()
format_str = '{}: step {}/{} (epoch {}/{}), loss = {:.6f} ({:.3f} sec/batch), lr: {:.6f}'
max_steps = len(train_batch) * opt['num_epoch']
# start training
for epoch in range(1, opt['num_epoch'] + 1):
train_loss = 0
for i, batch in enumerate(train_batch):
start_time = time.time()
#model_id = opt['id'] if len(opt['id']) > 1 else '0' + opt['id']
#model_save_dir = opt['save_dir'] + '/' + model_id
#opt['model_save_dir'] = model_save_dir
#helper.ensure_dir(model_save_dir, verbose=True)
# save config
#helper.save_config(opt, model_save_dir + '/config.json', verbose=True)
#vocab.save(model_save_dir + '/vocab.pkl')
#file_logger = helper.FileLogger(model_save_dir + '/' + opt['log'], header="# epoch\ttrain_loss\tdev_loss\tdev_precision\tdev recall\tdev f1\tbest f1")
# print model info
#helper.print_config(opt)
#print(np.array(meshvec_table))
# model
if not opt['load']:
trainer = GCNTrainer(opt,knowledge_emb=np.array(meshvec_table),word_emb=np.array(wordvec_table))
#print (trainer)
else:
# load pretrained model
model_file = opt['model_file']
print("Loading model from {}".format(model_file))
model_opt = torch_utils.load_config(model_file)
model_opt['optim'] = opt['optim']
trainer = GCNTrainer(model_opt)
trainer.load(model_file)
print("Evaluating on dev set...")
gold_answer=[]
predictions = []
doc_id_list = []
helper.ensure_dir(model_save_dir, verbose=True)
# save config
helper.save_config(opt, model_save_dir + '/config.json', verbose=True)
vocab.save(model_save_dir + '/vocab.pkl')
file_logger = helper.FileLogger(
model_save_dir + '/' + opt['log'],
header="# epoch\ttrain_loss\tdev_loss\tdev_score\tbest_dev_score")
# print model info
helper.print_config(opt)
# model
if not opt['load']:
trainer = GCNTrainer(opt,
emb_matrix=emb_matrix,
ucca_embedding_matrix=ucca_embedding.embedding_matrix
if ucca_embedding else None)
else:
# load pretrained model
model_file = opt['model_file']
print("Loading model from {}".format(model_file))
model_opt = torch_utils.load_config(model_file)
model_opt['optim'] = opt['optim']
trainer = GCNTrainer(model_opt)
trainer.load(model_file)
# The id2label[0] = 'no_relation' assignment is necessary for when --binary_classification is active
id2label = dict([(v, k) for k, v in label2id.items()])
id2label[0] = 'no_relation'
dev_score_history = []