def train(opt):
# basics definition
opt.experiment = os.path.join(root_dir, opt.experiment)
if not os.path.exists(opt.experiment):
os.makedirs(opt.experiment)
opt.save_model = os.path.join(opt.experiment, opt.save_model)
opt.log_path = os.path.join(opt.experiment, 'log.train')
opt.logger = make_logger(opt.log_path)
# dataIter definition
train_iter = OneBestIter4STC(opt.data_root+'train', opt.word2idx, opt.class2idx,
opt.batch_size, opt.cuda, True)
valid_iter = OneBestIter4STC(opt.data_root+'valid', opt.word2idx, opt.class2idx,
opt.batch_size, opt.cuda, False)
# model definition
model = make_model(opt)
if opt.load_emb:
emb = read_emb(opt.word2idx)
model.emb.init_weight_from_pre_emb(emb, opt.fix_emb)
print(model)
# criterion definition
criterion = nn.BCELoss(reduction='sum')
if opt.cuda:
criterion = criterion.cuda()
# optimizer definition
optimizer = Optim(opt.optim, opt.lr, max_grad_norm=opt.max_norm)
optimizer.set_parameters(model.named_parameters())
print('Trainable parameter number: {}'.format(len(optimizer.params)))
# training procedure
trainer = OneBestTrainer4STC(model, criterion, optimizer, opt.logger)
trainer.train(opt.epochs, train_iter, valid_iter, opt.save_model)
def train(opt):
opt.experiment = os.path.join(root_dir, opt.experiment)
if not os.path.exists(opt.experiment):
os.makedirs(opt.experiment)
opt.save_model = os.path.join(opt.experiment, opt.save_model)
opt.log_path = os.path.join(opt.experiment, 'log.train')
opt.logger = make_logger(opt.log_path)
# memory info
print("encoder word2idx number: {}".format(opt.enc_word_vocab_size))
print("decoder word2idx number: {}".format(opt.dec_word_vocab_size))
print("act2idx number: {}".format(opt.act_vocab_size))
print("slot2idx number: {}".format(opt.slot_vocab_size))
# Model definition
model = make_model(opt)
if opt.load_word_emb:
emb = read_emb(opt.memory['enc2idx'])
model.enc_word_emb.init_weight_from_pre_emb(emb, opt.fix_word_emb)
if opt.load_class_emb:
emb = opt.memory['act_emb']
model.act_emb.init_weight_from_pre_emb(emb, opt.fix_class_emb)
emb = opt.memory['slot_emb']
model.slot_emb.init_weight_from_pre_emb(emb, opt.fix_class_emb)
if opt.share_param:
#model.value_decoder.outlin.weight.data = model.word_emb.embedding.weight.data
#model.value_decoder.outlin.weight.requires_grad = model.word_emb.embedding.weight.requires_grad
model.act_stc.lin.weight.data = model.act_emb.embedding.weight.data
model.act_stc.lin.weight.requires_grad = model.act_emb.embedding.weight.requires_grad
model.slot_stc.lin.weight.data = model.slot_emb.embedding.weight.data
model.slot_stc.lin.weight.requires_grad = model.slot_emb.embedding.weight.requires_grad
if opt.cuda:
model = model.cuda()
print(model)
# optimizer details
optimizer = Optim(opt.optim, opt.lr, max_grad_norm=opt.max_norm)
optimizer.set_parameters(model.named_parameters())
print("training parameters number: {}".format(len(optimizer.params)))
# loss definition
#stc_criterion = MaskedBCELoss(opt.cuda)
stc_criterion = nn.BCELoss(reduction='sum')
nll_criterion = nn.NLLLoss(reduction='sum')
if opt.cuda:
stc_criterion = stc_criterion.cuda()
nll_criterion = nll_criterion.cuda()
# training procedure
if opt.task == 'slu':
data_iter = SLUDataset(opt.data_root + 'train', opt.memory, opt.cuda,
True)
trainer = SLUTrainer(model, (stc_criterion, nll_criterion),
optimizer,
opt.logger,
cuda=opt.cuda)
elif opt.task == 'act':
data_iter = ActDataset(opt.data_root + 'train', opt.memory, opt.cuda,
True)
trainer = ActTrainer(model,
stc_criterion,
optimizer,
opt.logger,
cuda=opt.cuda)
elif opt.task == 'slot':
data_iter = SlotDataset(opt.data_root + 'train', opt.memory, opt.cuda,
True)
trainer = SlotTrainer(model,
stc_criterion,
optimizer,
opt.logger,
cuda=opt.cuda)
elif opt.task == 'value':
data_iter = ValueDataset(opt.data_root + 'train', opt.memory, opt.cuda,
True)
trainer = ValueTrainer(model,
nll_criterion,
optimizer,
opt.logger,
cuda=opt.cuda)
trainer.train(opt.epochs, opt.batch_size, opt.memory, data_iter,
opt.data_root + 'valid', opt.save_model)