def train(train_data_path, test_data_path, args):
vocab = collections.defaultdict(lambda: len(vocab))
vocab['<unk>'] = 0
train_data = babi.read_data(vocab, train_data_path)
test_data = babi.read_data(vocab, test_data_path)
print('Training data: %s: %d' % (train_data_path, len(train_data)))
print('Test data: %s: %d' % (test_data_path, len(test_data)))
train_data = memnn.convert_data(train_data, args.max_memory)
test_data = memnn.convert_data(test_data, args.max_memory)
encoder = memnn.make_encoder(args.sentence_repr)
network = memnn.MemNN(args.unit, len(vocab), encoder, args.max_memory,
args.hop)
model = chainer.links.Classifier(network, label_key='answer')
opt = chainer.optimizers.Adam()
if args.gpu >= 0:
chainer.cuda.get_device(args.gpu).use()
model.to_gpu()
opt.setup(model)
train_iter = chainer.iterators.SerialIterator(train_data, args.batchsize)
test_iter = chainer.iterators.SerialIterator(test_data,
args.batchsize,
repeat=False,
shuffle=False)
updater = chainer.training.StandardUpdater(train_iter,
opt,
device=args.gpu)
trainer = chainer.training.Trainer(updater, (args.epoch, 'epoch'))
@chainer.training.make_extension()
def fix_ignore_label(trainer):
network.fix_ignore_label()
trainer.extend(fix_ignore_label)
trainer.extend(extensions.Evaluator(test_iter, model, device=args.gpu))
trainer.extend(extensions.LogReport())
trainer.extend(
extensions.PrintReport([
'epoch', 'main/loss', 'validation/main/loss', 'main/accuracy',
'validation/main/accuracy'
]))
trainer.extend(extensions.ProgressBar(update_interval=10))
trainer.run()
if args.model:
memnn.save_model(args.model, model, vocab)
def train(train_data_path, test_data_path, args):
device = chainer.get_device(args.device)
device.use()
vocab = collections.defaultdict(lambda: len(vocab))
vocab['<unk>'] = 0
train_data = babi.read_data(vocab, train_data_path)
test_data = babi.read_data(vocab, test_data_path)
print('Training data: %s: %d' % (train_data_path, len(train_data)))
print('Test data: %s: %d' % (test_data_path, len(test_data)))
train_data = memnn.convert_data(train_data, args.max_memory)
test_data = memnn.convert_data(test_data, args.max_memory)
encoder = memnn.make_encoder(args.sentence_repr)
network = memnn.MemNN(
args.unit, len(vocab), encoder, args.max_memory, args.hop)
model = chainer.links.Classifier(network, label_key='answer')
opt = chainer.optimizers.Adam()
model.to_device(device)
opt.setup(model)
train_iter = chainer.iterators.SerialIterator(
train_data, args.batchsize)
test_iter = chainer.iterators.SerialIterator(
test_data, args.batchsize, repeat=False, shuffle=False)
updater = chainer.training.StandardUpdater(train_iter, opt, device=device)
trainer = chainer.training.Trainer(updater, (args.epoch, 'epoch'))
@chainer.training.make_extension()
def fix_ignore_label(trainer):
network.fix_ignore_label()
trainer.extend(fix_ignore_label)
trainer.extend(extensions.Evaluator(test_iter, model, device=device))
trainer.extend(extensions.LogReport())
trainer.extend(extensions.PrintReport(
['epoch', 'main/loss', 'validation/main/loss',
'main/accuracy', 'validation/main/accuracy']))
trainer.extend(extensions.ProgressBar(update_interval=10))
trainer.run()
if args.model:
memnn.save_model(args.model, model, vocab)