def main():
opts = optparser.parse_args()[0]
train_loader = Loader(opts.train)
opts.vocab_len = len(train_loader._char_to_id)
opts.pos_len = len(train_loader._pos_to_id)
opts.max_pos_len = train_loader._pos_max_len
opts.max_target_len = train_loader._char_max_len
opts.use_cuda = opts.use_cuda == 1
opts.eval = opts.eval == 1
opts.data_size = train_loader.get_data_size()
if not torch.cuda.is_available():
opts.use_cuda = False
torch.manual_seed(opts.seed)
np.random.seed(opts.seed)
if not opts.eval:
# weights for paddings, set to 0
loss_weights = torch.ones(opts.vocab_len)
loss_weights[0] = 0
criterion = nn.NLLLoss(loss_weights, size_average=False)
c2i, i2c, p2i, i2p = train_loader.get_mappings()
dev_loader = Loader(opts.dev, c2i, i2c, p2i, i2p)
if dev_loader._pos_max_len > opts.max_pos_len:
opts.max_pos_len = dev_loader._pos_max_len
model = Module(opts)
if opts.model_path is not '':
model = torch.load(opts.model_path)
train_batcher = Batcher(opts.batch_size, train_loader.get_data(),
opts.max_pos_len, opts.eval)
dev_batcher = Batcher(decode_batch, dev_loader.get_data(),
opts.max_pos_len, True)
print model
start_train(model, criterion, opts, train_batcher, dev_batcher)
else:
model = torch.load(opts.model_path)
model.eval()
#print model
c2i, i2c, p2i, i2p = train_loader.get_mappings()
test_loader = Loader(opts.test, c2i, i2c, p2i, i2p)
if test_loader._pos_max_len > opts.max_pos_len:
opts.max_pos_len = test_loader._pos_max_len
test_batcher = Batcher(1, test_loader.get_data(), opts.max_pos_len,
opts.eval)
opts.data_size = test_loader.get_data_size()
decode(model, opts, test_batcher, i2c, i2p)
