ap.add_argument("--model", default="")
ap.add_argument("--small", action="store_true")
args = ap.parse_args()
vocab, lmdata = load_data(small=args.small, history_len=5, batch_size=64)
import pdb
pdb.set_trace()
model = NeuralLM(vocab.size)
model.stack(
RNN(hidden_size=100,
output_type="sequence",
hidden_activation='sigmoid',
persistent_state=True,
batch_size=lmdata.size,
reset_state_for_input=0),
ClassOutputLayer(output_size=100, class_size=100))
if os.path.exists(args.model):
model.load_params(args.model)
trainer = SGDTrainer(
model, {
"learning_rate": LearningRateAnnealer.learning_rate(1.2),
"weight_l2": 1e-7
})
annealer = LearningRateAnnealer()
trainer.run(lmdata, epoch_controllers=[annealer])
model.save_params(default_model)
default_model = os.path.join(os.path.dirname(__file__), "models", "lstm_rnnlmnew.gz")
default_dict = '/home/tangyaohua/dl4mt/data/larger.corpus/vocab.chinese.pkl'
# default_dict = '/home/tangyh/Dropbox/PycharmProjects/dl4mt/session2/lm/resources/vocab.chinese.pkl'
if __name__ == '__main__':
ap = ArgumentParser()
ap.add_argument("--model", default='')
ap.add_argument("--dictpath", default=default_dict)
ap.add_argument("--small", action="store_true")
args = ap.parse_args()
vocab, lmdata = load_datagivendict(dictpath=args.dictpath, small=args.small, history_len=5, batch_size=16)
inputx=T.imatrix('x')
print len(vocab), 'len(vocab)'
model = NeuralLM(len(vocab), test_data=None, input_tensor=inputx)
model.stack(LSTM(hidden_size=100, output_type="sequence",
persistent_state=True, batch_size=lmdata.size,
reset_state_for_input=0),
FullOutputLayer(len(vocab)))
if os.path.exists(args.model):
model.load_params(args.model)
trainer = SGDTrainer(model, {"learning_rate": LearningRateAnnealer.learning_rate(1.2),
"weight_l2": 1e-7})
annealer = LearningRateAnnealer(trainer)
trainer.run(lmdata, controllers=[annealer])
model.save_params(default_model)
