logging.basicConfig(level=logging.INFO) default_model = os.path.join(os.path.dirname(__file__), "models", "class_based_rnnlm.gz") if __name__ == '__main__': ap = ArgumentParser() 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),
from deepy.dataset import SequentialMiniBatches from deepy.trainers import SGDTrainer, LearningRateAnnealer from deepy.layers import RNN, Dense logging.basicConfig(level=logging.INFO) resource_dir = os.path.abspath(os.path.dirname(__file__)) + os.sep + "resources" vocab_path = os.path.join(resource_dir, "ptb.train.txt") train_path = os.path.join(resource_dir, "ptb.train.txt") valid_path = os.path.join(resource_dir, "ptb.valid.txt") vocab = Vocab(char_based=True) vocab.load(vocab_path, max_size=1000) model = NeuralLM(input_dim=vocab.size, input_tensor=3) model.stack( RNN(hidden_size=100, output_type="sequence"), RNN(hidden_size=100, output_type="sequence"), Dense(vocab.size, "softmax")) if __name__ == '__main__': ap = ArgumentParser() ap.add_argument("--model", default=os.path.join(os.path.dirname(__file__), "models", "char_rnn_model1.gz")) ap.add_argument("--sample", default="") args = ap.parse_args() if os.path.exists(args.model): model.load_params(args.model)
from deepy.layers import LSTM from layers import FullOutputLayer logging.basicConfig(level=logging.INFO) default_model = os.path.join(os.path.dirname(__file__), "models", "lstm_rnnlm.gz") if __name__ == '__main__': ap = ArgumentParser() 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) model = NeuralLM(vocab.size, test_data=None) model.stack( LSTM(hidden_size=100, output_type="sequence", persistent_state=True, batch_size=lmdata.size, reset_state_for_input=0), FullOutputLayer(vocab.size)) 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 })
logging.basicConfig(level=logging.INFO) default_model = os.path.join(os.path.dirname(__file__), "models", "class_based_rnnlm.gz") if __name__ == '__main__': ap = ArgumentParser() 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, class_based=True) 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),