default_model = os.path.join(os.path.dirname(__file__), "models",
"baseline_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)
model.stack(
RNN(hidden_size=100,
output_type="sequence",
hidden_activation="sigmoid",
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
})
annealer = LearningRateAnnealer()
trainer.run(lmdata, controllers=[annealer])
"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),
"weight_l2": 1e-7
})
annealer = LearningRateAnnealer()
trainer.run(lmdata, epoch_controllers=[annealer])
# -*- coding: utf-8 -*-
import os
from deepy.networks import AutoEncoder
from deepy.layers import RNN, Dense
from deepy.trainers import SGDTrainer, LearningRateAnnealer
from util import get_data, VECTOR_SIZE, SEQUENCE_LENGTH
HIDDEN_SIZE = 50
model_path = os.path.join(os.path.dirname(__file__), "models", "rnn1.gz")
if __name__ == '__main__':
model = AutoEncoder(rep_dim=10, input_dim=VECTOR_SIZE, input_tensor=3)
model.stack_encoders(
RNN(hidden_size=HIDDEN_SIZE, input_type="sequence", output_type="one"))
model.stack_decoders(
RNN(hidden_size=HIDDEN_SIZE,
input_type="one",
output_type="sequence",
steps=SEQUENCE_LENGTH), Dense(VECTOR_SIZE, 'softmax'))
trainer = SGDTrainer(model)
annealer = LearningRateAnnealer(trainer)
trainer.run(get_data(), controllers=[annealer])
model.save_params(model_path)
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)
lmdata = LMDataset(vocab, train_path, valid_path, history_len=30, char_based=True, max_tokens=300)
batch = SequentialMiniBatches(lmdata, batch_size=20)
# Separate data
valid_size = int(len(data) * 0.15)
train_set = data[valid_size:]
valid_set = data[:valid_size]
dataset = SequentialDataset(train_set, valid=valid_set)
dataset.pad_left(20)
dataset.report()
batch_set = MiniBatches(dataset)
if __name__ == '__main__':
model = NeuralClassifier(input_dim=26, input_tensor=3)
model.stack(
RNN(hidden_size=30,
input_type="sequence",
output_type="sequence",
vector_core=0.1),
RNN(hidden_size=30,
input_type="sequence",
output_type="sequence",
vector_core=0.3),
RNN(hidden_size=30,
input_type="sequence",
output_type="sequence",
vector_core=0.6),
RNN(hidden_size=30,
input_type="sequence",
output_type="one",
vector_core=0.9), Dense(4), Softmax())
trainer = SGDTrainer(model)
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)
lmdata = LMDataset(vocab,
# -*- coding: utf-8 -*-
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
from deepy.networks import AutoEncoder
from deepy.layers import RNN, Dense
from deepy.trainers import SGDTrainer, LearningRateAnnealer
from util import get_data, VECTOR_SIZE, SEQUENCE_LENGTH
HIDDEN_SIZE = 50
model_path = os.path.join(os.path.dirname(__file__), "models", "rnn1.gz")
if __name__ == '__main__':
model = AutoEncoder(input_dim=VECTOR_SIZE, input_tensor=3)
model.stack_encoders(RNN(hidden_size=HIDDEN_SIZE, input_type="sequence", output_type="one"))
model.stack_decoders(RNN(hidden_size=HIDDEN_SIZE, input_type="one", output_type="sequence", steps=SEQUENCE_LENGTH),
Dense(VECTOR_SIZE, 'softmax'))
trainer = SGDTrainer(model)
annealer = LearningRateAnnealer(trainer)
trainer.run(get_data(), controllers=[annealer])
model.save_params(model_path)