def main():
data = TextDataset(
path='../../../../datasets/shakespeare_input.txt',
source=
"http://cs.stanford.edu/people/karpathy/char-rnn/shakespeare_input.txt",
target_n_future=1,
sequence_length=50)
rnn = RNN(outdir='outputs/rnn/',
input_size=len(data.vocab),
hidden_size=128,
output_size=len(data.vocab),
layers=2,
activation='softmax',
hidden_activation='relu',
mrg=RNG_MRG.MRG_RandomStreams(1),
weights_init='uniform',
weights_interval='montreal',
bias_init=0.0,
r_weights_init='identity',
r_bias_init=0.0,
cost_function='nll',
cost_args=None,
noise='dropout',
noise_level=.7,
noise_decay='exponential',
noise_decay_amount=.99,
direction='forward')
cost_monitor = Monitor("cost",
rnn.get_train_cost(),
train=False,
valid=True,
test=True)
optimizer = RMSProp(model=rnn,
dataset=data,
grad_clip=5.,
hard_clip=False,
learning_rate=2e-3,
lr_decay='exponential',
lr_decay_factor=0.97,
decay=0.95,
batch_size=50,
epochs=50)
# optimizer = AdaDelta(model=gsn, dataset=mnist, n_epoch=200, batch_size=100, learning_rate=1e-6)
optimizer.train(monitor_channels=cost_monitor)
def main(sequence):
rnn_gsn = RNN_GSN()
# data! (needs to be 3d for rnn).
mnist = MNIST(sequence_number=sequence, seq_3d=True, seq_length=50)
# optimizer!
optimizer = RMSProp(model=rnn_gsn,
dataset=mnist,
epochs=500,
batch_size=50,
save_freq=10,
stop_patience=30,
stop_threshold=.9995,
learning_rate=1e-6,
decay=.95,
max_scaling=1e5,
grad_clip=5.,
hard_clip=False)
# train!
optimizer.train()
def main(sequence):
rnn_gsn = RNN_GSN()
# data! (needs to be 3d for rnn).
mnist = MNIST(sequence_number=sequence, seq_3d=True, seq_length=50)
# optimizer!
optimizer = RMSProp(
model=rnn_gsn,
dataset=mnist,
epochs=500,
batch_size=50,
save_freq=10,
stop_patience=30,
stop_threshold=.9995,
learning_rate=1e-6,
decay=.95,
max_scaling=1e5,
grad_clip=5.,
hard_clip=False
)
# train!
optimizer.train()
def main():
data = TextDataset(path='../../../../datasets/shakespeare_input.txt',
source="http://cs.stanford.edu/people/karpathy/char-rnn/shakespeare_input.txt",
target_n_future=1,
sequence_length=50)
rnn = RNN(outdir='outputs/rnn/',
input_size=len(data.vocab),
hidden_size=128,
output_size=len(data.vocab),
layers=2,
activation='softmax',
hidden_activation='relu',
mrg=RNG_MRG.MRG_RandomStreams(1),
weights_init='uniform',
weights_interval='montreal',
bias_init=0.0,
r_weights_init='identity',
r_bias_init=0.0,
cost_function='nll',
cost_args=None,
noise='dropout',
noise_level=.7,
noise_decay='exponential',
noise_decay_amount=.99,
direction='forward')
cost_monitor = Monitor("cost", rnn.get_train_cost(), train=False, valid=True, test=True)
optimizer = RMSProp(model=rnn, dataset=data,
grad_clip=5., hard_clip=False,
learning_rate=2e-3, lr_decay='exponential', lr_decay_factor=0.97,
decay=0.95, batch_size=50, epochs=50)
# optimizer = AdaDelta(model=gsn, dataset=mnist, n_epoch=200, batch_size=100, learning_rate=1e-6)
optimizer.train(monitor_channels=cost_monitor)