def _create_mlp(self):
model = NeuralRegressor(input_dim=self.unit_counts[0])
initializer = UniformInitializer(seed=self.random_state)
if self.spec.is_convolution:
model.stack_layer(layers.DimShuffle((0, 'x', 1, 2)))
for l, n in zip(self.layers, self.unit_counts[1:]):
t = None
if l.type in ('Tanh', 'Sigmoid'): t = l.type.lower()
if l.type in ('Rectifier'): t = 'relu'
if l.type in ('Linear', 'Softmax'): t = 'linear'
assert t is not None, "Unknown activation type `%s`." % l.type
if isinstance(l, Layer):
# self._check_layer(l, ['units'])
model.stack_layer(layers.Dense(n, t, init=initializer))
if l.type == 'Softmax':
model.stack_layer(layers.Softmax())
if isinstance(l, layers.Convolution):
# self._check_layer(l, ['channel', 'kernel_shape'])
model.stack_layer(layers.Convolution(
activation=t,
filter_shape=(l.channels, l.kernel_shape[0], l.kernel_shape[1]),
pool_size=l.pool_shape,
border_mode=l.border_mode,
init=initializer))
self.mlp = model
def get_model(state_num, action_num):
model = NeuralRegressor(state_num)
model.stack(
Dense(HIDDEN_UNITS,
activation='tanh',
init=GaussianInitializer(deviation=0.01)),
Dense(action_num, init=GaussianInitializer(deviation=0.01)))
return model
def _create_mlp(self):
model = NeuralRegressor(input_dim=self.unit_counts[0])
for l, n in zip(self.layers, self.unit_counts[1:]):
t = 'relu'
if l.type == 'Rectifier': t = 'relu'
if l.type == 'Linear': t = 'linear'
model.stack_layer(Dense(n, t))
model.stack_layer(Softmax())
self.mlp = model
valid_size = int(1000)
train_set = data[valid_size:]
valid_set = data[:valid_size]
dataset = SequentialDataset(train_set, valid=valid_set)
dataset.report()
batch_set = MiniBatches(dataset, batch_size=32)
if __name__ == '__main__':
ap = ArgumentParser()
ap.add_argument("--model", default=os.path.join(os.path.dirname(__file__), "models", "sequence_adding_100_2.gz"))
args = ap.parse_args()
model = NeuralRegressor(input_dim=2, input_tensor=3)
model.stack(IRNN(hidden_size=100, input_type="sequence",
output_type="one"),
Dense(1))
if os.path.exists(args.model):
model.load_params(args.model)
conf = TrainerConfig()
conf.learning_rate = LearningRateAnnealer.learning_rate(0.01)
conf.gradient_clipping = 3
conf.patience = 50
conf.gradient_tolerance = 5
conf.avoid_nan = False
trainer = SGDTrainer(model, conf)
def get_model(state_num, action_num):
model = NeuralRegressor(state_num)
model.stack(Dense(HIDDEN_UNITS, activation='tanh', init=GaussianInitializer(deviation=0.01)),
Dense(action_num, init=GaussianInitializer(deviation=0.01)))
return model
valid_size = int(1000)
train_set = data[valid_size:]
valid_set = data[:valid_size]
dataset = SequentialDataset(train_set, valid=valid_set)
dataset.report()
batch_set = MiniBatches(dataset, batch_size=32)
if __name__ == '__main__':
ap = ArgumentParser()
ap.add_argument("--model", default=os.path.join(os.path.dirname(__file__), "models", "sequence_adding_100_2.gz"))
args = ap.parse_args()
model = NeuralRegressor(input_dim=2, input_tensor=3, clip_value=3.)
model.stack_layer(IRNN(hidden_size=100, output_size=1, input_type="sequence",
output_type="one", output_activation="linear"))
if os.path.exists(args.model):
model.load_params(args.model)
conf = TrainerConfig()
conf.learning_rate = LearningRateAnnealer.learning_rate(0.01)
conf.max_norm = 1
conf.patience = 50
conf.gradient_tolerance = 5
trainer = SGDTrainer(model, conf)
annealer = LearningRateAnnealer(trainer, patience=20)