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_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)
annealer = LearningRateAnnealer(patience=20)
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