def __build_retrospective_encoder(
self,
input_neuron_count=20,
hidden_neuron_count=20,
weight_limit=0.5,
dropout_rate=0.5,
batch_size=20,
learning_rate=1e-05,
bptt_tau=8
):
encoder_graph = ReEncoderGraph()
encoder_graph.observed_activating_function = TanhFunction()
encoder_graph.input_gate_activating_function = LogisticFunction()
encoder_graph.forget_gate_activating_function = LogisticFunction()
encoder_graph.output_gate_activating_function = LogisticFunction()
encoder_graph.hidden_activating_function = LogisticFunction()
encoder_graph.output_activating_function = LogisticFunction()
encoder_graph.create_rnn_cells(
input_neuron_count=input_neuron_count,
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=1
)
encoder_opt_params = EncoderAdam()
encoder_opt_params.weight_limit = weight_limit
encoder_opt_params.dropout_rate = dropout_rate
encoder = ReEncoder(
graph=encoder_graph,
epochs=100,
batch_size=batch_size,
learning_rate=learning_rate,
learning_attenuate_rate=0.1,
attenuate_epoch=50,
bptt_tau=bptt_tau,
test_size_rate=0.3,
computable_loss=MeanSquaredError(),
opt_params=encoder_opt_params,
verificatable_result=VerificateFunctionApproximation()
)
return encoder
def Main(params_dict):
logger = getLogger("pydbm")
handler = StreamHandler()
if params_dict["debug_mode"] is True:
handler.setLevel(DEBUG)
logger.setLevel(DEBUG)
else:
handler.setLevel(ERROR)
logger.setLevel(ERROR)
logger.addHandler(handler)
epochs = params_dict["epochs"]
batch_size = params_dict["batch_size"]
seq_len = params_dict["seq_len"]
channel = params_dict["channel"]
height = params_dict["height"]
width = params_dict["width"]
scale = params_dict["scale"]
training_image_dir = params_dict["training_image_dir"]
test_image_dir = params_dict["test_image_dir"]
enc_dim = batch_size * height * width
dec_dim = batch_size * height * width
feature_generator = ImageGenerator(epochs=epochs,
batch_size=batch_size,
training_image_dir=training_image_dir,
test_image_dir=test_image_dir,
seq_len=seq_len,
gray_scale_flag=True,
wh_size_tuple=(height, width),
norm_mode="z_score")
# Init.
encoder_graph = EncoderGraph()
# Activation function in LSTM.
encoder_graph.observed_activating_function = TanhFunction()
encoder_graph.input_gate_activating_function = LogisticFunction()
encoder_graph.forget_gate_activating_function = LogisticFunction()
encoder_graph.output_gate_activating_function = LogisticFunction()
encoder_graph.hidden_activating_function = TanhFunction()
encoder_graph.output_activating_function = LogisticFunction()
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
encoder_graph.create_rnn_cells(input_neuron_count=enc_dim,
hidden_neuron_count=200,
output_neuron_count=enc_dim)
# Optimizer for Encoder.
encoder_opt_params = EncoderAdam()
encoder_opt_params.weight_limit = 0.5
encoder_opt_params.dropout_rate = 0.5
encoder = Encoder(
# Delegate `graph` to `LSTMModel`.
graph=encoder_graph,
# The number of epochs in mini-batch training.
epochs=epochs,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=1e-05,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=0.1,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=50,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=8,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=0.3,
# Loss function.
computable_loss=MeanSquaredError(),
# Optimizer.
opt_params=encoder_opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation(),
# Tolerance for the optimization.
# When the loss or score is not improving by at least tol
# for two consecutive iterations, convergence is considered
# to be reached and training stops.
tol=0.0)
# Init.
decoder_graph = DecoderGraph()
# Activation function in LSTM.
decoder_graph.observed_activating_function = TanhFunction()
decoder_graph.input_gate_activating_function = LogisticFunction()
decoder_graph.forget_gate_activating_function = LogisticFunction()
decoder_graph.output_gate_activating_function = LogisticFunction()
decoder_graph.hidden_activating_function = TanhFunction()
decoder_graph.output_activating_function = LogisticFunction()
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
decoder_graph.create_rnn_cells(input_neuron_count=200,
hidden_neuron_count=dec_dim,
output_neuron_count=200)
# Optimizer for Decoder.
decoder_opt_params = DecoderAdam()
decoder_opt_params.weight_limit = 0.5
decoder_opt_params.dropout_rate = 0.5
decoder = Decoder(
# Delegate `graph` to `LSTMModel`.
graph=decoder_graph,
# The number of epochs in mini-batch training.
epochs=epochs,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=1e-05,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=0.1,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=50,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=8,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=0.3,
# Loss function.
computable_loss=MeanSquaredError(),
# Optimizer.
opt_params=decoder_opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation(),
# Tolerance for the optimization.
# When the loss or score is not improving by at least tol
# for two consecutive iterations, convergence is considered
# to be reached and training stops.
tol=0.0)
conv1 = ConvolutionLayer1(
ConvGraph1(activation_function=TanhFunction(),
filter_num=batch_size,
channel=channel,
kernel_size=3,
scale=scale,
stride=1,
pad=1))
conv2 = ConvolutionLayer2(
ConvGraph2(activation_function=TanhFunction(),
filter_num=batch_size,
channel=batch_size,
kernel_size=3,
scale=scale,
stride=1,
pad=1))
cnn = SpatioTemporalAutoEncoder(
layerable_cnn_list=[conv1, conv2],
encoder=encoder,
decoder=decoder,
epochs=epochs,
batch_size=batch_size,
learning_rate=1e-05,
learning_attenuate_rate=0.1,
attenuate_epoch=25,
computable_loss=MeanSquaredError(),
opt_params=Adam(),
verificatable_result=VerificateFunctionApproximation(),
test_size_rate=0.3,
tol=1e-15,
save_flag=False)
cnn.learn_generated(feature_generator)
test_len = 0
test_limit = 1
test_arr_list = []
rec_arr_list = []
for batch_observed_arr, batch_target_arr, test_batch_observed_arr, test_batch_target_arr in feature_generator.generate(
):
test_len += 1
result_arr = cnn.inference(test_batch_observed_arr)
for batch in range(test_batch_target_arr.shape[0]):
for seq in range(test_batch_target_arr[batch].shape[0]):
arr = test_batch_target_arr[batch][seq][0]
arr = (arr - arr.min()) / (arr.max() - arr.min())
arr *= 255
img = Image.fromarray(np.uint8(arr))
img.save("result/" + str(i) + "_" + str(seq) + "_observed.png")
for seq in range(result_arr[batch].shape[0]):
arr = result_arr[batch][seq][0]
arr = (arr - arr.min()) / (arr.max() - arr.min())
arr *= 255
img = Image.fromarray(np.uint8(arr))
img.save("result/" + str(i) + "_" + str(seq) +
"_reconsturcted.png")
if test_len >= test_limit:
break
def __init__(self,
lstm_model=None,
computable_loss=None,
batch_size=20,
input_neuron_count=100,
hidden_neuron_count=300,
observed_activating_function=None,
input_gate_activating_function=None,
forget_gate_activating_function=None,
output_gate_activating_function=None,
hidden_activating_function=None,
output_activating_function=None,
seq_len=10,
join_io_flag=False,
learning_rate=1e-05,
learning_attenuate_rate=0.1,
attenuate_epoch=50):
'''
Init.
Args:
lstm_model: is-a `lstm_model`.
computable_loss: is-a `ComputableLoss`.
batch_size: Batch size.
This parameters will be refered only when `lstm_model` is `None`.
input_neuron_count: The number of input units.
This parameters will be refered only when `lstm_model` is `None`.
hidden_neuron_count: The number of hidden units.
This parameters will be refered only when `lstm_model` is `None`.
observed_activating_function: is-a `ActivatingFunctionInterface` in hidden layer.
This parameters will be refered only when `lstm_model` is `None`.
If `None`, this value will be `TanhFunction`.
input_gate_activating_function: is-a `ActivatingFunctionInterface` in hidden layer.
This parameters will be refered only when `lstm_model` is `None`.
If `None`, this value will be `LogisticFunction`.
forget_gate_activating_function: is-a `ActivatingFunctionInterface` in hidden layer.
This parameters will be refered only when `lstm_model` is `None`.
If `None`, this value will be `LogisticFunction`.
output_gate_activating_function: is-a `ActivatingFunctionInterface` in hidden layer.
This parameters will be refered only when `lstm_model` is `None`.
If `None`, this value will be `LogisticFunction`.
hidden_activating_function: is-a `ActivatingFunctionInterface` in hidden layer.
This parameters will be refered only when `lstm_model` is `None`.
output_activating_function: is-a `ActivatingFunctionInterface` in output layer.
This parameters will be refered only when `lstm_model` is `None`.
If `None`, this model outputs from LSTM's hidden layer in inferencing.
seq_len: The length of sequences.
This means refereed maxinum step `t` in feedforward.
join_io_flag: If this value and value of `output_activating_function` is not `None`,
This model outputs tensors combining observed data points and inferenced data
in a series direction.
learning_rate: Learning rate.
learning_attenuate_rate: Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
attenuate_epoch: Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
Additionally, in relation to regularization,
this class constrains weight matrixes every `attenuate_epoch`.
'''
if computable_loss is None:
computable_loss = MeanSquaredError()
if lstm_model is not None:
if isinstance(lstm_model, LSTM) is False:
raise TypeError()
else:
# Init.
graph = LSTMGraph()
# Activation function in LSTM.
if observed_activating_function is None:
graph.observed_activating_function = TanhFunction()
else:
if isinstance(observed_activating_function,
ActivatingFunctionInterface) is False:
raise TypeError()
graph.observed_activating_function = observed_activating_function
if input_gate_activating_function is None:
graph.input_gate_activating_function = LogisticFunction()
else:
if isinstance(input_gate_activating_function,
ActivatingFunctionInterface) is False:
raise TypeError()
graph.input_gate_activating_function = input_gate_activating_function
if forget_gate_activating_function is None:
graph.forget_gate_activating_function = LogisticFunction()
else:
if isinstance(forget_gate_activating_function,
ActivatingFunctionInterface) is False:
raise TypeError()
graph.forget_gate_activating_function = forget_gate_activating_function
if output_gate_activating_function is None:
graph.output_gate_activating_function = LogisticFunction()
else:
if isinstance(output_gate_activating_function,
ActivatingFunctionInterface) is False:
raise TypeError()
graph.output_gate_activating_function = output_gate_activating_function
if hidden_activating_function is None:
graph.hidden_activating_function = TanhFunction()
else:
if isinstance(hidden_activating_function,
ActivatingFunctionInterface) is False:
raise TypeError()
graph.hidden_activating_function = hidden_activating_function
if output_activating_function is None:
graph.output_activating_function = TanhFunction()
self.__output_flag = False
output_neuron_count = 1
else:
graph.output_activating_function = output_activating_function
self.__output_flag = True
output_neuron_count = hidden_neuron_count
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
graph.create_rnn_cells(input_neuron_count=input_neuron_count,
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=output_neuron_count)
opt_params = SGD()
opt_params.weight_limit = 1e+10
opt_params.dropout_rate = 0.0
lstm_model = LSTM(
# Delegate `graph` to `LSTMModel`.
graph=graph,
# The number of epochs in mini-batch training.
epochs=100,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=learning_rate,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=learning_attenuate_rate,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=attenuate_epoch,
# The length of sequences.
seq_len=seq_len,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=seq_len,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=0.3,
# Loss function.
computable_loss=computable_loss,
# Optimizer.
opt_params=opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation(),
tol=0.0)
self.__lstm_model = lstm_model
self.__seq_len = seq_len
self.__learning_rate = learning_rate
self.__join_io_flag = join_io_flag
self.__computable_loss = computable_loss
self.__loss_list = []
self.__epoch_counter = 0
self.__learning_attenuate_rate = learning_attenuate_rate
self.__attenuate_epoch = attenuate_epoch
logger = getLogger("pygan")
self.__logger = logger
def learn(self,
sentence_list,
token_master_list,
hidden_neuron_count=200,
epochs=100,
batch_size=100,
learning_rate=1e-05,
learning_attenuate_rate=0.1,
attenuate_epoch=50,
bptt_tau=8,
weight_limit=0.5,
dropout_rate=0.5,
test_size_rate=0.3):
'''
Init.
Args:
sentence_list: The `list` of sentences.
token_master_list: Unique `list` of tokens.
hidden_neuron_count: The number of units in hidden layer.
epochs: Epochs of Mini-batch.
bath_size: Batch size of Mini-batch.
learning_rate: Learning rate.
learning_attenuate_rate: Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
attenuate_epoch: Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
Additionally, in relation to regularization,
this class constrains weight matrixes every `attenuate_epoch`.
bptt_tau: Refereed maxinum step `t` in Backpropagation Through Time(BPTT).
weight_limit: Regularization for weights matrix
to repeat multiplying the weights matrix and `0.9`
until $\sum_{j=0}^{n}w_{ji}^2 < weight\_limit$.
dropout_rate: The probability of dropout.
test_size_rate: Size of Test data set. If this value is `0`, the
'''
observed_arr = self.__setup_dataset(sentence_list, token_master_list)
self.__logger.debug("Shape of observed data points:")
self.__logger.debug(observed_arr.shape)
# Init.
encoder_graph = EncoderGraph()
# Activation function in LSTM.
encoder_graph.observed_activating_function = LogisticFunction()
encoder_graph.input_gate_activating_function = LogisticFunction()
encoder_graph.forget_gate_activating_function = LogisticFunction()
encoder_graph.output_gate_activating_function = LogisticFunction()
encoder_graph.hidden_activating_function = LogisticFunction()
encoder_graph.output_activating_function = LogisticFunction()
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
encoder_graph.create_rnn_cells(
input_neuron_count=observed_arr.shape[-1],
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=observed_arr.shape[-1])
# Init.
decoder_graph = DecoderGraph()
# Activation function in LSTM.
decoder_graph.observed_activating_function = LogisticFunction()
decoder_graph.input_gate_activating_function = LogisticFunction()
decoder_graph.forget_gate_activating_function = LogisticFunction()
decoder_graph.output_gate_activating_function = LogisticFunction()
decoder_graph.hidden_activating_function = LogisticFunction()
decoder_graph.output_activating_function = LogisticFunction()
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
decoder_graph.create_rnn_cells(
input_neuron_count=hidden_neuron_count,
hidden_neuron_count=observed_arr.shape[-1],
output_neuron_count=hidden_neuron_count)
encoder_opt_params = EncoderAdam()
encoder_opt_params.weight_limit = weight_limit
encoder_opt_params.dropout_rate = dropout_rate
encoder = Encoder(
# Delegate `graph` to `LSTMModel`.
graph=encoder_graph,
# The number of epochs in mini-batch training.
epochs=epochs,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=learning_rate,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=learning_attenuate_rate,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=attenuate_epoch,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=bptt_tau,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=test_size_rate,
# Loss function.
computable_loss=MeanSquaredError(),
# Optimizer.
opt_params=encoder_opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation(),
tol=0.0)
decoder_opt_params = DecoderAdam()
decoder_opt_params.weight_limit = weight_limit
decoder_opt_params.dropout_rate = dropout_rate
decoder = Decoder(
# Delegate `graph` to `LSTMModel`.
graph=decoder_graph,
# The number of epochs in mini-batch training.
epochs=epochs,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=learning_rate,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=learning_attenuate_rate,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=attenuate_epoch,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=bptt_tau,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=test_size_rate,
# Loss function.
computable_loss=MeanSquaredError(),
# Optimizer.
opt_params=decoder_opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation(),
tol=0.0)
encoder_decoder_controller = EncoderDecoderController(
encoder=encoder,
decoder=decoder,
epochs=epochs,
batch_size=batch_size,
learning_rate=learning_rate,
learning_attenuate_rate=learning_attenuate_rate,
attenuate_epoch=attenuate_epoch,
test_size_rate=test_size_rate,
computable_loss=MeanSquaredError(),
verificatable_result=VerificateFunctionApproximation(),
tol=0.0)
# Learning.
encoder_decoder_controller.learn(observed_arr, observed_arr)
self.__controller = encoder_decoder_controller
self.__token_master_list = token_master_list
def __build_encoder_decoder_controller(
self,
input_neuron_count=20,
hidden_neuron_count=20,
weight_limit=0.5,
dropout_rate=0.5,
epochs=1000,
batch_size=20,
learning_rate=1e-05,
attenuate_epoch=50,
learning_attenuate_rate=0.1,
seq_len=8,
bptt_tau=8,
test_size_rate=0.3,
tol=1e-10,
tld=100.0
):
encoder_graph = EncoderGraph()
encoder_graph.observed_activating_function = LogisticFunction()
encoder_graph.input_gate_activating_function = LogisticFunction()
encoder_graph.forget_gate_activating_function = LogisticFunction()
encoder_graph.output_gate_activating_function = LogisticFunction()
encoder_graph.hidden_activating_function = LogisticFunction()
encoder_graph.output_activating_function = LogisticFunction()
encoder_graph.create_rnn_cells(
input_neuron_count=input_neuron_count,
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=1
)
encoder_opt_params = EncoderAdam()
encoder_opt_params.weight_limit = weight_limit
encoder_opt_params.dropout_rate = dropout_rate
encoder = Encoder(
graph=encoder_graph,
epochs=100,
batch_size=batch_size,
learning_rate=learning_rate,
learning_attenuate_rate=0.1,
attenuate_epoch=50,
bptt_tau=8,
test_size_rate=0.3,
computable_loss=MeanSquaredError(),
opt_params=encoder_opt_params,
verificatable_result=VerificateFunctionApproximation(),
tol=tol,
tld=tld
)
decoder_graph = DecoderGraph()
decoder_graph.observed_activating_function = LogisticFunction()
decoder_graph.input_gate_activating_function = LogisticFunction()
decoder_graph.forget_gate_activating_function = LogisticFunction()
decoder_graph.output_gate_activating_function = LogisticFunction()
decoder_graph.hidden_activating_function = LogisticFunction()
decoder_graph.output_activating_function = SoftmaxFunction()
decoder_graph.create_rnn_cells(
input_neuron_count=hidden_neuron_count,
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=input_neuron_count
)
decoder_opt_params = DecoderAdam()
decoder_opt_params.weight_limit = weight_limit
decoder_opt_params.dropout_rate = dropout_rate
decoder = Decoder(
graph=decoder_graph,
epochs=100,
batch_size=batch_size,
learning_rate=learning_rate,
learning_attenuate_rate=0.1,
attenuate_epoch=50,
seq_len=seq_len,
bptt_tau=bptt_tau,
test_size_rate=0.3,
computable_loss=MeanSquaredError(),
opt_params=decoder_opt_params,
verificatable_result=VerificateFunctionApproximation()
)
encoder_decoder_controller = EncoderDecoderController(
encoder=encoder,
decoder=decoder,
epochs=epochs,
batch_size=batch_size,
learning_rate=learning_rate,
learning_attenuate_rate=learning_attenuate_rate,
attenuate_epoch=attenuate_epoch,
test_size_rate=test_size_rate,
computable_loss=MeanSquaredError(),
verificatable_result=VerificateFunctionApproximation(),
tol=tol,
tld=tld
)
return encoder_decoder_controller
def __init__(self,
lstm_model=None,
batch_size=20,
input_neuron_count=100,
hidden_neuron_count=300,
hidden_activating_function=None,
seq_len=10,
learning_rate=1e-05,
verbose_mode=False):
'''
Init.
Args:
lstm_model: is-a `lstm_model`.
batch_size: Batch size.
This parameters will be refered only when `lstm_model` is `None`.
input_neuron_count: The number of input units.
This parameters will be refered only when `lstm_model` is `None`.
hidden_neuron_count: The number of hidden units.
This parameters will be refered only when `lstm_model` is `None`.
hidden_activating_function: is-a `ActivatingFunctionInterface` in hidden layer.
This parameters will be refered only when `lstm_model` is `None`.
seq_len: The length of sequences.
This means refereed maxinum step `t` in feedforward.
learning_rate: Learning rate.
verbose_mode: Verbose mode or not.
'''
logger = getLogger("pydbm")
handler = StreamHandler()
if verbose_mode is True:
handler.setLevel(DEBUG)
logger.setLevel(DEBUG)
else:
handler.setLevel(ERROR)
logger.setLevel(ERROR)
logger.addHandler(handler)
if lstm_model is not None:
if isinstance(lstm_model, LSTM) is False:
raise TypeError()
else:
# Init.
graph = LSTMGraph()
# Activation function in LSTM.
graph.observed_activating_function = TanhFunction()
graph.input_gate_activating_function = LogisticFunction()
graph.forget_gate_activating_function = LogisticFunction()
graph.output_gate_activating_function = LogisticFunction()
if hidden_activating_function is None:
graph.hidden_activating_function = TanhFunction()
else:
if isinstance(hidden_activating_function,
ActivatingFunctionInterface) is False:
raise TypeError()
graph.hidden_activating_function = hidden_activating_function
graph.output_activating_function = TanhFunction()
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
graph.create_rnn_cells(input_neuron_count=input_neuron_count,
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=1)
opt_params = SGD()
opt_params.weight_limit = 0.5
opt_params.dropout_rate = 0.0
lstm_model = LSTM(
# Delegate `graph` to `LSTMModel`.
graph=graph,
# The number of epochs in mini-batch training.
epochs=100,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=1e-05,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=0.1,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=50,
# The length of sequences.
seq_len=seq_len,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=seq_len,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=0.3,
# Loss function.
computable_loss=MeanSquaredError(),
# Optimizer.
opt_params=opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation(),
tol=0.0)
self.__lstm_model = lstm_model
self.__seq_len = seq_len
self.__learning_rate = learning_rate
self.__verbose_mode = verbose_mode
self.__loss_list = []
def __build_encoder_decoder_controller(self,
input_neuron_count=20,
hidden_neuron_count=20,
weight_limit=0.5,
dropout_rate=0.5,
epochs=1000,
batch_size=20,
learning_rate=1e-05,
attenuate_epoch=50,
learning_attenuate_rate=0.1,
seq_len=8,
bptt_tau=8,
test_size_rate=0.3,
tol=1e-10,
tld=100.0):
# Init.
encoder_graph = EncoderGraph()
# Activation function in LSTM.
encoder_graph.observed_activating_function = LogisticFunction()
encoder_graph.input_gate_activating_function = LogisticFunction()
encoder_graph.forget_gate_activating_function = LogisticFunction()
encoder_graph.output_gate_activating_function = LogisticFunction()
encoder_graph.hidden_activating_function = LogisticFunction()
encoder_graph.output_activating_function = LogisticFunction()
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
encoder_graph.create_rnn_cells(input_neuron_count=input_neuron_count,
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=1)
encoder_opt_params = EncoderAdam()
encoder_opt_params.weight_limit = weight_limit
encoder_opt_params.dropout_rate = dropout_rate
encoder = Encoder(
# Delegate `graph` to `LSTMModel`.
graph=encoder_graph,
# The number of epochs in mini-batch training.
epochs=100,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=learning_rate,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=0.1,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=50,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=8,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=0.3,
# Loss function.
computable_loss=MeanSquaredError(),
# Optimizer.
opt_params=encoder_opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation())
# Init.
decoder_graph = DecoderGraph()
# Activation function in LSTM.
decoder_graph.observed_activating_function = LogisticFunction()
decoder_graph.input_gate_activating_function = LogisticFunction()
decoder_graph.forget_gate_activating_function = LogisticFunction()
decoder_graph.output_gate_activating_function = LogisticFunction()
decoder_graph.hidden_activating_function = LogisticFunction()
decoder_graph.output_activating_function = SoftmaxFunction()
# Initialization strategy.
# This method initialize each weight matrices and biases in Gaussian distribution: `np.random.normal(size=hoge) * 0.01`.
decoder_graph.create_rnn_cells(input_neuron_count=hidden_neuron_count,
hidden_neuron_count=hidden_neuron_count,
output_neuron_count=input_neuron_count)
decoder_opt_params = DecoderAdam()
decoder_opt_params.weight_limit = weight_limit
decoder_opt_params.dropout_rate = dropout_rate
decoder = Decoder(
# Delegate `graph` to `LSTMModel`.
graph=decoder_graph,
# The number of epochs in mini-batch training.
epochs=100,
# The batch size.
batch_size=batch_size,
# Learning rate.
learning_rate=learning_rate,
# Attenuate the `learning_rate` by a factor of this value every `attenuate_epoch`.
learning_attenuate_rate=0.1,
# Attenuate the `learning_rate` by a factor of `learning_attenuate_rate` every `attenuate_epoch`.
attenuate_epoch=50,
# The length of sequences.
seq_len=seq_len,
# Refereed maxinum step `t` in BPTT. If `0`, this class referes all past data in BPTT.
bptt_tau=bptt_tau,
# Size of Test data set. If this value is `0`, the validation will not be executed.
test_size_rate=0.3,
# Loss function.
computable_loss=MeanSquaredError(),
# Optimizer.
opt_params=decoder_opt_params,
# Verification function.
verificatable_result=VerificateFunctionApproximation())
encoder_decoder_controller = EncoderDecoderController(
encoder=encoder,
decoder=decoder,
epochs=epochs,
batch_size=batch_size,
learning_rate=learning_rate,
learning_attenuate_rate=learning_attenuate_rate,
attenuate_epoch=attenuate_epoch,
test_size_rate=test_size_rate,
computable_loss=MeanSquaredError(),
verificatable_result=VerificateFunctionApproximation(),
tol=tol,
tld=tld)
return encoder_decoder_controller