y = y[indices]
# Explicitly set apart 10% for validation data that we never train over
split_at = len(X) - len(X) / 10
(X_train, X_val) = (slice_X(X, 0, split_at), slice_X(X, split_at))
(y_train, y_val) = (y[:split_at], y[split_at:])
print(X_train.shape)
print(y_train.shape)
print("Build model...")
model = Sequential()
# "Encode" the input sequence using an RNN, producing an output of HIDDEN_SIZE
# note: in a situation where your input sequences have a variable length,
# use input_shape=(None, nb_feature).
model.add(RNN(HIDDEN_SIZE, input_shape=(MAXLEN, convertor.get_dim())))
# For the decoder's input, we repeat the encoded input for each time step
model.add(RepeatVector(DIGITS + 1))
# The decoder RNN could be multiple layers stacked or a single keras_layer
for _ in range(LAYERS):
model.add(RNN(HIDDEN_SIZE, return_sequences=True))
# For each of step of the output sequence, decide which character should be chosen
model.add(TimeDistributedDense(convertor.get_dim()))
model.add(Activation("softmax"))
model.compile(loss="categorical_crossentropy", optimizer="adam")
# Train the model each generation and show predictions against the validation dataset
for iteration in range(1, 200):
print()
D_y = D_y[indices]
# Explicitly set apart 10% for validation data that we never train over
split_at = len(D_X) - len(D_X) / 10
(D_X_train, D_X_val) = (slice_X(D_X, 0, split_at), slice_X(D_X, split_at))
(D_y_train, D_y_val) = (D_y[:split_at], D_y[split_at:])
print(D_X_train.shape)
print(D_y_train.shape)
import dlx.unit.core as U
import dlx.unit.recurrent as R
from dlx.model import Model
print('Build model...')
input_dim = convertor.get_dim()
output_dim = convertor.get_dim()
hidden_dim = HIDDEN_SIZE
input_length = MAXLEN
output_length = DIGITS + 1
'''Define Units'''
#Data uayer
data = U.Input(3, 'X')
#RNN encoder
encoder = R.RNN(input_length, input_dim, hidden_dim, name='ENCODER')
#encoder = R.LSTM(input_length, input_dim, hidden_dim, name='ENCODER')
#RNN decoder
decoder = R.RNN(output_length, hidden_dim, hidden_dim, name='DECODER')
#decoder = R.LSTM(output_length, hidden_dim, hidden_dim, name='DECODER')
#Time Distributed Dense
tdd = U.TimeDistributedDense(output_length, hidden_dim, output_dim, 'TDD')
print("Vectorization...")
convertor = CharacterDataEngine(chars, maxlen=len(chars) - 1)
initial_value = convertor.encode_dataset(starts, maxlen=1)
y = convertor.encode_dataset(chains)
split_at = len(y) - len(y) / 10
(y_train, y_val) = (y[:split_at], y[split_at:])
(i_train, i_val) = (initial_value[:split_at], initial_value[split_at:])
(X_train, X_val) = (y_train, y_val)
print(i_train.shape)
print(y_train.shape)
print("Build model...")
HIDDEN_SIZE = 128
BATCH_SIZE = 50
MAXLEN = len(chars) - 1
input_dim = convertor.get_dim()
rnn_layer = SimpleRNN(HIDDEN_SIZE, input_shape=(MAXLEN, convertor.get_dim()), return_sequences=True)
shift_layer = Shift(rnn_layer, initial_value)
model = Graph()
model.add_input(name="initial_value", input_shape=(1, input_dim))
model.add_input(name="sequence_input", input_shape=(MAXLEN, input_dim))
model.add_node(shift_layer, name="shift", input="sequence_input")
model.add_node(rnn_layer, name="rnn", input="shift")
model.add_node(TimeDistributedDense(input_dim), name="tdd", input="rnn")
model.add_node(Activation("softmax"), name="softmax", input="tdd")
model.add_output(name="output", input="softmax")
model.compile(loss={"output": "categorical_crossentropy"}, optimizer="adam")
for iteration in range(1, 200):
print()
print(D_X_train.shape)
print(D_y_train.shape)
import lx_layer.layer as L
import lx_layer.recurrent as R
import theano.printing as P
from keras import activations, objectives
from keras import models
from keras.optimizers import Adam
from keras import backend as K
from util import initializations
print("Build model...")
input_dim = convertor.get_dim()
output_dim = convertor.get_dim()
hidden_dim = HIDDEN_SIZE
input_length = MAXLEN
output_length = DIGITS + 1
"""Define functions"""
activation_softmax = activations.get("softmax")
activation_linear = activations.get("linear")
activation_hard_sigmoid = activations.get("hard_sigmoid")
activation_tanh = activations.get("tanh")
init_glorot_uniform = initializations.glorot_normal
init_orthogonal = initializations.orthogonal
forget_bias_init = initializations.one
"""Define layers"""
# Explicitly set apart 10% for validation data that we never train over
split_at = len(D_A) - len(D_A) / 10
(D_A_train, D_A_val) = (slice_X(D_A, 0, split_at), slice_X(D_A, split_at))
(D_B_train, D_B_val) = (slice_X(D_B, 0, split_at), slice_X(D_B, split_at))
(D_y_train, D_y_val) = (D_y[:split_at], D_y[split_at:])
print(D_A_train.shape)
print(D_B_train.shape)
print(D_y_train.shape)
import dlx.unit.core as U
import dlx.unit.attention as A
from dlx.model import Model
print('Build model...')
input_dim = convertor.get_dim() + MAXLEN
output_dim = convertor.get_dim()
hidden_dim = HIDDEN_SIZE
output_length = MAXLEN
attention_hidden_dim = HIDDEN_SIZE
'''Define Units'''
#Data unit
dataA = U.Input(3, 'A')
dataB = U.Input(3, 'B')
#Add Remove 1
add1 = U.AddOneAtBegin()
remove1 = U.RemoveOneAtBegin()
#Attention
decoder = A.AttentionLSTM_X(output_length + 1,
input_dim,
hidden_dim,
split_at = len(D_A) - len(D_A) / 10
(D_A_train, D_A_val) = (slice_X(D_A, 0, split_at), slice_X(D_A, split_at))
(D_B_train, D_B_val) = (slice_X(D_B, 0, split_at), slice_X(D_B, split_at))
(D_y_train, D_y_val) = (D_y[:split_at], D_y[split_at:])
print(D_A_train.shape)
print(D_B_train.shape)
print(D_y_train.shape)
import dlx.unit.core as U
import dlx.unit.attention as A
from dlx.model import Model
print("Build model...")
input_dim = convertor.get_dim() + MAXLEN
output_dim = convertor.get_dim()
hidden_dim = HIDDEN_SIZE
output_length = MAXLEN
attention_hidden_dim = HIDDEN_SIZE
"""Define Units"""
# Data unit
dataA = U.Input(3, "A")
dataB = U.Input(3, "B")
# Add Remove 1
add1 = U.AddOneAtBegin()
remove1 = U.RemoveOneAtBegin()
# Attention
decoder = A.AttentionLSTM_X(output_length + 1, input_dim, hidden_dim, input_dim, attention_hidden_dim, name="ATT")
# One to Many