def res(x):
x = ResidualStart()(x)
x1 = Conv2D(f, 3, strides=1, padding='same')(x)
x1 = BatchNormalization()(x1)
x1 = Lambda(activation)(x1)
x1 = Conv2D(f, 3, strides=1, padding='same')(x1)
x1 = BatchNormalization()(x1)
return Add()([x1, x])
def convolutional_block(X, f, filters, stage, block, s=2):
# defining name basis
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
F1, F2, F3 = filters
X_shortcut = X
X = Conv2D(F1, (1, 1),
strides=(s, s),
name=conv_name_base + '2a',
padding="valid",
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2a')(X)
X = Activation('relu')(X)
X = Conv2D(F2, (f, f),
strides=(1, 1),
padding='same',
name=conv_name_base + '2b',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2b')(X)
X = Activation('relu')(X)
X = Conv2D(F3, (1, 1),
strides=(1, 1),
padding='valid',
name=conv_name_base + '2c',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2c')(X)
X_shortcut = Conv2D(F3, (1, 1),
strides=(s, s),
padding='valid',
name=conv_name_base + '1',
kernel_initializer=glorot_uniform(seed=0))(X_shortcut)
X_shortcut = BatchNormalization(axis=3,
name=bn_name_base + '1')(X_shortcut)
X = Add()([X, X_shortcut])
X = Activation('relu')(X)
return X
def _conv_block(x, out_filters, bneck_filters, groups, kernel_size, strides):
scope = Scoping.get_global_scope()
if int(x.shape[-1]) != out_filters or strides > 1:
with scope.name_scope('shortcut'):
shortcut = _preact_conv(x, out_filters, 1, strides)
else:
shortcut = x
with scope.name_scope('in'):
pi = _preact_conv(x, bneck_filters, 1, 1)
with scope.name_scope('bneck'):
pi = _preact_conv(pi, bneck_filters, kernel_size, strides, groups)
with scope.name_scope('out'):
pi = _preact_conv(pi, out_filters, 1, 1)
x = Add(name=scope+'add_shortcut')([shortcut, pi])
return x
def identity_block(X, f, filters, stage, block):
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
F1, F2, F3 = filters
X_shortcut = X
X = Conv2D(filters=F1,
kernel_size=(1, 1),
strides=(1, 1),
padding='valid',
name=conv_name_base + '2a',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2a')(X)
X = Activation('relu')(X)
X = Conv2D(filters=F2,
kernel_size=(f, f),
strides=(1, 1),
padding='same',
name=conv_name_base + '2b',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2b')(X)
X = Activation('relu')(X)
X = Conv2D(filters=F3,
kernel_size=(1, 1),
strides=(1, 1),
padding='valid',
name=conv_name_base + '2c',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2c')(X)
X = Add()([X, X_shortcut])
X = Activation('relu')(X)
return X
def build(self):
gru = GRU(units=self.input_shape[-1],
return_sequences=False,
name='gru')
bn = BatchNormalization()
decoder_1 = Dense(units=128, activation='sigmoid', name='decoder-1')
decoder_2 = Dense(units=self.output_dim,
activation='sigmoid',
name='decoder-2')
self.layers.append(gru)
self.layers.append(decoder_1)
self.layers.append(decoder_2)
activations = {}
for i in range(self.historical_len):
s_input = self.input_s[i]
t_input = self.input_t[i]
if i == 0:
# hs = bn(s_input)
hs = gru(s_input)
activations['s-r-{}-o'.format(i)] = hs
hs = Reshape((1, -1))(hs)
activations['s-r-{}'.format(i)] = hs
# ht = bn(t_input)
ht = gru(t_input)
activations['t-r-{}-o'.format(i)] = ht
ht = Reshape((1, -1))(ht)
activations['t-r-{}'.format(i)] = ht
else:
# hs = bn(s_input)
hs = gru(
Add()([activations['s-r-{}-o'.format(i - 1)], s_input]))
activations['s-r-{}-o'.format(i)] = hs
hs = Reshape((1, -1))(hs)
activations['s-r-{}'.format(i)] = hs
# ht = bn(t_input)
ht = gru(
Add()([activations['t-r-{}-o'.format(i - 1)], t_input]))
activations['s-r-{}-o'.format(i)] = ht
ht = Reshape((1, -1))(ht)
activations['t-r-{}'.format(i)] = ht
for i in range(self.historical_len):
idx = self.historical_len - 1 - i
s_input = self.input_s[idx]
t_input = self.input_t[idx]
if i == 0:
# hs = bn(s_input)
hs = gru(s_input)
activations['s-l-{}-o'.format(i)] = hs
hs = Reshape((1, -1))(hs)
activations['s-l-{}'.format(i)] = hs
# ht = bn(t_input)
ht = gru(t_input)
activations['t-l-{}-o'.format(i)] = ht
ht = Reshape((1, -1))(ht)
activations['t-l-{}'.format(i)] = ht
else:
# hs = bn(s_input)
hs = gru(
Add()([activations['s-l-{}-o'.format(i - 1)], s_input]))
activations['s-l-{}-o'.format(i)] = hs
hs = Reshape((1, -1))(hs)
activations['s-l-{}'.format(i)] = hs
# ht = bn(t_input)
ht = gru(
Add()([activations['t-r-{}-o'.format(i - 1)], t_input]))
activations['s-l-{}-o'.format(i)] = ht
ht = Reshape((1, -1))(ht)
activations['t-l-{}'.format(i)] = ht
s_h_r = concatenate([
activations['s-r-{}'.format(i)] for i in range(self.historical_len)
],
axis=1)
s_h_l = concatenate([
activations['s-l-{}'.format(i)] for i in range(self.historical_len)
],
axis=1)
t_h_r = concatenate([
activations['t-r-{}'.format(i)] for i in range(self.historical_len)
],
axis=1)
t_h_l = concatenate([
activations['t-l-{}'.format(i)] for i in range(self.historical_len)
],
axis=1)
s_c = concatenate([s_h_r, s_h_l], axis=1)
t_c = concatenate([t_h_r, t_h_l], axis=1)
s_c = Activation('relu')(Reshape((-1, ))(s_c))
t_c = Activation('relu')(Reshape((-1, ))(t_c))
# diff = tf.square(tf.subtract(s_c, t_c))
# tmp = diff.get_shape().as_list()[-1]
# self.weight = RepeatVector(tmp)(self.weight)
# self.weight = tf.reshape(self.weight, [-1, tmp])
# self.diff = tf.multiply(diff, self.weight)
self.output_s = decoder_2(decoder_1(s_c))
self.output_t = decoder_2(decoder_1(t_c))
self.variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
self.vars = {var.name: var for var in self.variables}
self._loss()
self._gradients()
self.opt_op = self.optimizer.minimize(self.loss)
from tensorflow.contrib.keras.api.keras.layers import Conv2D, MaxPooling2D, Flatten
from tensorflow.contrib.keras.api.keras.layers import Input, LSTM, Embedding, Dense, concatenate
from tensorflow.contrib.keras.api.keras.layers import Input, LSTM, Embedding, Dense, concatenate, Add
#from keras.layers import Conv2D, MaxPooling2D, Flatten, Layer
#from keras.layers import Input, LSTM, Embedding, Dense, concatenate
from tensorflow.contrib.keras.api.keras.models import Model, Sequential
from tensorflow.python.layers.base import Layer
input1 = Input(shape=(16,))
x1 = Dense(8, activation='relu')(input1)
input2 = Input(shape=(32,))
x2 = Dense(8, activation='relu')(input2)
added = Add()([x1, x2]) # equivalent to added = keras.layers.add([x1, x2])
print("")
print("")
print("---- iterate inbound nodes and tensors ----")
print("")
print("")
print("added")
for n in added.inbound_nodes:
print("")
print("In-Node ", id(n), n.get_config())
for n in added.outbound_nodes:
print("")
print("Out-Node ", id(n), n.get_config())
out = Dense(4)(added)
model = Model(inputs=[input1, input2], outputs=out)