def __init__(self, hidden_size):
super(Attention, self).__init__(
xh=L.Linear(in_size=None, out_size=hidden_size, initialW=GlorotNormal(), nobias=True),
hh=L.Linear(in_size=None, out_size=hidden_size, initialW=GlorotNormal(), nobias=True),
hw=L.Linear(hidden_size, 1, initialW=GlorotNormal(), nobias=True),
)
self.hidden_size = hidden_size
def __init__(self, item_size, hidden_size):
super(AttReDecoder, self).__init__(
re=L.Linear(None, 2, initialW=GlorotNormal(), nobias=True),
re_att=Attention(hidden_size),
r_att=Attention(hidden_size),
e_att=Attention(hidden_size),
fy=L.Linear(None, item_size, initialW=GlorotNormal(), nobias=True)
)
def __init__(self, hidden_size):
super(SelectiveGate, self).__init__(
xh=L.Linear(in_size=None,
out_size=hidden_size,
initialW=GlorotNormal(),
nobias=True),
hh=L.Linear(in_size=None,
out_size=hidden_size,
initialW=GlorotNormal(),
nobias=True),
)
self.hidden_size = hidden_size
def __init__(self, n_layers, in_size, out_size, dropout, use_bi_direction,
**kwargs):
argument.check_unexpected_kwargs(
kwargs,
use_cudnn='use_cudnn argument is not supported anymore. '
'Use chainer.using_config')
argument.assert_kwargs_empty(kwargs)
weights = []
direction = 2 if use_bi_direction else 1
for i in six.moves.range(n_layers):
for di in six.moves.range(direction):
weight = link.Link()
with weight.init_scope():
for j in six.moves.range(6):
if i == 0 and j < 3:
w_in = in_size
elif i > 0 and j < 3:
w_in = out_size * direction
else:
w_in = out_size
w = variable.Parameter(GlorotNormal(),
(out_size, w_in))
b = variable.Parameter(0, (out_size, ))
setattr(weight, 'w%d' % j, w)
setattr(weight, 'b%d' % j, b)
weights.append(weight)
super(NStepGRUBase, self).__init__(*weights)
self.n_layers = n_layers
self.dropout = dropout
self.out_size = out_size
self.direction = direction
self.rnn = rnn.n_step_bigru if use_bi_direction else rnn.n_step_gru
def __init__(self, item_size, embed_size, hidden_size):
super(NStepSelBiGRUEncoder, self).__init__(
xe=L.EmbedID(item_size, embed_size,initialW=GlorotNormal(), ignore_label=-1),
gru=NStepBiGRU(1, embed_size, hidden_size, 0.5),
sel=SelectiveGate(2 * hidden_size)
)
self.hidden_size = hidden_size
def __init__(self, output_dim, init_weights=False, filter_height=1):
super(Alex, self).__init__()
self.output_dim = output_dim
self.filter_height = filter_height
with self.init_scope():
if init_weights:
self.conv1 = L.Convolution2D(None, 96, (1, 3), 1, (0, 1), initialW=GlorotNormal())
self.conv2 = L.Convolution2D(None, 256, (filter_height, 3), 1, (0, 1), initialW=GlorotNormal())
self.conv3 = L.Convolution2D(None, 384, (1, 3), 1, (0, 1), initialW=GlorotNormal())
self.conv4 = L.Convolution2D(None, 384, (1, 3), 1, (0, 1), initialW=GlorotNormal())
self.conv5 = L.Convolution2D(None, 256, (1, 3), 1, (0, 1), initialW=GlorotNormal())
self.fc6 = L.Linear(None, 4096, initialW=HeNormal())
self.fc7 = L.Linear(None, 4096, initialW=HeNormal())
self.fc8 = L.Linear(None, output_dim, initialW=HeNormal())
else:
self.conv1 = L.Convolution2D(None, 96, (1, 3), 1, (0, 1))
self.conv2 = L.Convolution2D(None, 256, (filter_height, 3), 1, (0, 1))
self.conv3 = L.Convolution2D(None, 384, (1, 3), 1, (0, 1))
self.conv4 = L.Convolution2D(None, 384, (1, 3), 1, (0, 1))
self.conv5 = L.Convolution2D(None, 256, (1, 3), 1, (0, 1))
self.fc6 = L.Linear(None, 4096)
self.fc7 = L.Linear(None, 4096)
self.fc8 = L.Linear(None, output_dim)
def __init__(self, item_size):
super(GruDecoder, self).__init__(
fy=L.Linear(None, item_size, initialW=GlorotNormal(), nobias=True))