def __init__(self,
in_size,
out_size,
lateral_init=None,
upward_init=None,
bias_init=0,
forget_bias_init=0):
super(LSTMBase, self).__init__(
upward=linear.Linear(in_size, 4 * out_size, initialW=0),
lateral=linear.Linear(out_size,
4 * out_size,
initialW=0,
nobias=True),
)
self.state_size = out_size
for i in six.moves.range(0, 4 * out_size, out_size):
initializers.init_weight(self.lateral.W.data[i:i + out_size, :],
lateral_init)
initializers.init_weight(self.upward.W.data[i:i + out_size, :],
upward_init)
a, i, f, o = lstm._extract_gates(
self.upward.b.data.reshape(1, 4 * out_size, 1))
initializers.init_weight(a, bias_init)
initializers.init_weight(i, bias_init)
initializers.init_weight(f, forget_bias_init)
initializers.init_weight(o, bias_init)
def _initialize_params(self):
bias_initializer = initializers.Zero()
self.add_param('b', self.state_size*4, initializer=bias_initializer)
a, i, f, o = lstm._extract_gates(self.b.data.reshape(1, 4 * self.state_size, 1))
initializers.init_weight(a, self.bias_init)
initializers.init_weight(i, self.bias_init)
initializers.init_weight(f, self.forget_bias_init)
initializers.init_weight(o, self.bias_init)
def _initialize_params(self):
for i in six.moves.range(0, 4 * self.state_size, self.state_size):
initializers.init_weight(
self.lateral.W.data[i:i + self.state_size, :],
self.lateral_init)
initializers.init_weight(
self.upward.W.data[i:i + self.state_size, :], self.upward_init)
a, i, f, o = lstm._extract_gates(
self.upward.b.data.reshape(1, 4 * self.state_size, 1))
initializers.init_weight(a, self.bias_init)
initializers.init_weight(i, self.bias_init)
initializers.init_weight(f, self.forget_bias_init)
initializers.init_weight(o, self.bias_init)
def _initialize_params(self):
lateral_init = initializers._get_initializer(self.lateral_init)
upward_init = initializers._get_initializer(self.upward_init)
bias_init = initializers._get_initializer(self.bias_init)
forget_bias_init = initializers._get_initializer(self.forget_bias_init)
for i in six.moves.range(0, 4 * self.state_size, self.state_size):
lateral_init(self.lateral.W.array[i:i + self.state_size, :])
upward_init(self.upward.W.array[i:i + self.state_size, :])
a, i, f, o = lstm._extract_gates(
self.upward.b.array.reshape(1, 4 * self.state_size, 1))
bias_init(a)
bias_init(i)
forget_bias_init(f)
bias_init(o)
def _initialize_params(self):
lateral_init = initializers._get_initializer(self.lateral_init)
upward_init = initializers._get_initializer(self.upward_init)
bias_init = initializers._get_initializer(self.bias_init)
forget_bias_init = initializers._get_initializer(self.forget_bias_init)
for i in six.moves.range(0, 4 * self.state_size, self.state_size):
lateral_init(self.lateral.W.data[i:i + self.state_size, :])
upward_init(self.upward.W.data[i:i + self.state_size, :])
a, i, f, o = lstm._extract_gates(
self.upward.b.data.reshape(1, 4 * self.state_size, 1))
bias_init(a)
bias_init(i)
forget_bias_init(f)
bias_init(o)
def __init__(self, in_size, out_size,
lateral_init=None, upward_init=None,
bias_init=0, forget_bias_init=0):
super(LSTMBase, self).__init__(
upward=linear.Linear(in_size, 4 * out_size, initialW=0),
lateral=linear.Linear(out_size, 4 * out_size,
initialW=0, nobias=True),
)
self.state_size = out_size
for i in six.moves.range(0, 4 * out_size, out_size):
initializers.init_weight(
self.lateral.W.data[i:i + out_size, :], lateral_init)
initializers.init_weight(
self.upward.W.data[i:i + out_size, :], upward_init)
a, i, f, o = lstm._extract_gates(
self.upward.b.data.reshape(1, 4 * out_size, 1))
initializers.init_weight(a, bias_init)
initializers.init_weight(i, bias_init)
initializers.init_weight(f, forget_bias_init)
initializers.init_weight(o, bias_init)
def split_clstm(var):
return [chainer.Variable(m[0]) for m in _extract_gates(var.data[None, :])]
