def __init__(self, output_size, input_size=None, ignore_bias=False, initializer=GlorotNormal(),
weight_decay=0):
self._size_o = output_size
self._initializer = initializer
self._ignore_bias = ignore_bias
self._weight_decay = weight_decay
super(Gru, self).__init__(input_size)
def __init__(self,
output_size,
input_size=None,
initializer=GlorotNormal()):
self._output_size = output_size
self._initializer = initializer
super(Weighted_test_model, self).__init__(input_size)
def __init__(self,
output_size,
input_size=None,
initializer=GlorotNormal()):
self._size_o = output_size
self._initializer = initializer
super(PeepholeLstm, self).__init__(input_size)
def __init__(self,
output_size,
input_size=None,
initializer=GlorotNormal()):
self._output_size = output_size
self._initializer = initializer
super(Embedding, self).__init__(input_size)
def __init__(self,
channel=32,
filter=3,
padding=0,
stride=1,
input_size=None,
initializer=GlorotNormal()):
self._padding, self._stride, self._kernel = (tuplize(x)
for x in (padding, stride,
filter))
self._channel = channel
self._initializer = initializer
super(Conv2d, self).__init__(input_size)
def __init__(self,
input_size=None,
momentum=0.99,
mode="activation",
epsilon=1e-5,
initializer=GlorotNormal()):
self._mov_mean = 0
self._mov_std = 0
self._epsilon = epsilon
self._momentum = momentum
self._mode = mode_dict.get(mode, BATCH_NORMALIZE_ELEMENTWISE)
self.inference = False
self._initializer = initializer
super(BatchNormalize, self).__init__(input_size)
def __init__(self,
channel=32,
filter=3,
padding=0,
stride=1,
dilation=1,
input_size=None,
ignore_bias=False,
initializer=GlorotNormal(),
weight_decay=0):
self._padding, self._stride, self._kernel, self._dilation = (
tuplize(x) for x in (padding, stride, filter, dilation))
self._channel = channel
self._ignore_bias = ignore_bias
self._initializer = initializer
self._weight_decay = weight_decay
super(Conv2d, self).__init__(input_size)
def __init__(self,
input_size=None,
momentum=0.99,
mode="activation",
epsilon=1e-5,
ignore_bias=False,
initializer=GlorotNormal(),
weight_decay=0):
assert momentum > 0, "The value of momentum must be lager than 0."
self._mov_mean = 0
self._mov_std = 0
self._epsilon = epsilon
self._momentum = momentum
self._mode = mode_dict.get(mode, BATCH_NORMALIZE_ELEMENTWISE)
self.inference = False
self._ignore_bias = ignore_bias
self._initializer = initializer
self._weight_decay = weight_decay
super(BatchNormalize, self).__init__(input_size)
def __init__(self,
channel=32,
filter=3,
padding=0,
stride=1,
dilation=1,
groups=1,
input_size=None,
ignore_bias=False,
initializer=GlorotNormal(),
weight_decay=0):
self._padding, self._stride, self._kernel, self._dilation = (
tuplize(x) for x in (padding, stride, filter, dilation))
self._channel = channel
self._groups = groups
#print("self._groups: ", self._groups)
assert isinstance(
self._groups, int
) and self._groups > 0, "Please set groups to integer greater than 0"
self._ignore_bias = ignore_bias
self._initializer = initializer
self._weight_decay = weight_decay
super(GroupConv2d, self).__init__(input_size)
def __init__(self, output_size, initializer=GlorotNormal()):
self._size_o = output_size
self._initializer = initializer
def __init__(self, output_size, input_size, initializer=GlorotNormal(), weight_decay=None):
self._output_size = output_size
self._initializer = initializer
self._weight_decay = weight_decay
super(Embedding, self).__init__(input_size)