def __init__(self, name):
# Call parent's constructor
Net.__init__(self, name)
# Attributes
self._inter_type = self.RECURRENT
self._train_state_buffer = None
self._eval_state_buffer = None
self._state_size = None
self._init_state = None
self._weights = None
self._bias = None
self._weight_initializer = None
self._bias_initializer = None
# For real-time training TODO: BETA
self.repeater_tensors = None # registered in sub-classes
self._grad_tensors = None
self._new_state_tensor = None #
self._gradient_buffer_placeholder = None
self._gradient_buffer_array = None
self._custom_vars = None
# Gate activations should be registered here
self._gate_dict = OrderedDict()
def __init__(self, name):
# Call parent's constructor
Net.__init__(self, name)
# Attributes
self._inter_type = self.RECURRENT
self._state_array = None
self._state_size = None
self._init_state = None
self._kernel = None
self._bias = None
self._weight_initializer = None
self._bias_initializer = None
def __init__(self, mark=None, **kwargs):
# Call parent's initializer
Model.__init__(self, mark)
Net.__init__(self, 'Bamboo_Broad_Net', inter_type=pedia.fork)
assert self._inter_type == pedia.fork
self.outputs = None
# Private fields
self._losses = []
self._metrics = []
self._train_ops = []
self._var_list = []
self._output_list = []
self._branch_index = 0
self._identity_initial = kwargs.get('ientity', False)
def __init__(self,
z_dim=None,
sample_shape=None,
output_shape=None,
mark=None,
classes=0):
# Call parent's constructor
Model.__init__(self, mark)
self._targets = None
self._conditional = classes > 0
self._classes = classes
if self._conditional:
with self._graph.as_default():
self._targets = tf.placeholder(dtype=tf.float32,
shape=[None, classes],
name='one_hot_labels')
# Define generator and discriminator
self.Generator = Net(pedia.Generator)
self.Discriminator = Net(pedia.Discriminator)
# Alias
self.G = self.Generator
self.D = self.Discriminator
# If z_dim/sample_shape is provided, define the input for
# generator/discriminator accordingly
if z_dim is not None:
self.G.add(Input(sample_shape=[None, z_dim], name='z'))
if sample_shape is not None:
if (not isinstance(sample_shape, list)
and not isinstance(sample_shape, tuple)):
raise TypeError('sample shape must be a list or a tuple')
self.D.add(
Input(sample_shape=[None] + list(sample_shape),
name='samples'))
self._z_dim = z_dim
self._sample_shape = sample_shape
self._output_shape = output_shape
self._sample_num = None
# Private tensors and ops
self._G, self._outputs = None, None
self._Dr, self._Df = None, None
self._logits_Dr, self._logits_Df = None, None
self._loss_G, self._loss_D = None, None
self._loss_Dr, self._loss_Df = None, None
self._train_step_G, self._train_step_D = None, None
self._merged_summary_G, self._merged_summary_D = None, None
def _init_T(self):
# Add empty nets to each degree
for n in self.orders:
self.T[n] = Net('T{}'.format(n))
self.T[n].add(self._input)
# Initialize volterra part
for order in range(1, self._max_volterra_order + 1):
self.T[order].add(Homogeneous(order))
def __init__(self,
z_dim=None,
sample_shape=None,
output_shape=None,
mark=None,
classes=0):
# Call parent's constructor
Model.__init__(self, mark)
# Fields
self._output_shape = output_shape
# Define encoder and decoder
self.Encoder = Net(pedia.Encoder)
self.Decoder = Net(pedia.Decoder)
self.Q = self.Encoder
self.P = self.Decoder
# If z_dim/sample_shape is provided, define the input for
# decoder/encoder accordingly
if z_dim is not None:
self.P.add(Input(sample_shape=[None, z_dim], name='z'))
if sample_shape is not None:
if (not isinstance(sample_shape, list)
and not isinstance(sample_shape, tuple)):
raise TypeError('sample shape must be a list or a tuple')
self.Q.add(
Input(sample_shape=[None] + list(sample_shape),
name='samples'))
# Placeholders
self._sample_num = None
self._classes = classes
self._conditional = classes > 0
if self._conditional:
self._targets = tf.placeholder(dtype=tf.float32,
shape=[None, classes],
name='one_hot_labels')
self._P, self._outputs = None, None
# ...
pass
def __init__(self, mark=None):
Model.__init__(self, mark)
Net.__init__(self, 'FeedforwardNet')
self.superior = self
self._default_net = self
def __init__(self, mark=None):
Model.__init__(self, mark)
Net.__init__(self, 'FeedforwardNet')
self.outputs = None
