def _setOutputs(self):
from theano.tensor.nnet import conv
for layer in self.network.inConnections[self]:
if self.inputs is None:
self.inputs = layer.outputs
else:
self.inputs += layer.outputs
if self.filterHeight > self.inputHeight:
raise ValueError(
"Filter height for '%s' cannot be bigger than its input height: '%s' > '%s'"
% (self.name, self.filterHeight, self.inputHeight))
if self.filterWidth > self.inputWidth:
raise ValueError(
"Filter width for '%s' cannot be bigger than its input width: '%s' > '%s'"
% (self.name, self.filterWidth, self.inputWidth))
self.convolution = conv.conv2d(
input=self.inputs,
filters=self.W,
filter_shape=self.getParameterShape('W'))
self.pooled = self.pooler.apply(self)
self.nbFlatOutputs = self.nbChannels * self.height * self.width
if self.b is None:
MI.ZerosBias().apply(self)
self.b = self.b.dimshuffle('x', 0, 'x', 'x')
self.outputs = self.pooled + self.b
self.testOutputs = self.pooled + self.b
def __init__(self,
WInitialization=MI.SmallUniformWeights(),
bInitialization=MI.ZerosBias(),
epsilon=1e-6):
Decorator_ABC.__init__(self)
self.epsilon = epsilon
self.WInitialization = WInitialization
self.bInitialization = bInitialization
self.W = None
self.b = None
self.paramShape = None
def __init__(self,
size,
layerType,
initializations=[MI.SmallUniformWeights(),
MI.ZerosBias()],
**kwargs):
super(WeightBias_ABC, self).__init__(size,
layerType=layerType,
initializations=initializations,
**kwargs)
self.W = None
self.b = None
def _setOutputs(self):
"""initializes weights and bias. By default weights are setup to random low values, use Mariana decorators
to change this behaviour."""
for layer in self.network.inConnections[self]:
if self.inputs is None:
self.inputs = layer.outputs
else:
self.inputs += layer.outputs
if self.W is None:
raise ValueError(
"No initialization was defined for weights (self.W)")
if self.b is None:
MI.ZerosBias().apply(self)
self.outputs = tt.dot(self.inputs, self.W) + self.b
self.testOutputs = tt.dot(self.inputs, self.W) + self.b