Package dimer :: Package nnet :: Module nccn :: Class ConvPoolLayer
[hide private]
[frames] | no frames]

Class ConvPoolLayer

source code

object --+        
         |        
     Layer --+    
             |    
    SpeedLayer --+
                 |
                ConvPoolLayer

LeNet conv-pool layer

Nested Classes [hide private]

Inherited from Layer: __metaclass__

Instance Methods [hide private]
 
__init__(self, X, fshape, ishape, rng, poolsize, dtype)
Le Cun convolutional layer
source code
 
activation(self)
activation function
source code
 
__str__(self)
in_fature_maps -> nr_of_kern (receprive_field_size (wXh) / pool_size(wXh)) ->
source code

Inherited from SpeedLayer: get_params, get_speeds, set_params, set_speeds, speed_update, weight_update

Inherited from Layer: get_flat_weights, get_weights, load_flat_weights, set_weights, weight_norm

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __subclasshook__

Class Methods [hide private]

Inherited from SpeedLayer (private): _speed_update_f, _weight_update_f

Class Variables [hide private]
  __abstractmethods__ = frozenset([])
Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__init__(self, X, fshape, ishape, rng, poolsize, dtype)
(Constructor)

source code 

Le Cun convolutional layer

fshape: (# filters, # in_feature_maps, width, height) ishape: (batch_size, # feature_maps, width, height)

Parameters:
  • wshape_lst - shapes of weights
  • wnames - names of weights
  • fanin_lst - fan in of weights
  • rng - a random number generator or init value (see alloc_shared_weights_)
  • wdtype - data type of weights.
Overrides: object.__init__

activation(self)

source code 

activation function

Overrides: Layer.activation

__str__(self)
(Informal representation operator)

source code 

in_fature_maps -> nr_of_kern (receprive_field_size (wXh) / pool_size(wXh)) ->

Overrides: object.__str__