API reference, deeppy.feedforward¶
Neural network¶
Layers¶
-
class
deeppy.feedforward.layers.
FullyConnected
(n_out, weights, bias=0.0)[source]¶ Bases:
deeppy.feedforward.layers.Layer
,deeppy.base.ParamMixin
-
class
deeppy.feedforward.layers.
Layer
[source]¶ Bases:
deeppy.base.PickleMixin
-
bprop_to_x
= True¶
-
-
class
deeppy.feedforward.layers.
PReLU
(a=0.25)[source]¶ Bases:
deeppy.feedforward.layers.Layer
,deeppy.base.ParamMixin
Convnet layers¶
-
class
deeppy.feedforward.convnet_layers.
Convolution
(n_filters, filter_shape, weights, bias=0.0, strides=(1, 1), border_mode='valid')[source]¶ Bases:
deeppy.feedforward.layers.Layer
,deeppy.base.ParamMixin
-
class
deeppy.feedforward.convnet_layers.
LocalContrastNormalization
(kernel, eps=0.1, strides=(1, 1))[source]¶
-
class
deeppy.feedforward.convnet_layers.
LocalResponseNormalization
(alpha=0.0001, beta=0.75, n=5, k=1)[source]¶
Dropout layers¶
-
class
deeppy.feedforward.dropout_layers.
Dropout
(dropout=0.5)[source]¶ Bases:
deeppy.feedforward.layers.Layer
,deeppy.base.PhaseMixin
-
class
deeppy.feedforward.dropout_layers.
DropoutFullyConnected
(n_out, weights, bias=0.0, dropout=0.5)[source]¶ Bases:
deeppy.feedforward.layers.FullyConnected
,deeppy.base.PhaseMixin