XavierNormalWeightInitializer¶
-
class
XavierNormalWeightInitializer¶ Bases:
bluebird.weight_initializers.WeightInitializerUses Xavier uniform initialization, weights are normaly distributed. Xavier ensures small variance.
Example:
weight_init = XavierNormalWeightInitializer() w = weight_init.init((10, 20))
-
__init__()¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__()Initialize self.
init(dimension)Initializes the weights.
-
init(dimension: Tuple) → numpy.ndarray¶ Initializes the weights.
- Parameters
dimension (Tuple) – dimensions of weights in a network (input, output)
- Returns
Tensor with dimensions of (input, output)
- Return type
Tensor
-
