neon.initializers.initializer.Orthonormal

class neon.initializers.initializer.Orthonormal(scale=1.1, name='orthonormal')[source]

Bases: neon.initializers.initializer.Initializer

Initializes parameters with the single value decomposition of a random gaussian matrix.

Implementation taken from Lasagne. Reference: Saxe et al., http://arxiv.org/abs/1312.6120

__init__(scale=1.1, name='orthonormal')[source]

Class constructor.

Parameters:
  • scale (float, optional) – Scaling factor of values. Defaults to 1.1.
  • name (string, optional) – Name to assign an instance of this class.

Methods

__init__([scale, name]) Class constructor.
fill(param) Fill the provided tensor using the Orthonormal method.
gen_class(pdict)
get_description([skip]) Returns a dict that contains all necessary information needed to serialize this object.
recursive_gen(pdict, key) helper method to check whether the definition
be = None
classnm

Returns the class name.

fill(param)[source]

Fill the provided tensor using the Orthonormal method.

Parameters:params (tensor) – Tensor to fill
gen_class(pdict)
get_description(skip=[], **kwargs)

Returns a dict that contains all necessary information needed to serialize this object.

Parameters:skip (list) – Objects to omit from the dictionary.
Returns:Dictionary format for object information.
Return type:(dict)
modulenm

Returns the full module path.

recursive_gen(pdict, key)

helper method to check whether the definition dictionary is defining a NervanaObject child, if so it will instantiate that object and replace the dictionary element with an instance of that object