neuralogic.nn.init

class Normal

Bases: Initializer

Initializes learnable parameters with random samples from a normal (Gaussian) distribution

class Uniform(scale: float = 2)

Bases: Initializer

Initializes learnable parameters with random uniformly distributed samples from the interval [-scale / 2, scale / 2].

Parameters:

scale (float) – Scale of the distribution interval [-scale / 2, scale / 2]. Default: 2

get_settings() → Dict[str, Any]

class Constant(value: float = 0.1)

Bases: Initializer

Initializes learnable parameters with the value.

Parameters:

value (float) – Value to fill weights with. Default: 0.1

get_settings() → Dict[str, Any]

class Longtail

Bases: Initializer

Initializes learnable parameters with random samples from a long tail distribution

class Glorot(scale: float = 2)

Bases: Initializer

Initializes learnable parameters with samples from a uniform distribution (from the interval [-scale / 2, scale / 2]) using the Glorot method.

Parameters:

scale (float) – Scale of a uniform distribution interval [-scale / 2, scale / 2]. Default: 2

is_simple() → bool

get_settings() → Dict[str, Any]

class He(scale: float = 2)

Bases: Initializer

Initializes learnable parameters with samples from a uniform distribution (from the interval [-scale / 2, scale / 2]) using the He method.

Parameters:

scale (float) – Scale of a uniform distribution interval [-scale / 2, scale / 2]. Default: 2

is_simple() → bool

get_settings() → Dict[str, Any]

class Initializer

Bases: object

is_simple() → bool

get_settings() → Dict[str, Any]

class InitializerNames

Bases: object

UNIFORM = 'UNIFORM'

NORMAL = 'NORMAL'

CONSTANT = 'CONSTANT'

LONGTAIL = 'LONGTAIL'

GLOROT = 'GLOROT'

HE = 'HE'