Parameter initialization¶

Some of those are just less verbose versions of dynet’s PyInitializer s

dynn.parameter_initialization.NormalInit(mean=0, std=1)¶

Gaussian initialization

Parameters:	mean (int, optional) – Mean (default: 0.0) std (int, optional) – Standard deviation (\(\neq\) variance) (default: 1.0)
Returns:	`dy.NormalInitializer(mean, sqrt(std))`
Return type:	`dynet.PyInitializer`

dynn.parameter_initialization.OneInit()¶

Initialize with \(1\)

Returns:	`dy.ConstInitializer(1)`
Return type:	`dynet.PyInitializer`

dynn.parameter_initialization.UniformInit(scale=1.0)¶

Uniform initialization between -scale and scale

Parameters:	scale (float) – Scale of the distribution
Returns:	`dy.UniformInitializer(scale)`
Return type:	`dynet.PyInitializer`

dynn.parameter_initialization.ZeroInit()¶

Initialize with \(0\)

Returns:	dy.ConstInitializer(0)
Return type:	`dynet.PyInitializer`