LostTech.TensorFlow : API Documentation

Type variance_scaling_initializer

Namespace tensorflow

Parent Initializer

Interfaces Ivariance_scaling_initializer

Initializer capable of adapting its scale to the shape of weights tensors.

With `distribution="truncated_normal" or "untruncated_normal"`, samples are drawn from a truncated/untruncated normal distribution with a mean of zero and a standard deviation (after truncation, if used) `stddev = sqrt(scale / n)` where n is: - number of input units in the weight tensor, if mode = "fan_in" - number of output units, if mode = "fan_out" - average of the numbers of input and output units, if mode = "fan_avg"

With `distribution="uniform"`, samples are drawn from a uniform distribution within [-limit, limit], with `limit = sqrt(3 * scale / n)`.



Public static methods

variance_scaling_initializer NewDyn(ImplicitContainer<T> scale, ImplicitContainer<T> mode, ImplicitContainer<T> distribution, object seed, ImplicitContainer<T> dtype)

Initialize self. See help(type(self)) for accurate signature.

Public properties

string distribution get; set;

DType dtype get; set;

string mode get; set;

object PythonObject get;

double scale get; set;

Nullable<int> seed get; set;