LostTech.TensorFlow : API Documentation

Type orthogonal_initializer

Namespace tensorflow

Parent Initializer

Interfaces Iorthogonal_initializer

Initializer that generates an orthogonal matrix.

If the shape of the tensor to initialize is two-dimensional, it is initialized with an orthogonal matrix obtained from the QR decomposition of a matrix of random numbers drawn from a normal distribution. If the matrix has fewer rows than columns then the output will have orthogonal rows. Otherwise, the output will have orthogonal columns.

If the shape of the tensor to initialize is more than two-dimensional, a matrix of shape `(shape[0] *... * shape[n - 2], shape[n - 1])` is initialized, where `n` is the length of the shape vector. The matrix is subsequently reshaped to give a tensor of the desired shape.



Public static methods

orthogonal_initializer NewDyn(ImplicitContainer<T> gain, object seed, ImplicitContainer<T> dtype)

Creates a `CosineSimilarity` instance.
ImplicitContainer<T> gain
object seed
ImplicitContainer<T> dtype
(Optional) data type of the metric result.

Public properties

DType dtype get; set;

double gain get; set;

object PythonObject get;

Nullable<int> seed get; set;