rc.gpf.base§
Contains extensions to gpflow.base.
Classes§
A non-diagonal Variance Matrix. |
Module Contents§
- class Variance(value, name='Variance', cholesky_diagonal_lower_bound=CHOLESKY_DIAGONAL_LOWER_BOUND)§
Bases:
gpflow.Module
A non-diagonal Variance Matrix.
- Parameters:
name (str)
cholesky_diagonal_lower_bound (float)
- property shape: Tuple[int, int]§
Returns (L,L), which is the shape of self.value and self.cholesky.
- Return type:
Tuple[int, int]
- property cholesky: tensorflow.Tensor§
The (lower triangular) Cholesky decomposition of the covariance matrix.
- Return type:
tensorflow.Tensor
- property value§
The covariance matrix, shape (L,L).
- property value_to_broadcast§
The covariance matrix, shape (L,1,L,1) ready to broadcast.
- value_times_eye(N)§
The cartesian product variance[:L, :L] * eye[:N, :N], transposed.
- Parameters:
N (int) – The dimension of the identity matrix we are multiplying by.
- Return type:
tensorflow.Tensor
Returns: An [:L, :N, :L, :N] Tensor, after transposition.