terminator.models.layers.gvp.randn

terminator.models.layers.gvp.randn(n, dims, device='cpu')[source]

Returns random tuples (s, V) drawn elementwise from a normal distribution.

Parameters:
  • n – number of data points

  • dims – tuple of dimensions (n_scalar, n_vector)

Returns:

(s, V) with s.shape = (n, n_scalar) and V.shape = (n, n_vector, 3)