tfg.math.interpolation.slerp.interpolate_with_weights

Interpolates vectors by taking their weighted sum.

tfg.math.interpolation.slerp.interpolate_with_weights(
    vector1: type_alias.TensorLike,
    vector2: type_alias.TensorLike,
    weight1: Union[type_alias.Float, type_alias.TensorLike],
    weight2: Union[type_alias.Float, type_alias.TensorLike],
    name: str = 'interpolate_with_weights'
) -> tf.Tensor

Interpolation for all variants of slerp is a simple weighted sum over inputs. Therefore this function simply returns weight1 * vector1 + weight2 * vector2.

In the following, A1 to An are optional batch dimensions.

vector1 A tensor of shape [A1, ... , An, M], which stores a normalized vector in its last dimension.
vector2 A tensor of shape [A1, ... , An, M], which stores a normalized vector in its last dimension.
weight1 A float or a tensor describing weights for the vector1 and with a shape broadcastable to the shape of the input vectors.
weight2 A float or a tensor describing weights for the vector2 and with a shape broadcastable to the shape of the input vectors.
name A name for this op. Defaults to "interpolate_with_weights".

A tensor of shape [A1, ... , An, M] containing the result of the interpolation.