box_embeddings.modules.volume.tf_bessel_volume

Module Contents

eps = 1e-23
euler_gamma = 0.5772156649015329
tf_bessel_volume_approx(box_tensor: box_embeddings.parameterizations.tf_box_tensor.TFBoxTensor, volume_temperature: float = 1.0, intersection_temperature: float = 1.0, log_scale: bool = True, scale: float = 1.0) → tensorflow.Tensor

Volume of boxes. Uses the Softplus as an approximation of Bessel funtion.

Parameters

  • box_tensor – input

  • volume_temperature – 1/volume_temperature is the beta parameter for the softplus

  • intersection_temperature – the intersection_temperature parameter (same value used in intersection).

  • log_scale – Whether the output should be in log scale or not.

  • scale – scale parameter. Should be left as 1.0 (default) in most cases.

Returns

Tensor of shape (…, ) when self has shape (…, 2, num_dims)

Raises

ValueError – if scale not in (0,1] or volume_temperature is 0.

class TFBesselApproxVolume(log_scale: bool = True, volume_temperature: float = 1.0, intersection_temperature: float = 1.0)

Bases: box_embeddings.modules.volume._tf_volume._TFVolume

Uses the Softplus as an approximation of Bessel function.