Pass-through layer that adds a KL divergence penalty to the model loss

layer_kl_divergence_add_loss(object, distribution_b,
  use_exact_kl = FALSE, test_points_reduce_axis = NULL,
  test_points_fn = tf$convert_to_tensor, weight = NULL, ...)



Model or layer object


Distribution instance corresponding to b as in KL[a, b]. The previous layer's output is presumed to be a Distribution instance and is a.


Logical indicating if KL divergence should be calculated exactly via tfp$distributions$kl_divergence or via Monte Carlo approximation. Default value: FALSE.


Integer vector or scalar representing dimensions over which to reduce_mean while calculating the Monte Carlo approximation of the KL divergence. As is with all tf$reduce_* ops, NULL means reduce over all dimensions; () means reduce over none of them. Default value: () (i.e., no reduction).


A callable taking a tfp$distributions$Distribution instance and returning a tensor used for random test points to approximate the KL divergence. Default value: tf$convert_to_tensor.


Multiplier applied to the calculated KL divergence for each Keras batch member. Default value: NULL (i.e., do not weight each batch member).


Additional arguments passed to args of keras::create_layer.


a Keras layer

See also