Keras layer enabling plumbing TFP distributions through Keras models
Keras layer enabling plumbing TFP distributions through Keras models
layer_distribution_lambda( object, make_distribution_fn, convert_to_tensor_fn = tfp$distributions$Distribution$sample, ... )
object |
Model or layer object |
make_distribution_fn |
A callable that takes previous layer outputs and returns a |
convert_to_tensor_fn |
A callable that takes a tfd$Distribution instance and returns a
tf$Tensor-like object. Default value: |
... |
Additional arguments passed to |
a Keras layer
For an example how to use in a Keras model, see layer_independent_normal().
Other distribution_layers:
layer_categorical_mixture_of_one_hot_categorical(),
layer_independent_bernoulli(),
layer_independent_logistic(),
layer_independent_normal(),
layer_independent_poisson(),
layer_kl_divergence_add_loss(),
layer_kl_divergence_regularizer(),
layer_mixture_logistic(),
layer_mixture_normal(),
layer_mixture_same_family(),
layer_multivariate_normal_tri_l(),
layer_one_hot_categorical()
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.