buddi.models.buddi_abstract_class

Functions

Input([shape, batch_size, dtype, sparse, ...])	Used to instantiate a Keras tensor.
abstractmethod(funcobj)	A decorator indicating abstract methods.
kl_loss(y_true, y_pred)	KL divergence loss function.
unsupervised_dummy_loss_fn(y_true, y_pred)	Dummy loss function for unsupervised branch proportion estimator.
wrapped_build_decoder_branch(...[, ...])	Factory wrapper around build_decoder_branch.
wrapped_build_encoder_branch(input_shape, ...)	Factory wrapper around build_encoder_branch.
wrapped_build_latent_space_classifier_branch(...)	Factory wrapper around build_latent_space_classifier.
wrapped_build_prop_estimator_branch(...[, ...])	Factory wrapper around build_prop_estimator.

Classes

ABC()	Helper class that provides a standard way to create an ABC using inheritance.
Adam([learning_rate, beta_1, beta_2, ...])	Optimizer that implements the Adam algorithm.
BuDDIAbstract(n_x, n_y[, z_dim, ...])	Abstract class for BuDDI models.
CategoricalCrossentropy([from_logits, ...])	Computes the crossentropy loss between the labels and predictions.
MeanAbsoluteError([reduction, name, dtype])	Computes the mean of absolute difference between labels and predictions.
Model(*args, **kwargs)	A model grouping layers into an object with training/inference features.
Optimizer(*args, **kwargs)	Abstract optimizer base class.
ReparameterizationLayer(*args, **kwargs)	Custom layer that applies the reparameterization trick.