deepof.hypermodels.VaDE

class deepof.hypermodels.VaDE(input_shape: tuple, latent_dim: int, batch_size: int, n_components: int = 10, learn_rate: float = 0.001, edge_feature_shape: tuple | None = None, use_gnn: bool = False, adjacency_matrix: ndarray | None = None)

Hyperparameter tuning pipeline for deepof.models.VaDE.

__init__(input_shape: tuple, latent_dim: int, batch_size: int, n_components: int = 10, learn_rate: float = 0.001, edge_feature_shape: tuple | None = None, use_gnn: bool = False, adjacency_matrix: ndarray | None = None)

Build VaDE hypermodel for hyperparameter tuning.

Parameters:

• input_shape (tuple) – shape of the input tensor.

• latent_dim (int) – dimension of the latent space.

• batch_size (int) – batch size for training.

• learn_rate (float) – learning rate for the optimizer.

• n_components (int) – number of components in the quantization space.

• edge_feature_shape (tuple) – shape of the edge feature tensor.

• use_gnn (bool) – whether to use a graph neural network to encode the input data.

• adjacency_matrix (np.ndarray) – adjacency matrix of the graph.

Methods

__init__(input_shape, latent_dim, batch_size)	Build VaDE hypermodel for hyperparameter tuning.
build(hp)	Override Hypermodel's build method.
declare_hyperparameters(hp)
fit(hp, model, *args, **kwargs)	Train the model.
get_hparams(hp)	Retrieve hyperparameters to tune.

__init__(input_shape: tuple, latent_dim: int, batch_size: int, n_components: int = 10, learn_rate: float = 0.001, edge_feature_shape: tuple | None = None, use_gnn: bool = False, adjacency_matrix: ndarray | None = None)

Build VaDE hypermodel for hyperparameter tuning.

Parameters:

• input_shape (tuple) – shape of the input tensor.

• latent_dim (int) – dimension of the latent space.

• batch_size (int) – batch size for training.

• learn_rate (float) – learning rate for the optimizer.

• n_components (int) – number of components in the quantization space.

• edge_feature_shape (tuple) – shape of the edge feature tensor.

• use_gnn (bool) – whether to use a graph neural network to encode the input data.

• adjacency_matrix (np.ndarray) – adjacency matrix of the graph.