ncem.estimators.EstimatorCVAEncem.init_model

EstimatorCVAEncem.init_model(optimizer='adam', learning_rate=0.0001, latent_dim=8, intermediate_dim_enc=128, intermediate_dim_dec=128, depth_enc=1, depth_dec=1, dropout_rate=0.1, l2_coef=0.0, l1_coef=0.0, cond_depth=1, cond_dim=8, cond_dropout_rate=0.1, cond_activation='relu', cond_l2_reg=0.0, cond_use_bias=False, n_eval_nodes_per_graph=32, use_domain=False, use_batch_norm=False, scale_node_size=True, transform_input=False, beta=0.01, max_beta=1.0, pre_warm_up=0, output_layer='gaussian', **kwargs)[source]

Initialize a ModelCVAEncem object.

Parameters

  • optimizer (str) – Optimizer.

  • learning_rate (float) – Learning rate.

  • latent_dim (int) – Latent dimension.

  • dropout_rate (float) – Dropout rate.

  • l2_coef (float) – l2 regularization coefficient.

  • l1_coef (float) – l1 regularization coefficient.

  • intermediate_dim_enc (int) – Encoder intermediate dimension.

  • depth_enc (int) – Encoder depth.

  • intermediate_dim_dec (int) – Decoder intermediate dimension.

  • depth_dec (int) – Decoder depth.

  • cond_depth (int) – Graph conditional depth.

  • cond_dim (int) – Graph conditional dimension.

  • cond_dropout_rate (float) – Graph conditional dropout rate.

  • cond_activation (str) – Graph conditional activation.

  • cond_l2_reg (float) – Graph conditional l2 regularization coefficient.

  • cond_use_bias (bool) – Graph conditional use bias.

  • n_eval_nodes_per_graph (int) – Number of nodes per graph.

  • use_domain (bool) – Whether to use domain information.

  • use_batch_norm (bool) – Whether to use batch normalization.

  • scale_node_size (bool) – Whether to scale output layer by node sizes.

  • transform_input (bool) – Whether to transform input.

  • beta (float) – Beta used in BetaScheduler.

  • max_beta (float) – Maximal beta used in BetaScheduler.

  • pre_warm_up (int) – Number of epochs in pre warm up.

  • output_layer (str) – Output layer.

  • kwargs – Arbitrary keyword arguments.