ncem.models.ModelCVAEncem

class ncem.models.ModelCVAEncem(input_shapes, latent_dim=10, 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_type='gcn', cond_depth=1, cond_dim=8, cond_dropout_rate=0.1, cond_activation='relu', cond_l2_reg=0.0, cond_use_bias=True, use_domain=False, scale_node_size=False, use_type_cond=True, use_batch_norm=False, transform_input=False, output_layer='gaussian', **kwargs)[source]

Model class for NCEM conditional variational autoencoder with graph layer IND (MAX) or GCN.

Methods

Parameters

  • latent_dim (int) –

  • intermediate_dim_enc (int) –

  • intermediate_dim_dec (int) –

  • depth_enc (int) –

  • depth_dec (int) –

  • dropout_rate (float) –

  • l2_coef (float) –

  • l1_coef (float) –

  • cond_type (str) –

  • cond_depth (int) –

  • cond_dim (int) –

  • cond_dropout_rate (float) –

  • cond_activation (Union[str, Layer]) –

  • cond_l2_reg (float) –

  • cond_use_bias (bool) –

  • use_domain (bool) –

  • scale_node_size (bool) –

  • use_type_cond (bool) –

  • use_batch_norm (bool) –

  • transform_input (bool) –

  • output_layer (str) –