def __init__(self, features, latent_dim, encoder, decoder, deterministic_path_drop_rate=0.5):
super().__init__()
self.embedder = nn.Embedding(MAX_VALUE, features)
self.encoder = ResidualAttentionEncoder(**encoder)
self._latent_encoder = nn.ModuleList([
ResidualAttentionEncoder(**encoder),
NormalNode(features, latent_dim)]
)
self.z_to_c = nn.Linear(latent_dim, latent_dim*155)
self.decoder = CondtionalResidualAttentionEncoder(**decoder)
self.logits = FeedForwardGELU(features, MAX_VALUE)
self.drop = nn.Dropout(deterministic_path_drop_rate)
def __init__(self, features, encoder):
super().__init__()
self.embedder = nn.Embedding(MAX_VALUE, features)
self.encoder = ResidualAttentionEncoder(**encoder)
self.logits = nn.Linear(features, MAX_VALUE)
def __init__(self,
features,
latent_dim,
encoder,
decoder,
deterministic_path_drop_rate=0.5,
num_flows=3):
super().__init__()
self.embedder = nn.Embedding(MAX_VALUE, features)
self.encoder = ResidualAttentionEncoder(**encoder)
self._latent_encoder = nn.ModuleList([
ResidualAttentionEncoder(**encoder),
TriangularSylvesterFlow(features, latent_dim, num_flows)
])
self.z_to_c = nn.Linear(latent_dim, latent_dim * 155)
self.decoder = CondtionalResidualAttentionEncoder(**decoder)
self.logits = FeedForwardGELU(features, MAX_VALUE)
self.drop = nn.Dropout(deterministic_path_drop_rate)
self.n_features = features
def __init__(self, features, latent_dim, encoder, decoder, num_flows=3):
"""
features - number of features in the model
latent_dim - the latent dimension of the model
encoder - dictionary containing instantiation parameters for ResidualAttentionEncoder module
decoder - dictionary containing instantiation parameters for CondtionalResidualAttentionEncoder module
num_flows - the number of flows for the TriangularSylvesterFlow module
"""
super().__init__()
self.embedder = nn.Embedding(MAX_VALUE, features)
self.encoder = ResidualAttentionEncoder(**encoder)
self._latent_encoder = nn.ModuleList([
ResidualAttentionEncoder(**encoder),
TriangularSylvesterFlow(features, latent_dim, num_flows)
])
self.z_to_c = nn.Linear(latent_dim, latent_dim * 155)
self.decoder = CondtionalResidualAttentionEncoder(**decoder)
self.logits = FeedForwardGELU(features, MAX_VALUE)
self.n_features = features