def get_hyper_model(model_str, placeholders, H_dim):
discriminator = Discriminator()
d_real = discriminator.construct(placeholders['real_distribution'])
model = None
if model_str == 'hyper_arga_ae':
model = HCAE(placeholders, H_dim)
return d_real, discriminator, model
def get_model(model_str, placeholders, num_features, num_nodes,
features_nonzero):
discriminator = Discriminator()
d_real = discriminator.construct(placeholders['real_distribution'])
model = None
if model_str == 'arga_ae':
model = ARGA(placeholders, num_features, features_nonzero)
elif model_str == 'arga_vae':
model = ARVGA(placeholders, num_features, num_nodes, features_nonzero)
return d_real, discriminator, model
def get_model(model_str,
placeholders,
num_features,
num_nodes,
features_nonzero,
num_classes=1,
cat=True):
discriminator = Discriminator()
d_real = discriminator.construct(placeholders['real_distribution'])
model = None
if model_str == 'vgc' or model_str == 'vgcg':
model = VGC(placeholders, num_features, num_nodes, features_nonzero,
num_classes, cat)
return d_real, discriminator, model
def get_model(model_str, placeholders, num_features, num_nodes, features_nonzero):
# 计算图构建
discriminator = Discriminator()
D_Graph = D_graph(num_features)
d_real = discriminator.construct(placeholders['real_distribution'])
GD_real = D_Graph.construct(placeholders['features_dense'])
model = None
if model_str == 'arga_ae':
model = GCN(placeholders, num_features, features_nonzero)
elif model_str == 'DBGAN':
model = GCN(placeholders, num_features, features_nonzero)
model_z2g = Generator_z2g(placeholders, num_features,features_nonzero)
return d_real, discriminator, model, model_z2g, D_Graph, GD_real
def get_model(placeholders, num_features, num_nodes, features_nonzero,pri_attr,dim_attr):
discriminator = Discriminator()
d_real = discriminator.construct(placeholders['real_distribution'])
model = None
model = APGE(placeholders, num_features, features_nonzero,pri_attr,dim_attr)
return d_real, discriminator, model
