def __init__(self, args):
super(LotteryWAE, self).__init__(args)
LotteryAE.__init__(self, args)
WAE.__init__(self, args)
self.pruning = args.pruning
self.mu.unprunable = True
self.log_var.unprunable = True
def __init__(self, encoder, decoder, synth, args, upsampler=None):
DDSSynth.__init__(self, encoder, decoder, synth, args, upsampler)
WAE.__init__(self)
args.encoder_dims,
args.latent_dims,
channels=args.channels,
n_layers=args.n_layers,
hidden_size=args.n_hidden,
n_mlp=args.n_layers // 2,
type_mod=args.layers,
args=args)
# Construct specific type of AE
if (args.model == 'ae'):
model = AE(encoder, decoder, args.encoder_dims, args.latent_dims)
elif (args.model == 'vae'):
model = VAE(encoder, decoder, args.input_size, args.encoder_dims,
args.latent_dims)
elif (args.model == 'wae'):
model = WAE(encoder, decoder, args.input_size, args.encoder_dims,
args.latent_dims)
elif (args.model == 'vae_flow'):
# Construct the normalizing flow
flow, blocks = construct_flow(args.latent_dims,
flow_type=args.flow,
flow_length=args.flow_length,
amortization='input')
# Construct full VAE with given flow
model = VAEFlow(encoder, decoder, flow, args.input_size,
args.encoder_dims, args.latent_dims)
# Construct specific regressor
regression_model = construct_regressor(args.latent_dims,
args.output_size,
model=args.regressor,
hidden_dims=args.reg_hiddens,
n_layers=args.reg_layers,