# p(a|x,y,z) - a ~ Gaussian
p_a_yz = Sequential(weight_initializer=config.weight_initializer,
weight_init_std=config.weight_init_std)
p_a_yz.add(
Merge(num_inputs=2, out_size=500,
use_weightnorm=config.use_weightnorm))
p_a_yz.add(BatchNormalization(500))
p_a_yz.add(Activation(config.nonlinearity))
p_a_yz.add(Linear(None, 500, use_weightnorm=config.use_weightnorm))
p_a_yz.add(BatchNormalization(500))
p_a_yz.add(Activation(config.nonlinearity))
p_a_yz.add(Linear(None, 500, use_weightnorm=config.use_weightnorm))
p_a_yz.add(BatchNormalization(500))
p_a_yz.add(Activation(config.nonlinearity))
p_a_yz.add(Gaussian(None, config.ndim_a)) # outputs mean and ln(var)
# q(z|a,x,y) - z ~ Gaussian
q_z_axy = Sequential(weight_initializer=config.weight_initializer,
weight_init_std=config.weight_init_std)
q_z_axy.add(
Merge(num_inputs=3, out_size=500,
use_weightnorm=config.use_weightnorm))
q_z_axy.add(BatchNormalization(500))
q_z_axy.add(Activation(config.nonlinearity))
q_z_axy.add(Linear(None, 500, use_weightnorm=config.use_weightnorm))
q_z_axy.add(BatchNormalization(500))
q_z_axy.add(Activation(config.nonlinearity))
q_z_axy.add(Linear(None, 500, use_weightnorm=config.use_weightnorm))
q_z_axy.add(BatchNormalization(500))
q_z_axy.add(Activation(config.nonlinearity))
discriminator.add(Activation(config.nonlinearity))
discriminator.add(Linear(None, 1000))
discriminator.add(Activation(config.nonlinearity))
discriminator.add(Linear(None, 1000))
discriminator.add(Activation(config.nonlinearity))
discriminator.add(Linear(None, 2))
generator = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
generator.add(Linear(config.ndim_x, 1000))
generator.add(Activation(config.nonlinearity))
generator.add(Linear(None, 1000))
generator.add(Activation(config.nonlinearity))
if config.distribution_z == "deterministic":
generator.add(Linear(None, config.ndim_z))
elif config.distribution_z == "gaussian":
generator.add(Gaussian(None, config.ndim_z)) # outputs mean and ln(var)
else:
raise Exception()
params = {
"config": config.to_dict(),
"decoder": decoder.to_dict(),
"generator": generator.to_dict(),
"discriminator": discriminator.to_dict(),
}
with open(model_filename, "w") as f:
json.dump(params, f, indent=4, sort_keys=True, separators=(',', ': '))
aae = AAE(params)
aae.load(args.model_dir)