config.weight_init_std = 0.001 config.weight_initializer = "Normal" config.nonlinearity = "relu" config.optimizer = "Adam" config.learning_rate = 0.0002 config.momentum = 0.5 config.gradient_clipping = 5 config.weight_decay = 0 decoder = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std) decoder.add(Linear(None, 1000)) decoder.add(Activation(config.nonlinearity)) decoder.add(Linear(None, 1000)) decoder.add(Activation(config.nonlinearity)) decoder.add(Linear(None, config.ndim_x)) decoder.add(sigmoid()) discriminator = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std) discriminator.add(Merge(num_inputs=2, out_size=1000, nobias=True)) discriminator.add(gaussian_noise(std=0.3)) 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))
128,
ksize=4,
stride=2,
pad=paddings.pop(0),
use_weightnorm=config.use_weightnorm))
generator.add(BatchNormalization(128))
generator.add(Activation(config.nonlinearity))
generator.add(
Deconvolution2D(128,
3,
ksize=4,
stride=2,
pad=paddings.pop(0),
use_weightnorm=config.use_weightnorm))
if config.distribution_output == "sigmoid":
generator.add(sigmoid())
if config.distribution_output == "tanh":
generator.add(tanh())
params = {
"config": config.to_dict(),
"model": generator.to_dict(),
}
with open(generator_sequence_filename, "w") as f:
json.dump(params, f, indent=4, sort_keys=True, separators=(',', ': '))
generator_params = params
gan = GAN(discriminator_params, generator_params)
gan.load(args.model_dir)
config.learning_rate = 0.0002
config.momentum = 0.5
config.gradient_clipping = 10
config.weight_decay = 0
# model
model = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
model.add(Linear(config.ndim_input, 500, use_weightnorm=config.use_weightnorm))
model.add(BatchNormalization(500))
model.add(Activation(config.nonlinearity))
model.add(Linear(None, 500, use_weightnorm=config.use_weightnorm))
model.add(BatchNormalization(500))
model.add(Activation(config.nonlinearity))
model.add(Linear(None, config.ndim_output, use_weightnorm=config.use_weightnorm))
if config.distribution_output == "sigmoid":
model.add(sigmoid())
if config.distribution_output == "tanh":
model.add(tanh())
params = {
"config": config.to_dict(),
"model": model.to_dict(),
}
with open(generative_model_filename, "w") as f:
json.dump(params, f, indent=4, sort_keys=True, separators=(',', ': '))
params_generative_model = params
ddgm = DDGM(params_energy_model, params_generative_model)
ddgm.load(args.model_dir)