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)
if args.gpu_device != -1:
config.gradient_clipping = 10
config.weight_decay = 0
# feature extractor
feature_extractor = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
feature_extractor.add(Linear(config.ndim_input, 1000, use_weightnorm=config.use_weightnorm))
feature_extractor.add(Activation(config.nonlinearity))
feature_extractor.add(gaussian_noise(std=0.3))
feature_extractor.add(Linear(None, 500, use_weightnorm=config.use_weightnorm))
feature_extractor.add(Activation(config.nonlinearity))
feature_extractor.add(gaussian_noise(std=0.3))
feature_extractor.add(Linear(None, 250, use_weightnorm=config.use_weightnorm))
feature_extractor.add(Activation(config.nonlinearity))
feature_extractor.add(gaussian_noise(std=0.3))
feature_extractor.add(Linear(None, config.num_experts, use_weightnorm=config.use_weightnorm))
feature_extractor.add(tanh())
# experts
experts = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
experts.add(Linear(config.num_experts, config.num_experts, use_weightnorm=config.use_weightnorm))
# b
b = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
b.add(Linear(config.ndim_input, 1, nobias=True))
params = {
"config": config.to_dict(),
"feature_extractor": feature_extractor.to_dict(),
"experts": experts.to_dict(),
"b": b.to_dict(),
}
config.nonlinearity = "relu"
config.optimizer = "Adam"
config.learning_rate = 0.001
config.momentum = 0.5
config.gradient_clipping = 5
config.weight_decay = 0
decoder = Sequential()
decoder.add(Linear(None, 1000))
decoder.add(Activation(config.nonlinearity))
# decoder.add(BatchNormalization(1000))
decoder.add(Linear(None, 1000))
decoder.add(Activation(config.nonlinearity))
# decoder.add(BatchNormalization(1000))
decoder.add(Linear(None, config.ndim_x))
decoder.add(tanh())
discriminator = Sequential()
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(BatchNormalization(1000))
discriminator.add(Linear(None, 1000))
discriminator.add(Activation(config.nonlinearity))
# discriminator.add(BatchNormalization(1000))
discriminator.add(Linear(None, 1000))
discriminator.add(Activation(config.nonlinearity))
# discriminator.add(BatchNormalization(1000))
discriminator.add(Linear(None, 2))
generator = Sequential()
config.weight_init_std = 0.05
config.weight_initializer = "Normal"
config.use_weightnorm = True
config.nonlinearity = "elu"
config.optimizer = "Adam"
config.learning_rate = 0.0002
config.momentum = 0.5
config.gradient_clipping = 10
config.weight_decay = 0
# feature extractor
feature_extractor = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
feature_extractor.add(Linear(config.ndim_input, 128, use_weightnorm=config.use_weightnorm))
feature_extractor.add(Activation(config.nonlinearity))
feature_extractor.add(Linear(None, 128, use_weightnorm=config.use_weightnorm))
feature_extractor.add(tanh())
# experts
experts = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
experts.add(Linear(128, config.num_experts, use_weightnorm=config.use_weightnorm))
# b
b = Sequential(weight_initializer=config.weight_initializer, weight_init_std=config.weight_init_std)
b.add(Linear(config.ndim_input, 1, nobias=True))
params = {
"config": config.to_dict(),
"feature_extractor": feature_extractor.to_dict(),
"experts": experts.to_dict(),
"b": b.to_dict(),
}