image_height = image_width
ndim_z = 50
# specify discriminator
discriminator_sequence_filename = args.model_dir + "/discriminator.json"
if os.path.isfile(discriminator_sequence_filename):
print "loading", discriminator_sequence_filename
with open(discriminator_sequence_filename, "r") as f:
try:
params = json.load(f)
except Exception as e:
raise Exception(
"could not load {}".format(discriminator_sequence_filename))
else:
config = DiscriminatorParams()
config.weight_init_std = 0.001
config.weight_initializer = "Normal"
config.use_weightnorm = False
config.nonlinearity = "elu"
config.optimizer = "Adam"
config.learning_rate = 0.0001
config.momentum = 0.5
config.gradient_clipping = 10
config.weight_decay = 0
config.use_feature_matching = False
config.use_minibatch_discrimination = False
discriminator = Sequential(weight_initializer=config.weight_initializer,
weight_init_std=config.weight_init_std)
discriminator.add(gaussian_noise(std=0.3))
except:
pass
# specify discriminator
discriminator_sequence_filename = args.model_dir + "/discriminator.json"
if os.path.isfile(discriminator_sequence_filename):
print "loading", discriminator_sequence_filename
with open(discriminator_sequence_filename, "r") as f:
try:
discriminator_params = json.load(f)
except Exception as e:
raise Exception(
"could not load {}".format(discriminator_sequence_filename))
else:
config = DiscriminatorParams()
config.a = 0
config.b = 1
config.c = 1
config.weight_std = 0.01
config.weight_initializer = "Normal"
config.use_weightnorm = False
config.nonlinearity = "leaky_relu"
config.optimizer = "adam"
config.learning_rate = 0.0001
config.momentum = 0.5
config.gradient_clipping = 1
config.weight_decay = 0
discriminator = Sequential()
discriminator.add(Linear(None, 128, use_weightnorm=config.use_weightnorm))
image_height = image_width
ndim_latent_code = 50
# specify discriminator
discriminator_sequence_filename = args.model_dir + "/discriminator.json"
if os.path.isfile(discriminator_sequence_filename):
print "loading", discriminator_sequence_filename
with open(discriminator_sequence_filename, "r") as f:
try:
params = json.load(f)
except Exception as e:
raise Exception(
"could not load {}".format(discriminator_sequence_filename))
else:
config = DiscriminatorParams()
config.ndim_input = image_width * image_height
config.clamp_lower = -0.01
config.clamp_upper = 0.01
config.num_critic = 5
config.weight_init_std = 0.001
config.weight_initializer = "Normal"
config.use_weightnorm = False
config.nonlinearity = "leaky_relu"
config.optimizer = "rmsprop"
config.learning_rate = 0.0001
config.momentum = 0.5
config.gradient_clipping = 1
config.weight_decay = 0
config.use_feature_matching = False
config.use_minibatch_discrimination = False
ndim_z = 50
# specify discriminator
discriminator_sequence_filename = args.model_dir + "/discriminator.json"
if os.path.isfile(discriminator_sequence_filename):
print "loading", discriminator_sequence_filename
with open(discriminator_sequence_filename, "r") as f:
try:
params = json.load(f)
chainer.global_config.discriminator = to_object(params["config"])
except Exception as e:
raise Exception(
"could not load {}".format(discriminator_sequence_filename))
else:
config = DiscriminatorParams()
config.clamp_lower = -0.01
config.clamp_upper = 0.01
config.num_critic = 1
config.weight_std = 0.001
config.weight_initializer = "Normal"
config.nonlinearity = "leaky_relu"
config.optimizer = "rmsprop"
config.learning_rate = 0.0001
config.momentum = 0.5
config.gradient_clipping = 10
config.weight_decay = 0
chainer.global_config.discriminator = config
discriminator = Sequential()
image_height = image_width
ndim_latent_code = 50
# specify discriminator
discriminator_sequence_filename = args.model_dir + "/discriminator.json"
if os.path.isfile(discriminator_sequence_filename):
print "loading", discriminator_sequence_filename
with open(discriminator_sequence_filename, "r") as f:
try:
discriminator_params = json.load(f)
except Exception as e:
raise Exception(
"could not load {}".format(discriminator_sequence_filename))
else:
config = DiscriminatorParams()
config.a = 0
config.b = 1
config.c = 1
config.weight_std = 0.01
config.weight_initializer = "Normal"
config.use_weightnorm = False
config.nonlinearity = "leaky_relu"
config.optimizer = "adam"
config.learning_rate = 0.0001
config.momentum = 0.5
config.gradient_clipping = 1
config.weight_decay = 0
discriminator = Sequential()
discriminator.add(Linear(None, 500, use_weightnorm=config.use_weightnorm))