def run(dataset, data_dir, result_dir, config_id, num_gpus, total_kimg, gamma,
mirror_augment, metrics):
train = EasyDict(run_func_name='training.training_loop.training_loop'
) # Options for training loop.
G = EasyDict(func_name='training.networks_stylegan2.G_main'
) # Options for generator network.
D = EasyDict(func_name='training.networks_stylegan2.D_stylegan2'
) # Options for discriminator network.
G_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for generator optimizer.
D_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for discriminator optimizer.
G_loss = EasyDict(func_name='training.loss.G_logistic_ns_pathreg'
) # Options for generator loss.
D_loss = EasyDict(func_name='training.loss.D_logistic_r1'
) # Options for discriminator loss.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size='8k', layout='random') # Options for setup_snapshot_image_grid().
sc = dnnlib.SubmitConfig() # Options for dnnlib.submit_run().
tf_config = {'rnd.np_random_seed': 1000} # Options for tflib.init_tf().
train.data_dir = data_dir
train.total_kimg = total_kimg
train.mirror_augment = mirror_augment
train.image_snapshot_ticks = train.network_snapshot_ticks = 2
sched.G_lrate_base = sched.D_lrate_base = 0.002
sched.minibatch_size_base = 32
sched.minibatch_gpu_base = 4
D_loss.gamma = 10
metrics = [metric_defaults[x] for x in metrics]
desc = 'stylegan2'
desc += '-' + dataset
dataset_args = EasyDict(tfrecord_dir=dataset)
assert num_gpus in [1, 2, 4, 8]
sc.num_gpus = num_gpus
desc += '-%dgpu' % num_gpus
assert config_id in _valid_configs
desc += '-' + config_id
# Configs A-E: Shrink networks to match original StyleGAN.
if config_id != 'config-f':
G.fmap_base = D.fmap_base = 8 << 10
# Config E: Set gamma to 100 and override G & D architecture.
if config_id.startswith('config-e'):
D_loss.gamma = 100
if 'Gorig' in config_id: G.architecture = 'orig'
if 'Gskip' in config_id: G.architecture = 'skip' # (default)
if 'Gresnet' in config_id: G.architecture = 'resnet'
if 'Dorig' in config_id: D.architecture = 'orig'
if 'Dskip' in config_id: D.architecture = 'skip'
if 'Dresnet' in config_id: D.architecture = 'resnet' # (default)
# Configs A-D: Enable progressive growing and switch to networks that support it.
if config_id in ['config-a', 'config-b', 'config-c', 'config-d']:
sched.lod_initial_resolution = 8
sched.G_lrate_base = sched.D_lrate_base = 0.001
sched.G_lrate_dict = sched.D_lrate_dict = {
128: 0.0015,
256: 0.002,
512: 0.003,
1024: 0.003
}
sched.minibatch_size_base = 32 # (default)
sched.minibatch_size_dict = {8: 256, 16: 128, 32: 64, 64: 32}
sched.minibatch_gpu_base = 4 # (default)
sched.minibatch_gpu_dict = {8: 32, 16: 16, 32: 8, 64: 4}
G.synthesis_func = 'G_synthesis_stylegan_revised'
D.func_name = 'training.networks_stylegan2.D_stylegan'
# Configs A-C: Disable path length regularization.
if config_id in ['config-a', 'config-b', 'config-c']:
G_loss = EasyDict(func_name='training.loss.G_logistic_ns')
# Configs A-B: Disable lazy regularization.
if config_id in ['config-a', 'config-b']:
train.lazy_regularization = False
# Config A: Switch to original StyleGAN networks.
if config_id == 'config-a':
G = EasyDict(func_name='training.networks_stylegan.G_style')
D = EasyDict(func_name='training.networks_stylegan.D_basic')
if gamma is not None:
D_loss.gamma = gamma
sc.submit_target = dnnlib.SubmitTarget.LOCAL
sc.local.do_not_copy_source_files = True
kwargs = EasyDict(train)
kwargs.update(G_args=G,
D_args=D,
G_opt_args=G_opt,
D_opt_args=D_opt,
G_loss_args=G_loss,
D_loss_args=D_loss)
kwargs.update(dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
metric_arg_list=metrics,
tf_config=tf_config)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = result_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)
def run(dataset, data_dir, result_dir, config_id, num_gpus, total_kimg, gamma, mirror_augment, metrics):
train = EasyDict(run_func_name='training.training_loop.training_loop_mirror_v6_remove_half_fl_fr.training_loop')
G = EasyDict(func_name='training.networks.networks_stylegan2.G_main')
D = EasyDict(func_name='training.networks.networks_stylegan2_discriminator_new_rotation.D_stylegan2_new_rotaion') # Options for discriminator network.
G_opt = EasyDict(beta1=0.0, beta2=0.99, epsilon=1e-8)
D_opt = EasyDict(beta1=0.0, beta2=0.99, epsilon=1e-8)
G_loss = EasyDict(func_name='training.loss.loss_G_new_rotation_squared_euclidean_10_interpolate_50_percent_uniform_dist_int_penalty.G_logistic_ns_pathreg')
D_loss = EasyDict(func_name='training.loss.loss_D_logistic_r1_new_rotation_euclidean_square.D_logistic_r1_new_rotation')
sched = EasyDict()
grid = EasyDict(size='1080p', layout='random')
sc = dnnlib.SubmitConfig()
tf_config = {'rnd.np_random_seed': 1000}
train.data_dir = data_dir
train.total_kimg = total_kimg
train.mirror_augment = mirror_augment
train.image_snapshot_ticks = train.network_snapshot_ticks = 10
sched.G_lrate_base = sched.D_lrate_base = 0.002
sched.minibatch_size_base = 32
sched.minibatch_gpu_base = 4
# train.resume_pkl = './results/00200-stylegan2-car_labels_v7_oversample_filter-2gpu-config-f-squared_euclidean_10_interpolate_50_percent_int_reg-256/network-snapshot-000887.pkl'
# train.resume_kimg = 887.2
D_loss.gamma = 10
metrics = [metric_defaults[x] for x in metrics]
desc = 'stylegan2'
G.style_mixing_prob = None
desc += '-' + dataset
dataset_args = EasyDict(tfrecord_dir=dataset)
assert num_gpus in [1, 2, 4, 8]
sc.num_gpus = num_gpus
desc += '-%dgpu' % num_gpus
assert config_id in _valid_configs
desc += '-' + config_id
desc += '-squared_euclidean_10_interpolate_50_percent_int_reg_remove_half_fl_fr_no_noise_square'
desc += '-256'
# Configs A-E: Shrink networks to match original StyleGAN.
if config_id != 'config-f':
G.fmap_base = D.fmap_base = 8 << 10
# Config E: Set gamma to 100 and override G & D architecture.
if config_id.startswith('config-e'):
D_loss.gamma = 100
if 'Gorig' in config_id: G.architecture = 'orig'
if 'Gskip' in config_id: G.architecture = 'skip' # (default)
if 'Gresnet' in config_id: G.architecture = 'resnet'
if 'Dorig' in config_id: D.architecture = 'orig'
if 'Dskip' in config_id: D.architecture = 'skip'
if 'Dresnet' in config_id: D.architecture = 'resnet' # (default)
# Configs A-D: Enable progressive growing and switch to networks that support it.
if config_id in ['config-a', 'config-b', 'config-c', 'config-d']:
sched.lod_initial_resolution = 8
sched.G_lrate_base = sched.D_lrate_base = 0.001
sched.G_lrate_dict = sched.D_lrate_dict = {128: 0.0015, 256: 0.002, 512: 0.003, 1024: 0.003}
sched.minibatch_size_base = 32 # (default)
sched.minibatch_size_dict = {8: 256, 16: 128, 32: 64, 64: 32}
sched.minibatch_gpu_base = 4 # (default)
sched.minibatch_gpu_dict = {8: 32, 16: 16, 32: 8, 64: 4}
G.synthesis_func = 'G_synthesis_stylegan_revised'
D.func_name = 'training.networks_stylegan2.D_stylegan'
# Configs A-C: Disable path length regularization.
if config_id in ['config-a', 'config-b', 'config-c']:
G_loss = EasyDict(func_name='training.loss.G_logistic_ns')
# Configs A-B: Disable lazy regularization.
if config_id in ['config-a', 'config-b']:
train.lazy_regularization = False
# Config A: Switch to original StyleGAN networks.
if config_id == 'config-a':
G = EasyDict(func_name='training.networks_stylegan.G_style')
D = EasyDict(func_name='training.networks_stylegan.D_basic')
if gamma is not None:
D_loss.gamma = gamma
sc.submit_target = dnnlib.SubmitTarget.LOCAL
sc.local.do_not_copy_source_files = True
kwargs = EasyDict(train)
kwargs.update(G_args=G, D_args=D, G_opt_args=G_opt, D_opt_args=D_opt, G_loss_args=G_loss, D_loss_args=D_loss)
kwargs.update(dataset_args=dataset_args, sched_args=sched, grid_args=grid, metric_arg_list=metrics, tf_config=tf_config)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = result_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)
def create_model(config_id='config-f',
gamma=None,
height=512,
width=512,
cond=None,
label_size=0):
train = EasyDict(run_func_name='training.diagnostic.create_initial_pkl'
) # Options for training loop.
G = EasyDict(func_name='training.networks_stylegan2.G_main'
) # Options for generator network.
D = EasyDict(func_name='training.networks_stylegan2.D_stylegan2'
) # Options for discriminator network.
D_loss = EasyDict(func_name='training.loss.D_logistic_r1'
) # Options for discriminator loss.
sched = EasyDict() # Options for TrainingSchedule.
sc = dnnlib.SubmitConfig() # Options for dnnlib.submit_run().
tf_config = {'rnd.np_random_seed': 1000} # Options for tflib.init_tf().
sched.minibatch_size_base = 192
sched.minibatch_gpu_base = 3
D_loss.gamma = 10
desc = 'stylegan2'
dataset_args = EasyDict() # (tfrecord_dir=dataset)
if cond:
desc += '-cond'
dataset_args.max_label_size = 'full' # conditioned on full label
desc += '-' + config_id
# Configs A-E: Shrink networks to match original StyleGAN.
if config_id != 'config-f':
G.fmap_base = D.fmap_base = 8 << 10
# Config E: Set gamma to 100 and override G & D architecture.
if config_id.startswith('config-e'):
D_loss.gamma = 100
if 'Gorig' in config_id: G.architecture = 'orig'
if 'Gskip' in config_id: G.architecture = 'skip' # (default)
if 'Gresnet' in config_id: G.architecture = 'resnet'
if 'Dorig' in config_id: D.architecture = 'orig'
if 'Dskip' in config_id: D.architecture = 'skip'
if 'Dresnet' in config_id: D.architecture = 'resnet' # (default)
# Configs A-D: Enable progressive growing and switch to networks that support it.
if config_id in ['config-a', 'config-b', 'config-c', 'config-d']:
sched.lod_initial_resolution = 8
sched.G_lrate_base = sched.D_lrate_base = 0.001
sched.G_lrate_dict = sched.D_lrate_dict = {
128: 0.0015,
256: 0.002,
512: 0.003,
1024: 0.003
}
sched.minibatch_size_base = 32 # (default)
sched.minibatch_size_dict = {8: 256, 16: 128, 32: 64, 64: 32}
sched.minibatch_gpu_base = 4 # (default)
sched.minibatch_gpu_dict = {8: 32, 16: 16, 32: 8, 64: 4}
G.synthesis_func = 'G_synthesis_stylegan_revised'
D.func_name = 'training.networks_stylegan2.D_stylegan'
# Configs A-C: Disable path length regularization.
if config_id in ['config-a', 'config-b', 'config-c']:
G_loss = EasyDict(func_name='training.loss.G_logistic_ns')
# Configs A-B: Disable lazy regularization.
if config_id in ['config-a', 'config-b']:
train.lazy_regularization = False
# Config A: Switch to original StyleGAN networks.
if config_id == 'config-a':
G = EasyDict(func_name='training.networks_stylegan.G_style')
D = EasyDict(func_name='training.networks_stylegan.D_basic')
if gamma is not None:
D_loss.gamma = gamma
G.update(resolution_h=height)
G.update(resolution_w=width)
D.update(resolution_h=height)
D.update(resolution_w=width)
sc.submit_target = dnnlib.SubmitTarget.DIAGNOSTIC
sc.local.do_not_copy_source_files = True
kwargs = EasyDict(train)
# [EDITED]
kwargs.update(G_args=G,
D_args=D,
tf_config=tf_config,
config_id=config_id,
resolution_h=height,
resolution_w=width,
label_size=label_size)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_desc = desc
dnnlib.submit_diagnostic(**kwargs)
return f'network-initial-config-f-{height}x{width}-{label_size}.pkl'
def run(dataset,
data_dir,
result_dir,
config_id,
num_gpus,
total_kimg,
gamma,
mirror_augment,
metrics,
resume_run_id=None):
train = EasyDict(run_func_name='training.training_loop.training_loop'
) # Options for training loop.
G = EasyDict(func_name='training.networks_stylegan2.G_main'
) # Options for generator network.
D = EasyDict(func_name='training.networks_stylegan2.D_stylegan2'
) # Options for discriminator network.
G_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for generator optimizer.
D_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for discriminator optimizer.
G_loss = EasyDict(func_name='training.loss.G_logistic_ns_pathreg'
) # Options for generator loss.
D_loss = EasyDict(func_name='training.loss.D_logistic_r1'
) # Options for discriminator loss.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size='8k', layout='random') # Options for setup_snapshot_image_grid().
sc = dnnlib.SubmitConfig() # Options for dnnlib.submit_run().
tf_config = {'rnd.np_random_seed': 1000} # Options for tflib.init_tf().
if resume_run_id is not None:
# Resume from the ID of the results directory given
ids = sorted(get_valid_runids(result_dir))
if resume_run_id == 'recent':
resume_run_id = ids[-1][0]
else:
try:
resume_run_id = int(resume_run_id)
except ValueError:
raise RuntimeError(
'--resume argument is invalid (must be number, or "recent"): {}'
.format(resume_run_id))
try:
rundir_name = next(x[1] for x in ids if x[0] == resume_run_id)
except StopIteration:
raise RuntimeError(
'Could not find results directory with run ID {} (options: {})'
.format(resume_run_id, [x[0] for x in ids]))
# Find kimg & pkl file
rundir = os.path.join(result_dir, rundir_name)
pkls = [
name for name in os.listdir(rundir)
if name.startswith('network-snapshot-') and name.endswith('.pkl')
]
kimgs = sorted([(int(
pkl.replace('network-snapshot-', '').replace('.pkl', '')), pkl)
for pkl in pkls],
key=lambda x: x[0])
if len(kimgs) == 0:
raise RuntimeError(
'No network-snapshot-[0-9].pkl files found in {}'.format(
rundir))
max_kimg = kimgs[-1][0]
pkl_name = kimgs[-1][1]
# Get wall clock time
logfilepath = os.path.join(rundir, 'log.txt')
with open(logfilepath, 'r') as f:
logfile = f.read()
for line in logfile.splitlines():
if 'kimg {}'.format(max_kimg) in line:
if 'time ' not in line:
raise RuntimeError(
'Invalid log file: {}'.format(logfilepath))
line = line.split('time ')[1]
if 'sec/tick' not in line:
raise RuntimeError(
'Invalid log file: {}'.format(logfilepath))
line = line.split('sec/tick')[0].strip()
# Parse d h m s, etc.
total_seconds_formatted = line
total_seconds = 0
if 'd' in line:
arr = line.split('d')
days = int(arr[0].strip())
total_seconds += days * 24 * 60 * 60
line = arr[1]
if 'h' in line:
arr = line.split('h')
hours = int(arr[0].strip())
total_seconds += hours * 60 * 60
line = arr[1]
if 'm' in line:
arr = line.split('m')
mins = int(arr[0].strip())
total_seconds += mins * 60
line = arr[1]
if 's' in line:
arr = line.split('s')
secs = int(arr[0].strip())
total_seconds += secs
line = arr[1]
break
# Set args for training
train.resume_pkl = os.path.join(rundir, pkl_name)
train.resume_kimg = max_kimg
train.resume_time = total_seconds
print('Resuming from run {}: kimg {}, time {}'.format(
rundir_name, max_kimg, total_seconds_formatted))
train.data_dir = data_dir
train.total_kimg = total_kimg
train.mirror_augment = mirror_augment
train.image_snapshot_ticks = train.network_snapshot_ticks = 1
sched.G_lrate_base = sched.D_lrate_base = 0.002
sched.minibatch_size_base = 32
sched.minibatch_gpu_base = 4
D_loss.gamma = 10
metrics = [metric_defaults[x] for x in metrics]
desc = 'stylegan2'
desc += '-' + dataset
dataset_args = EasyDict(tfrecord_dir=dataset)
assert num_gpus in [1, 2, 4, 8]
sc.num_gpus = num_gpus
desc += '-%dgpu' % num_gpus
assert config_id in _valid_configs
desc += '-' + config_id
# Configs A-E: Shrink networks to match original StyleGAN.
if config_id != 'config-f':
G.fmap_base = D.fmap_base = 8 << 10
# Config E: Set gamma to 100 and override G & D architecture.
if config_id.startswith('config-e'):
D_loss.gamma = 100
if 'Gorig' in config_id: G.architecture = 'orig'
if 'Gskip' in config_id: G.architecture = 'skip' # (default)
if 'Gresnet' in config_id: G.architecture = 'resnet'
if 'Dorig' in config_id: D.architecture = 'orig'
if 'Dskip' in config_id: D.architecture = 'skip'
if 'Dresnet' in config_id: D.architecture = 'resnet' # (default)
# Configs A-D: Enable progressive growing and switch to networks that support it.
if config_id in ['config-a', 'config-b', 'config-c', 'config-d']:
sched.lod_initial_resolution = 8
sched.G_lrate_base = sched.D_lrate_base = 0.001
sched.G_lrate_dict = sched.D_lrate_dict = {
128: 0.0015,
256: 0.002,
512: 0.003,
1024: 0.003
}
sched.minibatch_size_base = 32 # (default)
sched.minibatch_size_dict = {8: 256, 16: 128, 32: 64, 64: 32}
sched.minibatch_gpu_base = 4 # (default)
sched.minibatch_gpu_dict = {8: 32, 16: 16, 32: 8, 64: 4}
G.synthesis_func = 'G_synthesis_stylegan_revised'
D.func_name = 'training.networks_stylegan2.D_stylegan'
# Configs A-C: Disable path length regularization.
if config_id in ['config-a', 'config-b', 'config-c']:
G_loss = EasyDict(func_name='training.loss.G_logistic_ns')
# Configs A-B: Disable lazy regularization.
if config_id in ['config-a', 'config-b']:
train.lazy_regularization = False
# Config A: Switch to original StyleGAN networks.
if config_id == 'config-a':
G = EasyDict(func_name='training.networks_stylegan.G_style')
D = EasyDict(func_name='training.networks_stylegan.D_basic')
if gamma is not None:
D_loss.gamma = gamma
sc.submit_target = dnnlib.SubmitTarget.LOCAL
sc.local.do_not_copy_source_files = True
kwargs = EasyDict(train)
kwargs.update(G_args=G,
D_args=D,
G_opt_args=G_opt,
D_opt_args=D_opt,
G_loss_args=G_loss,
D_loss_args=D_loss)
kwargs.update(dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
metric_arg_list=metrics,
tf_config=tf_config)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = result_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)
def run(dataset, data_dir, result_dir, config_id, num_gpus, total_kimg, gamma,
mirror_augment, metrics):
train = EasyDict(run_func_name='training.training_loop.training_loop'
) # Options for training loop.
G = EasyDict(func_name='training.networks_stylegan2.G_main'
) # Options for generator network.
D = EasyDict(func_name='training.networks_stylegan2.D_stylegan2'
) # Options for discriminator network.
G_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for generator optimizer.
D_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for discriminator optimizer.
G_loss = EasyDict(func_name='training.loss.G_logistic_ns_pathreg'
) # Options for generator loss.
D_loss = EasyDict(func_name='training.loss.D_logistic_r1'
) # Options for discriminator loss.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size='8k', layout='random') # Options for setup_snapshot_image_grid().
sc = dnnlib.SubmitConfig() # Options for dnnlib.submit_run().
tf_config = {'rnd.np_random_seed': 1000} # Options for tflib.init_tf().
train.data_dir = data_dir
train.total_kimg = total_kimg
train.mirror_augment = mirror_augment
train.image_snapshot_ticks = train.network_snapshot_ticks = 10
sched.G_lrate_base = sched.D_lrate_base = 0.002
sched.minibatch_size_base = 32
sched.minibatch_gpu_base = 4
D_loss.gamma = 10
metrics = [metric_defaults[x] for x in metrics]
desc = 'stylegan2'
desc += '-' + dataset
dataset_args = EasyDict(tfrecord_dir=dataset)
assert num_gpus in [1, 2, 4, 8]
sc.num_gpus = num_gpus
desc += '-%dgpu' % num_gpus
assert config_id in _valid_configs
desc += '-' + config_id
# Configs A-E: Shrink networks to match original StyleGAN.
if config_id not in ['config-f', 'config-l']:
G.fmap_base = D.fmap_base = 8 << 10
# Config L: Generator training only
if config_id == 'config-l':
# Use labels as latent vector input
dataset_args.max_label_size = "full"
# Deactivate methods specific for GAN training
G.truncation_psi = None
G.randomize_noise = False
G.style_mixing_prob = None
G.dlatent_avg_beta = None
G.conditional_labels = False
# Refinement training
G_loss.func_name = 'training.loss.G_reconstruction'
train.run_func_name = 'training.training_loop.training_loop_refinement'
# G.freeze_layers = ["mapping", "noise"]#, "4x4", "8x8", "16x16", "32x32"]
# Network for refinement
train.resume_pkl = "nets/stylegan2-ffhq-config-f.pkl" # TODO init net
train.resume_with_new_nets = True
# Maintenance tasks
sched.tick_kimg_base = 1 # 1 tick = 5000 images (metric update)
sched.tick_kimg_dict = {}
train.image_snapshot_ticks = 5 # Save every 5000 images
train.network_snapshot_ticks = 10 # Save every 10000 images
# Training parameters
sched.G_lrate_base = 1e-4
train.G_smoothing_kimg = 0.0
sched.minibatch_size_base = sched.minibatch_gpu_base * num_gpus # 4 per GPU
# Config E: Set gamma to 100 and override G & D architecture.
if config_id.startswith('config-e'):
D_loss.gamma = 100
if 'Gorig' in config_id: G.architecture = 'orig'
if 'Gskip' in config_id: G.architecture = 'skip' # (default)
if 'Gresnet' in config_id: G.architecture = 'resnet'
if 'Dorig' in config_id: D.architecture = 'orig'
if 'Dskip' in config_id: D.architecture = 'skip'
if 'Dresnet' in config_id: D.architecture = 'resnet' # (default)
# Configs A-D: Enable progressive growing and switch to networks that support it.
if config_id in ['config-a', 'config-b', 'config-c', 'config-d']:
sched.lod_initial_resolution = 8
sched.G_lrate_base = sched.D_lrate_base = 0.001
sched.G_lrate_dict = sched.D_lrate_dict = {
128: 0.0015,
256: 0.002,
512: 0.003,
1024: 0.003
}
sched.minibatch_size_base = 32 # (default)
sched.minibatch_size_dict = {8: 256, 16: 128, 32: 64, 64: 32}
sched.minibatch_gpu_base = 4 # (default)
sched.minibatch_gpu_dict = {8: 32, 16: 16, 32: 8, 64: 4}
G.synthesis_func = 'G_synthesis_stylegan_revised'
D.func_name = 'training.networks_stylegan2.D_stylegan'
# Configs A-C: Disable path length regularization.
if config_id in ['config-a', 'config-b', 'config-c']:
G_loss = EasyDict(func_name='training.loss.G_logistic_ns')
# Configs A-B: Disable lazy regularization.
if config_id in ['config-a', 'config-b']:
train.lazy_regularization = False
# Config A: Switch to original StyleGAN networks.
if config_id == 'config-a':
G = EasyDict(func_name='training.networks_stylegan.G_style')
D = EasyDict(func_name='training.networks_stylegan.D_basic')
if gamma is not None:
D_loss.gamma = gamma
sc.submit_target = dnnlib.SubmitTarget.LOCAL
sc.local.do_not_copy_source_files = True
kwargs = EasyDict(train)
kwargs.update(G_args=G,
D_args=D,
G_opt_args=G_opt,
D_opt_args=D_opt,
G_loss_args=G_loss,
D_loss_args=D_loss)
kwargs.update(dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
metric_arg_list=metrics,
tf_config=tf_config)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = result_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)
def run(
dataset,
data_dir,
result_dir,
config_id,
num_gpus,
total_kimg,
gamma,
mirror_augment,
metrics,
resume_pkl=None,
resume_kimg=None,
):
train = EasyDict(
run_func_name="training.training_loop.training_loop",
# training resume options:
resume_pkl=
resume_pkl, # Network pickle to resume training from, None = train from scratch.
resume_kimg=
resume_kimg, # Assumed training progress at the beginning. Affects reporting and training schedule.
) # Options for training loop.
G = EasyDict(func_name="training.networks_stylegan2.G_main"
) # Options for generator network.
D = EasyDict(func_name="training.networks_stylegan2.D_stylegan2"
) # Options for discriminator network.
G_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for generator optimizer.
D_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for discriminator optimizer.
G_loss = EasyDict(func_name="training.loss.G_logistic_ns_pathreg"
) # Options for generator loss.
D_loss = EasyDict(func_name="training.loss.D_logistic_r1"
) # Options for discriminator loss.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size="8k", layout="random") # Options for setup_snapshot_image_grid().
sc = dnnlib.SubmitConfig() # Options for dnnlib.submit_run().
tf_config = {"rnd.np_random_seed": 1000} # Options for tflib.init_tf().
train.data_dir = data_dir
train.total_kimg = total_kimg
train.mirror_augment = mirror_augment
train.image_snapshot_ticks = train.network_snapshot_ticks = 10
sched.G_lrate_base = sched.D_lrate_base = 0.002
sched.minibatch_size_base = 32
sched.minibatch_gpu_base = 4
D_loss.gamma = 10
metrics = [metric_defaults[x] for x in metrics]
desc = "stylegan2"
desc += "-" + dataset
dataset_args = EasyDict(tfrecord_dir=dataset)
assert num_gpus in [1, 2, 4, 8]
sc.num_gpus = num_gpus
desc += "-%dgpu" % num_gpus
assert config_id in _valid_configs
desc += "-" + config_id
# Configs A-E: Shrink networks to match original StyleGAN.
if config_id != "config-f":
G.fmap_base = D.fmap_base = 8 << 10
# Config E: Set gamma to 100 and override G & D architecture.
if config_id.startswith("config-e"):
D_loss.gamma = 100
if "Gorig" in config_id:
G.architecture = "orig"
if "Gskip" in config_id:
G.architecture = "skip" # (default)
if "Gresnet" in config_id:
G.architecture = "resnet"
if "Dorig" in config_id:
D.architecture = "orig"
if "Dskip" in config_id:
D.architecture = "skip"
if "Dresnet" in config_id:
D.architecture = "resnet" # (default)
# Configs A-D: Enable progressive growing and switch to networks that support it.
if config_id in ["config-a", "config-b", "config-c", "config-d"]:
sched.lod_initial_resolution = 8
sched.G_lrate_base = sched.D_lrate_base = 0.001
sched.G_lrate_dict = sched.D_lrate_dict = {
128: 0.0015,
256: 0.002,
512: 0.003,
1024: 0.003,
}
sched.minibatch_size_base = 32 # (default)
sched.minibatch_size_dict = {8: 256, 16: 128, 32: 64, 64: 32}
sched.minibatch_gpu_base = 4 # (default)
sched.minibatch_gpu_dict = {8: 32, 16: 16, 32: 8, 64: 4}
G.synthesis_func = "G_synthesis_stylegan_revised"
D.func_name = "training.networks_stylegan2.D_stylegan"
# Configs A-C: Disable path length regularization.
if config_id in ["config-a", "config-b", "config-c"]:
G_loss = EasyDict(func_name="training.loss.G_logistic_ns")
# Configs A-B: Disable lazy regularization.
if config_id in ["config-a", "config-b"]:
train.lazy_regularization = False
# Config A: Switch to original StyleGAN networks.
if config_id == "config-a":
G = EasyDict(func_name="training.networks_stylegan.G_style")
D = EasyDict(func_name="training.networks_stylegan.D_basic")
if gamma is not None:
D_loss.gamma = gamma
sc.submit_target = dnnlib.SubmitTarget.LOCAL
sc.local.do_not_copy_source_files = True
kwargs = EasyDict(train)
kwargs.update(
G_args=G,
D_args=D,
G_opt_args=G_opt,
D_opt_args=D_opt,
G_loss_args=G_loss,
D_loss_args=D_loss,
)
kwargs.update(
dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
metric_arg_list=metrics,
tf_config=tf_config,
)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = result_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)