def run_eval(dataset, resolution, result_dir, DiffAugment, num_gpus, batch_size, total_kimg, ema_kimg, num_samples, gamma, fmap_base, fmap_max, latent_size, mirror_augment, impl, metrics, resume, resume_kimg, num_repeats, eval):
dataset, total_samples = dataset_tool.create_from_images(dataset, resolution)
print('Evaluating metrics "%s" for "%s"...' % (','.join(metrics), resume))
tflib.init_tf()
resume = pretrained_networks.get_path_or_url(resume)
dataset_args = dnnlib.EasyDict(tfrecord_dir=dataset, num_samples=num_samples or total_samples, resolution=resolution, from_tfrecords=True)
metric_group = metric_base.MetricGroup([metric_defaults[metric] for metric in metrics], num_repeats=num_repeats)
metric_group.run(resume, dataset_args=dataset_args, num_gpus=num_gpus)
def run(dataset, resolution, result_dir, DiffAugment, num_gpus, batch_size,
gpu_batch, total_kimg, ema_kimg, num_samples, gamma, fmap_base,
fmap_max, latent_size, mirror_augment, impl, metrics, resume,
resume_kimg, num_repeats, eval):
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.
loss_args = EasyDict(
func_name='training.loss.ns_DiffAugment_r1') # Options for loss.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size='4k', 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.total_kimg = total_kimg
train.mirror_augment = mirror_augment
metrics = [metric_defaults[x] for x in metrics]
metric_args = EasyDict(cache_dir=dataset, num_repeats=num_repeats)
# preprocess dataset into tfrecords
dataset, total_samples = dataset_tool.create_from_images(
dataset, resolution)
desc = 'DiffAugment-stylegan2' if DiffAugment else 'stylegan2'
dataset_args = EasyDict(tfrecord_dir=dataset,
resolution=resolution,
from_tfrecords=True)
desc += '-' + os.path.basename(dataset)
if resolution is not None:
desc += '-{}'.format(resolution)
if num_samples is not None:
dataset_args.num_samples = num_samples
desc += '-{}samples'.format(num_samples)
else:
dataset_args.num_samples = total_samples
if batch_size is not None:
desc += '-batch{}'.format(batch_size)
else:
batch_size = 32
assert batch_size % num_gpus == 0
sc.num_gpus = num_gpus
desc += '-%dgpu' % num_gpus
sched.minibatch_size_base = batch_size
if gpu_batch is not None:
sched.minibatch_gpu_base = gpu_batch
else:
sched.minibatch_gpu_base = batch_size // num_gpus
G.impl = D.impl = impl
if fmap_base is not None:
G.fmap_base = D.fmap_base = fmap_base
desc += '-fmap{}'.format(fmap_base)
if fmap_max is not None:
G.fmap_max = D.fmap_max = fmap_max
desc += '-fmax{}'.format(fmap_max)
if latent_size is not None:
G.latent_size = G.mapping_fmaps = G.dlatent_size = latent_size
desc += '-latent{}'.format(latent_size)
if gamma is not None:
loss_args.gamma = gamma
desc += '-gamma{}'.format(gamma)
if DiffAugment:
loss_args.policy = DiffAugment
desc += '-' + DiffAugment.replace(',', '-')
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,
loss_args=loss_args)
kwargs.update(dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
metric_arg_list=metrics,
tf_config=tf_config)
kwargs.update(resume_pkl=resume,
resume_kimg=resume_kimg,
resume_with_new_nets=True)
kwargs.update(metric_args=metric_args)
if ema_kimg is not None:
kwargs.update(G_ema_kimg=ema_kimg)
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, train_dir, config, d_aug, diffaug_policy, cond, ops, jpg_data, mirror, mirror_v, \
lod_step_kimg, batch_size, resume, resume_kimg, finetune, num_gpus, ema_kimg, gamma, freezeD):
# dataset (tfrecords) - preprocess or get
tfr_files = file_list(os.path.dirname(dataset), 'tfr')
tfr_files = [f for f in tfr_files if basename(dataset) in f]
if len(tfr_files) == 0:
tfr_file, total_samples = create_from_images(dataset, jpg=jpg_data)
else:
tfr_file = tfr_files[0]
dataset_args = EasyDict(tfrecord=tfr_file, jpg_data=jpg_data)
desc = basename(tfr_file).split('-')[0]
# training functions
if d_aug: # https://github.com/mit-han-lab/data-efficient-gans
train = EasyDict(
run_func_name='training.training_loop_diffaug.training_loop'
) # Options for training loop (Diff Augment method)
loss_args = EasyDict(
func_name='training.loss_diffaug.ns_DiffAugment_r1',
policy=diffaug_policy) # Options for loss (Diff Augment method)
else: # original nvidia
train = EasyDict(run_func_name='training.training_loop.training_loop'
) # Options for training loop (original from NVidia)
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.
# network functions
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.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size='1080p',
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().
G.impl = D.impl = ops
# resolutions
data_res = basename(tfr_file).split('-')[-1].split(
'x') # get resolution from dataset filename
data_res = list(reversed([int(x)
for x in data_res])) # convert to int list
init_res, resolution, res_log2 = calc_init_res(data_res)
if init_res != [4, 4]:
print(' custom init resolution', init_res)
G.init_res = D.init_res = list(init_res)
train.setname = desc + config
desc = '%s-%d-%s' % (desc, resolution, config)
# training schedule
sched.lod_training_kimg = lod_step_kimg
sched.lod_transition_kimg = lod_step_kimg
train.total_kimg = lod_step_kimg * res_log2 * 2 # a la ProGAN
if finetune:
train.total_kimg = 15000 # should start from ~10k kimg
train.image_snapshot_ticks = 1
train.network_snapshot_ticks = 5
train.mirror_augment = mirror
train.mirror_augment_v = mirror_v
# learning rate
if config == 'e':
if finetune: # uptrain 1024
sched.G_lrate_base = 0.001
else: # train 1024
sched.G_lrate_base = 0.001
sched.G_lrate_dict = {0: 0.001, 1: 0.0007, 2: 0.0005, 3: 0.0003}
sched.lrate_step = 1500 # period for stepping to next lrate, in kimg
if config == 'f':
# sched.G_lrate_base = 0.0003
sched.G_lrate_base = 0.001
sched.D_lrate_base = sched.G_lrate_base # *2 - not used anyway
sched.minibatch_gpu_base = batch_size
sched.minibatch_size_base = num_gpus * sched.minibatch_gpu_base
sc.num_gpus = num_gpus
if config == 'e':
G.fmap_base = D.fmap_base = 8 << 10
if d_aug: loss_args.gamma = 100 if gamma is None else gamma
else: D_loss.gamma = 100 if gamma is None else gamma
elif config == 'f':
G.fmap_base = D.fmap_base = 16 << 10
else:
print(' Only configs E and F are implemented')
exit()
if cond:
desc += '-cond'
dataset_args.max_label_size = 'full' # conditioned on full label
if freezeD:
D.freezeD = True
train.resume_with_new_nets = True
if d_aug:
desc += '-daug'
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)
kwargs.update(dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
tf_config=tf_config)
kwargs.update(resume_pkl=resume,
resume_kimg=resume_kimg,
resume_with_new_nets=True)
if ema_kimg is not None:
kwargs.update(G_ema_kimg=ema_kimg)
if d_aug:
kwargs.update(loss_args=loss_args)
else:
kwargs.update(G_loss_args=G_loss, D_loss_args=D_loss)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = train_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)
def run(data, train_dir, config, d_aug, diffaug_policy, cond, ops, mirror, mirror_v, \
kimg, batch_size, lrate, resume, resume_kimg, num_gpus, ema_kimg, gamma, freezeD):
# training functions
if d_aug: # https://github.com/mit-han-lab/data-efficient-gans
train = EasyDict(
run_func_name='training.training_loop_diffaug.training_loop'
) # Options for training loop (Diff Augment method)
loss_args = EasyDict(
func_name='training.loss_diffaug.ns_DiffAugment_r1',
policy=diffaug_policy) # Options for loss (Diff Augment method)
else: # original nvidia
train = EasyDict(run_func_name='training.training_loop.training_loop'
) # Options for training loop (original from NVidia)
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.
# network functions
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.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size='1080p',
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().
G.impl = D.impl = ops
# dataset (tfrecords) - get or create
tfr_files = file_list(os.path.dirname(data), 'tfr')
tfr_files = [
f for f in tfr_files if basename(data) == basename(f).split('-')[0]
]
if len(tfr_files) == 0 or os.stat(tfr_files[0]).st_size == 0:
tfr_file, total_samples = create_from_image_folders(
data) if cond is True else create_from_images(data)
else:
tfr_file = tfr_files[0]
dataset_args = EasyDict(tfrecord=tfr_file)
# resolutions
with tf.Graph().as_default(), tflib.create_session().as_default(): # pylint: disable=not-context-manager
dataset_obj = dataset.load_dataset(
**dataset_args) # loading the data to see what comes out
resolution = dataset_obj.resolution
init_res = dataset_obj.init_res
res_log2 = dataset_obj.res_log2
dataset_obj.close()
dataset_obj = None
if list(init_res) == [4, 4]:
desc = '%s-%d' % (basename(data), resolution)
else:
print(' custom init resolution', init_res)
desc = basename(tfr_file)
G.init_res = D.init_res = list(init_res)
train.savenames = [desc.replace(basename(data), 'snapshot'), desc]
desc += '-%s' % config
# training schedule
train.total_kimg = kimg
train.image_snapshot_ticks = 1 * num_gpus if kimg <= 1000 else 4 * num_gpus
train.network_snapshot_ticks = 5
train.mirror_augment = mirror
train.mirror_augment_v = mirror_v
sched.tick_kimg_base = 2 if train.total_kimg < 2000 else 4
# learning rate
if config == 'e':
sched.G_lrate_base = 0.001
sched.G_lrate_dict = {0: 0.001, 1: 0.0007, 2: 0.0005, 3: 0.0003}
sched.lrate_step = 1500 # period for stepping to next lrate, in kimg
if config == 'f':
sched.G_lrate_base = lrate # 0.001 for big datasets, 0.0003 for few-shot
sched.D_lrate_base = sched.G_lrate_base # *2 - not used anyway
# batch size (for 16gb memory GPU)
sched.minibatch_gpu_base = 4096 // resolution if batch_size is None else batch_size
print(' Batch size', sched.minibatch_gpu_base)
sched.minibatch_size_base = num_gpus * sched.minibatch_gpu_base
sc.num_gpus = num_gpus
if config == 'e':
G.fmap_base = D.fmap_base = 8 << 10
if d_aug: loss_args.gamma = 100 if gamma is None else gamma
else: D_loss.gamma = 100 if gamma is None else gamma
elif config == 'f':
G.fmap_base = D.fmap_base = 16 << 10
else:
print(' Only configs E and F are implemented')
exit()
if cond:
desc += '-cond'
dataset_args.max_label_size = 'full' # conditioned on full label
if freezeD:
D.freezeD = True
train.resume_with_new_nets = True
if d_aug:
desc += '-daug'
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)
kwargs.update(dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
tf_config=tf_config)
kwargs.update(resume_pkl=resume,
resume_kimg=resume_kimg,
resume_with_new_nets=True)
if ema_kimg is not None:
kwargs.update(G_ema_kimg=ema_kimg)
if d_aug:
kwargs.update(loss_args=loss_args)
else:
kwargs.update(G_loss_args=G_loss, D_loss_args=D_loss)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = train_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)
