def generate_videos(args, eigenvectors):
clips_dir = os.path.join(args.out, 'videos')
if not os.path.isdir(clips_dir):
os.mkdir(clips_dir)
if args.samples_for_videos is None:
dim_z = load_generator(args.__dict__, args.gan_weights).dim_z
zs = torch.randn((4, dim_z)).cuda()
else:
zs = torch.load(args.samples_for_videos).cuda()
print('Making videos...')
for i, eigenvector in tqdm(enumerate(eigenvectors)):
eigenvector = eigenvector.cuda()
for amplitude in [10, 50, 100, 200, 500]:
generator = load_generator(args.__dict__, args.gan_weights)
wd = ConstantWeightDeformator(
generator=generator,
conv_layer_ix=args.gan_conv_layer_index,
direction=eigenvector)
clip_path = os.path.join(clips_dir,
f'direction{i}_amplitude{amplitude}')
make_video(generator=generator,
zs=zs,
wd=wd,
file_dest=clip_path,
shift_from=-amplitude,
shift_to=amplitude,
step=amplitude / 50.,
interpolate=args.video_interpolate)
def objective(trial: optuna.trial.Trial):
print(f"[Optuna]: Trial #{trial.number}")
G = load_generator(args.__dict__, weights_path, args.w_shift)
params = Params(**args.__dict__)
params.batch_size = 128
params.directions_count = 200
params.deformator_lr = trial.suggest_float("deformator_lr", 1e-4, 1e-4, log=True)
params.shift_predictor_lr = params.deformator_lr
# params.torch_grad = True if trial.suggest_int("torch_grad", 0, 1) else False
deformator = LatentDeformator(shift_dim=G.dim_shift,
input_dim=params.directions_count,
out_dim=params.max_latent_dim,
type=DEFORMATOR_TYPE_DICT[args.deformator],
random_init=args.deformator_random_init
).cuda()
# deformator = MyDeformator(48*8*8, 48*8*8)
if args.shift_predictor == 'ResNet':
shift_predictor = LatentShiftPredictor(params.directions_count, args.shift_predictor_size).cuda()
elif args.shift_predictor == 'LeNet':
shift_predictor = LeNetShiftPredictor(
params.directions_count, 1 if args.gan_type == 'SN_MNIST' else 3).cuda()
# training
args.shift_distribution = SHIFT_DISTRIDUTION_DICT[args.shift_distribution_key]
# update dims with respect to the deformator if some of params are None
params.directions_count = int(deformator.input_dim)
params.max_latent_dim = int(deformator.out_dim)
trainer = Trainer(params, out_dir=args.out, verbose=True)
loss = trainer.train(G, deformator, shift_predictor, multi_gpu=args.multi_gpu, trial=trial)
# my_save_results_charts(G, deformator, params, trainer.log_dir)
compute_DVN(G, deformator, f'DVN_{args.gan_type}_{args.deformator}_{params.directions_count}.pt')
return loss
parser.add_argument('--epsilon', type=float, default=0.1)
parser.add_argument('--lpips_net', type=str, default='vgg')
parser.add_argument('--make_videos', type=bool, default=True)
parser.add_argument('--samples_for_videos', type=str, default=None)
parser.add_argument('--out', type=str, required=True)
parser.add_argument('--lpips_interpolation_size', type=int, default=64)
parser.add_argument('--video_interpolate', type=int, default=None)
args = parser.parse_args()
if not os.path.exists(args.out):
print(f'Out: {args.out}')
os.mkdir(args.out)
lpips_model = lpips.LPIPS(net=args.lpips_net).cuda()
generator = load_generator(args.__dict__, args.gan_weights)
hvp = HVP_forward(generator=generator,
lpips_model=lpips_model,
conv_layer_ix=args.gan_conv_layer_index,
batch_size=args.batch_size,
cache_path=args.out,
lpips_interpolation_size=args.lpips_interpolation_size)
eigenvectors = hvp.find_top_n_eigenvectors(n=args.num_eigenvectors,
num_samples=args.num_samples,
max_iter=args.max_iter,
epsilon=args.epsilon)
eigenvectors = torch.stack([
F.normalize(eig.view(-1), p=2, dim=0).view(eig.shape)
def main():
parser = argparse.ArgumentParser(description='Latent space rectification')
for key, val in Params().__dict__.items():
target_type = type(val) if val is not None else int
parser.add_argument('--{}'.format(key), type=target_type, default=None)
parser.add_argument('--out', type=str, required=True, help='results directory')
parser.add_argument('--gan_type', type=str, choices=WEIGHTS.keys(), help='generator model type')
parser.add_argument('--gan_weights', type=str, default=None, help='path to generator weights')
parser.add_argument('--resolution', type=int, required=True)
parser.add_argument('--target_class', nargs='+', type=int, default=[239],
help='classes to use for conditional GANs')
parser.add_argument('--deformator', type=str, default='ortho',
choices=DEFORMATOR_TYPE_DICT.keys(), help='deformator type')
parser.add_argument('--deformator_random_init', type=bool, default=True)
parser.add_argument('--deformator_target', type=str, default='latent',
choices=DEFORMATOR_TARGET_DICT.keys())
parser.add_argument('--deformator_conv_layer_index', type=int, default=3)
parser.add_argument('--basis_vectors_path', type=str)
parser.add_argument('--shift_predictor_size', type=int, help='reconstructor resolution')
parser.add_argument('--shift_predictor', type=str,
choices=['ResNet', 'LeNet'], default='ResNet', help='reconstructor type')
parser.add_argument('--shift_distribution_key', type=str,
choices=SHIFT_DISTRIDUTION_DICT.keys())
parser.add_argument('--make_videos', type=bool, default=True)
parser.add_argument('--samples_for_videos', type=str, default=None)
parser.add_argument('--video_interpolate', type=int, default=None)
parser.add_argument('--seed', type=int, default=2)
parser.add_argument('--device', type=int, default=0)
parser.add_argument('--multi_gpu', type=bool, default=False,
help='Run generator in parallel. Be aware of old pytorch versions:\
https://github.com/pytorch/pytorch/issues/17345')
# model-specific
parser.add_argument('--w_shift', type=bool, default=True,
help='latent directions search in w-space for StyleGAN')
args = parser.parse_args()
torch.cuda.set_device(args.device)
random.seed(args.seed)
torch.random.manual_seed(args.seed)
save_command_run_params(args)
# init models
if args.gan_weights is not None:
weights_path = args.gan_weights
else:
weights_path = WEIGHTS[args.gan_type]
G = load_generator(args.__dict__, weights_path, args.w_shift)
if args.deformator_target == 'latent':
deformator = LatentDeformator(
shift_dim=G.dim_shift,
input_dim=args.directions_count,
out_dim=args.max_latent_dim,
type=DEFORMATOR_TYPE_DICT[args.deformator],
random_init=args.deformator_random_init
).cuda()
elif args.deformator_target == 'weight_svd':
deformator = WeightDeformatorSVDBasis(
generator=G,
conv_layer_ix=args.deformator_conv_layer_index,
directions_count=args.directions_count
).cuda()
G = G.cuda()
dim_shift = args.directions_count
elif args.deformator_target == 'weight_fixedbasis':
assert args.basis_vectors_path is not None
deformator = WeightDeformatorFixedBasis(
generator=G,
conv_layer_ix=args.deformator_conv_layer_index,
directions_count=args.directions_count,
basis_vectors_path=args.basis_vectors_path
).cuda()
G = G.cuda()
dim_shift = args.directions_count
else:
raise ValueError("Unknown deformator_target")
if args.shift_predictor == 'ResNet':
shift_predictor = LatentShiftPredictor(
dim_shift, args.shift_predictor_size).cuda()
elif args.shift_predictor == 'LeNet':
shift_predictor = LeNetShiftPredictor(
dim_shift, 1 if args.gan_type == 'SN_MNIST' else 3).cuda()
# training
args.shift_distribution = SHIFT_DISTRIDUTION_DICT[args.shift_distribution_key]
params = Params(**args.__dict__)
# update dims with respect to the deformator if some of params are None
if args.deformator_target == 'latent':
params.directions_count = int(deformator.input_dim)
params.max_latent_dim = int(deformator.out_dim)
trainer = Trainer(params, out_dir=args.out)
trainer.train(G, deformator, shift_predictor, multi_gpu=args.multi_gpu)
if args.make_videos:
if 'weight_' not in args.deformator_target:
sys.stderr.write("Making video is available only for weight deformations.\n")
else:
generate_videos(args, G, deformator)
if args.deformator_target == 'latent':
save_results_charts(G, deformator, params, trainer.log_dir)
def main():
parser = argparse.ArgumentParser(description='Latent space rectification')
for key, val in Params().__dict__.items():
target_type = type(val) if val is not None else int
parser.add_argument('--{}'.format(key), type=target_type, default=None)
parser.add_argument('--out',
type=str,
required=True,
help='results directory')
parser.add_argument('--gan_type',
type=str,
choices=WEIGHTS.keys(),
help='generator model type')
parser.add_argument('--gan_weights',
type=str,
default=None,
help='path to generator weights')
parser.add_argument('--target_class',
nargs='+',
type=int,
default=[239],
help='classes to use for conditional GANs')
parser.add_argument('--deformator',
type=str,
default='ortho',
choices=DEFORMATOR_TYPE_DICT.keys(),
help='deformator type')
parser.add_argument('--deformator_random_init', type=bool, default=True)
parser.add_argument('--shift_predictor_size',
type=int,
help='reconstructor resolution')
parser.add_argument('--shift_predictor',
type=str,
choices=['ResNet', 'LeNet'],
default='ResNet',
help='reconstructor type')
parser.add_argument('--shift_distribution_key',
type=str,
choices=SHIFT_DISTRIDUTION_DICT.keys())
parser.add_argument('--seed', type=int, default=2)
parser.add_argument('--device', type=int, default=0)
parser.add_argument(
'--multi_gpu',
type=bool,
default=False,
help='Run generator in parallel. Be aware of old pytorch versions:\
https://github.com/pytorch/pytorch/issues/17345')
# model-specific
parser.add_argument(
'--w_shift',
type=bool,
default=True,
help='latent directions search in w-space for StyleGAN')
args = parser.parse_args()
torch.cuda.set_device(args.device)
random.seed(args.seed)
torch.random.manual_seed(args.seed)
save_command_run_params(args)
# init models
if args.gan_weights is not None:
weights_path = args.gan_weights
else:
weights_path = WEIGHTS[args.gan_type]
G = load_generator(args.__dict__, weights_path, args.w_shift)
deformator = LatentDeformator(
shift_dim=G.dim_shift,
input_dim=args.directions_count,
out_dim=args.max_latent_dim,
type=DEFORMATOR_TYPE_DICT[args.deformator],
random_init=args.deformator_random_init).cuda()
if args.shift_predictor == 'ResNet':
shift_predictor = LatentShiftPredictor(
G.dim_shift, args.shift_predictor_size).cuda()
elif args.shift_predictor == 'LeNet':
shift_predictor = LeNetShiftPredictor(
G.dim_shift, 1 if args.gan_type == 'SN_MNIST' else 3).cuda()
# training
args.shift_distribution = SHIFT_DISTRIDUTION_DICT[
args.shift_distribution_key]
params = Params(**args.__dict__)
# update dims with respect to the deformator if some of params are None
params.directions_count = int(deformator.input_dim)
params.max_latent_dim = int(deformator.out_dim)
trainer = Trainer(params, out_dir=args.out)
trainer.train(G, deformator, shift_predictor, multi_gpu=args.multi_gpu)
save_results_charts(G, deformator, params, trainer.log_dir)