Skip to content

Fix projection for class conditioned networks #79

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix projection for class conditioned networks #79

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions projector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,8 @@
def project(
G,
target: torch.Tensor, # [C,H,W] and dynamic range [0,255], W & H must match G output resolution
label,
label_dim,
*,
num_steps = 1000,
w_avg_samples = 10000,
Expand All @@ -35,7 +37,7 @@ def project(
noise_ramp_length = 0.75,
regularize_noise_weight = 1e5,
verbose = False,
device: torch.device
device: torch.device,
):
assert target.shape == (G.img_channels, G.img_resolution, G.img_resolution)

Expand All @@ -47,8 +49,15 @@ def logprint(*args):

# Compute w stats.
logprint(f'Computing W midpoint and stddev using {w_avg_samples} samples...')

z_samples = np.random.RandomState(123).randn(w_avg_samples, G.z_dim)
w_samples = G.mapping(torch.from_numpy(z_samples).to(device), None) # [N, L, C]

if label is not None and label_dim is not None:
onehot = np.zeros((w_avg_samples, label_dim), dtype=np.float32)
onehot[:, label] = 1
label = torch.Tensor(onehot).to(device)

w_samples = G.mapping(torch.from_numpy(z_samples).to(device), label) # [N, L, C]
w_samples = w_samples[:, :1, :].cpu().numpy().astype(np.float32) # [N, 1, C]
w_avg = np.mean(w_samples, axis=0, keepdims=True) # [1, 1, C]
w_std = (np.sum((w_samples - w_avg) ** 2) / w_avg_samples) ** 0.5
Expand Down Expand Up @@ -134,13 +143,17 @@ def logprint(*args):

@click.command()
@click.option('--network', 'network_pkl', help='Network pickle filename', required=True)
@click.option('--label', help='Class Label', type=int, default=None, required=False)
@click.option('--label-dim', help='Label Dimension', type=int, default=None, required=False)
@click.option('--target', 'target_fname', help='Target image file to project to', required=True, metavar='FILE')
@click.option('--num-steps', help='Number of optimization steps', type=int, default=1000, show_default=True)
@click.option('--seed', help='Random seed', type=int, default=303, show_default=True)
@click.option('--save-video', help='Save an mp4 video of optimization progress', type=bool, default=True, show_default=True)
@click.option('--outdir', help='Where to save the output images', required=True, metavar='DIR')
def run_projection(
network_pkl: str,
label: int,
label_dim: int,
target_fname: str,
outdir: str,
save_video: bool,
Expand Down Expand Up @@ -177,6 +190,8 @@ def run_projection(
projected_w_steps = project(
G,
target=torch.tensor(target_uint8.transpose([2, 0, 1]), device=device), # pylint: disable=not-callable
label=label,
label_dim=label_dim,
num_steps=num_steps,
device=device,
verbose=True
Expand Down