Skip to content

Update gaussian_blur fluxion util #431

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

Merged
merged 1 commit into from
Sep 9, 2024
Merged

Update gaussian_blur fluxion util #431

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
10 changes: 6 additions & 4 deletions src/refiners/fluxion/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,18 +70,20 @@ def gaussian_blur(
) -> Float[Tensor, "*batch channels height width"]:
assert torch.is_floating_point(tensor)

def get_gaussian_kernel1d(kernel_size: int, sigma: float) -> Float[Tensor, "kernel_size"]:
def get_gaussian_kernel1d(
kernel_size: int, sigma: float, dtype: torch.dtype, device: torch.device
) -> Float[Tensor, "kernel_size"]:
ksize_half = (kernel_size - 1) * 0.5
x = torch.linspace(-ksize_half, ksize_half, steps=kernel_size)
x = torch.linspace(-ksize_half, ksize_half, steps=kernel_size, device=device, dtype=dtype)
pdf = torch.exp(-0.5 * (x / sigma).pow(2))
kernel1d = pdf / pdf.sum()
return kernel1d

def get_gaussian_kernel2d(
kernel_size_x: int, kernel_size_y: int, sigma_x: float, sigma_y: float, dtype: DType, device: Device
) -> Float[Tensor, "kernel_size_y kernel_size_x"]:
kernel1d_x = get_gaussian_kernel1d(kernel_size_x, sigma_x).to(device, dtype=dtype)
kernel1d_y = get_gaussian_kernel1d(kernel_size_y, sigma_y).to(device, dtype=dtype)
kernel1d_x = get_gaussian_kernel1d(kernel_size_x, sigma_x, dtype, device)
kernel1d_y = get_gaussian_kernel1d(kernel_size_y, sigma_y, dtype, device)
kernel2d = torch.mm(kernel1d_y[:, None], kernel1d_x[None, :])
return kernel2d

Expand Down