Skip to content

feat: implement FluffyRocket #3

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
JSS95 merged 1 commit into from
Dec 1, 2025
Merged

feat: implement FluffyRocket #3

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
8 changes: 7 additions & 1 deletion src/fluffyrocket/fluffyrocket.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@ class FluffyRocket(MiniRocketBase):
Sharpness parameter for the sigmoid function used to compute soft PPV.
num_features : int, default=10,000
max_dilations_per_kernel : int, default=32
learnable : bool, default=False
Whether the sharpness parameter is learnable.
random_state : int, default=None

Examples
Expand Down Expand Up @@ -51,10 +53,14 @@ def __init__(
sharpness=10.0,
num_features=10_000,
max_dilations_per_kernel=32,
learnable=False,
random_state=None,
):
super().__init__(num_features, max_dilations_per_kernel, random_state)
self.sharpness = sharpness
if learnable:
self.sharpness = torch.nn.Parameter(torch.tensor(sharpness))
else:
self.sharpness = sharpness

def ppv(self, x, biases):
return torch.sigmoid(self.sharpness * (x - biases)).mean(1)