Skip to content
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.

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

Add Conv and ConvTranspose #42

Merged
merged 10 commits into from
Oct 9, 2023
Merged

Add Conv and ConvTranspose #42

merged 10 commits into from
Oct 9, 2023

Conversation

dlwh
Copy link
Member

@dlwh dlwh commented Oct 6, 2023

Fixes #23

@dlwh dlwh changed the title rough cut at convolution Add Conv and ConvTranspose Oct 9, 2023
@dlwh dlwh merged commit bed0d7d into main Oct 9, 2023
2 checks passed
@dlwh dlwh deleted the conv branch October 9, 2023 01:46
@leizaf
Copy link

leizaf commented Oct 14, 2023

class _ConvBase(eqx.Module):
    """
    Base class for Conv and ConvTranspose. Mostly just contains shared code.
    """

    Spatial: tuple[str | Axis, ...] = eqx.field(static=True)
    In: Axis = eqx.field(static=True)
    Out: Axis = eqx.field(static=True)
    weight: NamedArray = eqx.field(static=True)
    bias: Optional[NamedArray] = eqx.field(static=True)

How come weight and bias are static fields? Doesn't this prevent grad? It also prevents me from casting their type.

@dlwh
Copy link
Member Author

dlwh commented Oct 14, 2023 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

NN Layers: Convolutions
2 participants