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

Query of theorem of handling residual networks with ADD layer #8

Open
JacksonZyy opened this issue Nov 21, 2023 · 0 comments
Open

Query of theorem of handling residual networks with ADD layer #8

JacksonZyy opened this issue Nov 21, 2023 · 0 comments

Comments

@JacksonZyy
Copy link

Dear,

I am very impressed with how you enforce constraints with Lagrange multipliers.
In the paper, I notice that affine layers are encoded with z(i) = W(i)z(i-1)+b(i), which only captures fully-connected/convolutional/... layers's behavior.
But for an Add layer in residual networks in ONNX model, its function is like z(i) = z(i-1)+z(i-k). I fail to see how your process extends to residual networks, but I did observe residual networks in your experiments.
So I wonder if there is a theorem behind handling the residual networks? And is this theorem (if any) just a customization of your existing version?
Thank you in advance for your clarification!

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

No branches or pull requests

1 participant