lllyasviel / lllyasviel/ControlNet

About Eq(5) in paper

Open
#474 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
34.1k
Forks
3k
PR merge metrics
No merged PRs in 30d

Description

Hi,
I have a question about eq(5) in paper,
$$\mathcal{Z}(I;{W, B})_{p, i} = B_i + \sum_j^c I_{p,i}W_{i,j}$$
why not
$$\mathcal{Z}(I;{W, B})_{p, i} = B_i + \sum_j^c I_{\textcolor{red}{p,j}}W_{i,j}$$

the output of $\mathcal{Z}_{p, i}$ is producted by the i-th 1*1 conv kernel params $W_i$ and $B_i$, with the input of $I_p$?

have I missed something?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with Eq. (5) in the referenced paper and compare its index notation with the surrounding definitions of I, W, and B. Done means resolving whether the displayed index is a typo or explaining why the stated summation is correct in the paper's notation.

Written by the indexing model from the issue text.

Assessment

Domain
documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.