microsoft / microsoft/Swin3D

Question about Memory-efficient self-attention

Open
#24 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Cuda
Stars
298
Forks
26
Avg merge
22h 44m
Merged PRs (30d)
1

Description

Hi, it is a nice job about utilizing swin transformer to point cloud. However, I really don't understand the content of Memory-efficient self-attention.

$f_{i,h}^{*}=\frac{\sum_{j=1}^{N}(exp(e_{ij,h})f_{j}W_{V,h})}{\sum_{j=1}^{N}exp(e_{ij},h)}----(3)$

how can I understand the idea of allowing to postpone the SoftMax normalization and avoid constructing and storing ${αij,h}$ explicitly.

Calculating the denominator and numerator of Eq. (3) simultaneously is also a question that hard to fully understand.

Could you please give me some tips about how to grasp the idea of Memory-efficient self-attention.

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

No files, tests, or entry points are mentioned. First clarify whether the desired outcome is documentation explaining the memory-efficient self-attention equations or an implementation change; done should be a specific, reviewed explanation or a clearly scoped code task.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.