pytorch / pytorch/vision

Add other swin architectures.

Open
#6,602 6 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement module: models
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

🚀 The feature

The original paper describes a few more configurations based on swin Transformer.

  1. Swin Large: Simply a large model of swin transformer, needs a few config tweaks and we can port weights probably?
  2. SwinMLP: MLP Mixer Based SwinTransformer. Described in the original paper.
  3. SwinMoe: Mixture of experts for Swin https://arxiv.org/pdf/2204.09636.pdf
Motivation, pitch

I think that Swin Large and SwinMLP could be good candidates as they need few edits for implementation.

I'm not sure if we can port weights, or train from scratch. As adding weights and implementation would also add a CI job and maintaining it.

Alternatives

No response

Additional context

No response

cc @datumbox

Contributor guide

Open the contributing guide

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 by reviewing the existing Swin Transformer implementation and the configurations described in the original paper, including Swin Large and SwinMLP; the linked SwinMoe paper defines another possible scope. First establish which architecture should be supported, whether pretrained weights are required, and whether CI coverage is expected. Done means an agreed implementation scope with corresponding weights and CI requirements addressed.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.