SkyworkAI / SkyworkAI/UniPic

SigLIP2 in UniPic-1

Open
#22 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
875
Forks
43
PR merge metrics
No merged PRs in 30d

Description

Similar to #9, I'm also confused why SigLIP2 isn't used in the code.

The paper says, 'Image understanding is performed using a SigLIP2 encoder to extract rich visual features, which are subsequently passed to an LLM for autoregressive text generation.'

However, the code in image2text.py uses VAE+MAR.
https://github.com/SkyworkAI/UniPic/blob/main/UniPic-1/scripts/image2text.py#L64

Also, the loss calculation does not involve the SigLIP2.
https://github.com/SkyworkAI/UniPic/blob/main/UniPic-1/src/models/skywork_unipic_dev.py#L334

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

Compare UniPic-1/scripts/image2text.py at line 64 with UniPic-1/src/models/skywork_unipic_dev.py at line 334, then trace the model and loss configuration to determine the intended SigLIP2 integration. The issue does not define the desired behavior, so completion requires clarifying whether the implementation or the paper description should be changed before updating the relevant path.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.