about finetuning
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.7k
- Forks
- 1.3k
- PR merge metrics
- No merged PRs in 30d
Description
Hi. I have two questions about finetuning the model, hope someone can give some insights.
I would like to fine‑tune the SS model on a hand‑only dataset where I have attached a MANO head, but the dataset does not contain the ground‑truth noise (or velocity) required by the original SS model, since we do not have the 3D scanned hand model. Is it possible to train the model without the diffusion (noise) loss, only with the mano loss, joint loss, etc?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file, test, or training entry point is identified in the issue. Start by locating the fine-tuning configuration and loss definitions, then determine whether diffusion loss can be omitted while retaining MANO and joint losses. Done means a documented, supported training approach or a clear statement that this configuration is not supported.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100