MIC-DKFZ / MIC-DKFZ/nnInteractive

transfer learning

Open
#11 2 comments 10 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
493
Forks
59
PR merge metrics
No merged PRs in 30d

Description

Dear nnInteractive team,

Thank you very much for developing and sharing nnInteractive.
I've tested it within 3D Slicer and was truly impressed by its powerful segmentation performance.

To conduct more robust and dataset-relevant research, I would like to fine-tune the model on my own data.

Could you please clarify the following:

  1. Is it permitted—under the current license—to use the provided pretrained model weights as initialization for fine-tuning?
  2. After fine-tuning, can the resulting model weights be used for non-commercial research purposes?
  3. If appropriate, would it also be allowed to share the fine-tuned weights with other researchers for academic collaboration?

Thank you for your time and for providing this valuable tool to the community.

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 named. Start by reviewing the repository license and the terms covering the provided pretrained model weights, then determine whether fine-tuning, non-commercial use, and sharing fine-tuned weights are permitted. Done means documenting clear answers to all three questions.

Written by the indexing model from the issue text.

Assessment

Domain
documentation
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.