UMass-Rescue / UMass-Rescue/RescueBox

Plugin: fine tuning of existing vision models

Open
#89 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

complex hackathon
Dominant language
Python
Stars
6
Forks
15
Avg merge
14h 42m
Merged PRs (30d)
7

Description

current plugins namely : facematch , deepfake , age-detector all three of them could be benfit from fine tuning . for example, focus on age 5 to 19 images

all of these use onnx models , can a common code approach work for fine tuning ?

Fine-tuning with LoRA adapters in ONNX Runtime
if GPU is required can we use AVD /Unity host for this ?

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

The issue names the facematch, deepfake, and age-detector plugins and their ONNX models, but no files or tests. Start by locating those plugin entry points and reviewing the linked issue #82. Done would require a decided common fine-tuning approach, including whether LoRA and GPU hosting through AVD or Unity are supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.