Megvii-BaseDetection / Megvii-BaseDetection/GFSD

Integrating the training of the base model

Open
#4 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
50
Forks
4
PR merge metrics
No merged PRs in 30d

Description

Hi,

I noticed that you use the pretrained base-class model form another repo. In the end, I guess it would also be possible to train it using CVPODS by adding another exp folder and the required files to the playground folder. Is there a simple way to achieve this? Would be nice to have everything at one place. And would be good example to start developing new Few-Shot Methods using your framework and dataset splits etc. What would I have to add? Or could you add this? Thx in advance.

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

Start by reviewing the existing playground structure and exp folders, then trace how the pretrained base-class model from the other repository is currently consumed through CVPODS. The scope is not defined enough to name specific files or tests; completion would require a documented training entry point and example configuration that works with the project's dataset splits.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
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.