Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Optional: frozen backbone vs full fine-tuning

Open
#39 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
Half a day
Newbie friendliness
45/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
python

Research direction

Start in scripts/finetune.py, where the training setup and the existing full fine-tuning path live, and check how issue #37 changes it before you begin. Add a --freeze-backbone flag that trains only the classifier head, then run MobileNetV2 in both modes. Done means accuracy and epoch-time results for both modes are saved in results/.

Written by the indexing model from the issue text.

Description

optional pretrained

Extra experiment for the discussion.

Files: scripts/finetune.py

Tasks
  • Add --freeze-backbone flag (train only the classifier)
  • Run for MobileNetV2 and compare accuracy and epoch time with full fine-tuning
Done when

Results of both modes saved in results/.

Depends on

#37

Close with a commit or PR message containing Closes #<this issue>.

Dominant language
Jupyter Notebook
Stars
0
Forks
0
Avg merge
1m
Merged PRs (30d)
3

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

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.

More from VisionForgeCSE/CNN-For-Image-Classification

All issues in VisionForgeCSE/CNN-For-Image-Classification

Similar issues

More Machine Learning issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.