pytorch / pytorch/vision

Create reset_parameters method for ResNet blocks and models + move existing parameters init code there

Open
#3,410 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

module: models new feature
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

This would ease re-initialization some blocks that are not meant to be pretrained/frozen:
https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py#L188-L203

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

Start in torchvision/models/resnet.py at the linked initialization code around lines 188-203. Trace how initialization is currently applied across the ResNet blocks and models, then define what reset_parameters should cover and how existing initialization should move there. Done means the requested blocks and models can be re-initialized through that method without losing the current initialization behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.