meetps / meetps/pytorch-semseg

PolynomialLR always return base_lr

Open
#151 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.4k
Forks
786
PR merge metrics
No merged PRs in 30d

Description

In the implementation of get_lr() function of Polynomial LR, self.last_epoch % self.max_iter will always be true unless last_epoch > max_iter
https://github.com/meetshah1995/pytorch-semseg/blob/89f4abe180528a69e32ac1217746f68dfafd0e36/ptsemseg/schedulers/schedulers.py#L26-L31

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 reading get_lr() in ptsemseg/schedulers/schedulers.py at the referenced lines and reproduce the PolynomialLR behavior across last_epoch values. The work is done when the scheduler no longer always returns base_lr and its learning-rate progression behaves correctly through max_iter.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.