Cadene / Cadene/vqa.pytorch

No learning rate decay?

Open
#37 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
733
Forks
176
PR merge metrics
No merged PRs in 30d

Description

Hi,

I saw you commented out the adjust_learning_rate function. Does this mean lr decay isn't essential to the performance of VQA training?

Cheers,
Jake

Contributor guide

No contributing guide indexed for this repository

Research direction

Locate the commented-out adjust_learning_rate function and the VQA training entry point, then inspect how learning rate is currently configured. Determine whether decay is intended to be supported and define the expected training behavior before deciding whether an implementation or documentation change is appropriate.

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
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.