kohya-ss / kohya-ss/sd-scripts

Adding Validation Loss to detect Overtraining

Open
#193 9 comments 4 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.2k
Forks
1.2k
Avg merge
11m
Merged PRs (30d)
2

Description

I saw that this repo has added the ability to use a validation loss to help figure out the optimal amount of training. Might be an interesting addition.

https://github.com/victorchall/EveryDream2trainer/blob/main/doc/VALIDATION.md

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reading the linked VALIDATION.md document in the EveryDream2trainer repository to understand the proposed validation-loss workflow. Then compare that workflow with the relevant training entry points in sd-scripts. Done means adding validation-loss support that can help identify when training is overfitting.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.