kwea123 / kwea123/nerf_pl

Can more video memory occupied to speed up training ?

Open
#176 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
2.8k
Forks
458
PR merge metrics
No merged PRs in 30d

Description

Hi, thanks for sharing this excellent work.
#25 mentioned that too large batch size will deteriorate the result and may not accelerate training? So is there any way to use free gpu memory to reduce the training time,or it is only related to img's resolution?

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue points to discussion #25 and the training setup, but names no file or test. Start by reviewing #25 and how batch size and image resolution affect GPU memory; done requires a concrete, validated way to reduce training time or a documented limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
pytorch
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.