kwea123 / kwea123/nerf_pl

image width and length in train&eval&mesh

Open
#211 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

Can the param img_wh in train be different from img_wh in in eval&mesh ?
There is "killed" problem when i set the img_wh to (4032, 3024), and it seems to be OOM.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by tracing where img_wh is consumed during train, eval, and mesh workflows, then investigate the reported killed process at (4032, 3024). Determine whether training and evaluation can use different dimensions and whether the high-resolution setting causes an out-of-memory failure.

Written by the indexing model from the issue text.

Assessment

Tech stack
pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.