image width and length in train&eval&mesh
Open
- 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