Help regarding mask/ no-mask
Open
- Dominant language
- Jupyter Notebook
- Stars
- 2.8k
- Forks
- 458
- PR merge metrics
- No merged PRs in 30d
Description
I am using this to compare it with my project's outputs which is using a mask to segment the foreground. Is it better to run colmap and train the network with or without masks?
@kwea123 thoughts?
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or entry points. Start by reviewing the repository's COLMAP and network-training workflow to determine where masks are supported or expected. Done means documenting whether to use masks for COLMAP, training, both, or neither, with enough guidance to reproduce the comparison.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100