training with resolution 1024
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 25/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- computer-vision, machine-learning
Research direction
Start by reviewing the training configuration and the Cityscapes setup used for 1024-resolution training, then compare it with the configuration behind the paper's results. Done means identifying whether the resolution explains the discrepancy and documenting the configuration changes needed for a reasonable result.
Written by the indexing model from the issue text.
Description
I don't have access to enough computation resource so I'm training on 8gpus with resolution 1024 on cityscapes, and I find it really hard to recover the result that's even nearly compatible to the ones in the paper. Would really appreciate if you can let me know if this is caused by the resolution? And what should I modify in configuration for resolution 1024 to work reasonably well?
- Dominant language
- Python
- Stars
- 301
- Forks
- 52
- PR merge metrics
- No merged PRs in 30d
Getting set up
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from mapillary/seamseg
-
ImportError during testing pre-trained model with test_panoptic.py, possibly a circular import?Open
Difficulty 4/5 3-5 days Newbie friendliness 38/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 35/100
-
Difficulty 4/5 3-5 days Newbie friendliness 38/100
-
Creating a ColabOpen
Difficulty 4/5 3-5 days Newbie friendliness 25/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 45/100
All issues in mapillary/seamseg
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
google-agentic-commerce/AP2#388 ·
-
area:codegen backend:cuda backend:hip bug direction:input
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
CrossGL/crosstl#3061 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
rlaope/oh-my-hermes#2304 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
mochan-tk/agentic-dev-kit-for-codex#64 ·
Maintainers usually reply within 1 day
-
bug docs performance
Difficulty 1/5 Under an hour Newbie friendliness 85/100
Maintainers usually reply within 3 days