The claimed effect cannot be detected when using the 360V2 dataset
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 742
- Forks
- 59
- PR merge metrics
- No merged PRs in 30d
Description
python3.10 train.py train.gs_epochs=3000 train.no_densify=True gs.dataset.source_path=/workspace/EDGS/data/bicycle gs.dataset.model_path=/workspace/output/6 init_wC.matches_per_ref=20000 init_wC.nns_per_ref=3 init_wC.num_refs=180 wandb.mode=disabled
Contributor guide
No contributing guide indexed for this repository
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.
Research direction
Start by reproducing the reported command in train.py with the 360V2 bicycle dataset settings shown in the issue, then compare the training speed and claimed effect with the attached results. Done means identifying why the effect is not detectable and addressing the reported slow training without changing the intended experiment.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100