eval_baseline.py: read_meta undefined in test dataloader
Nobody has claimed this yet.
- Dominant language
- JavaScript
- Stars
- 3k
- Forks
- 234
- PR merge metrics
- No merged PRs in 30d
Description
Running moge/scripts/eval_baseline.py with configs/eval/benchmarks/diode.json and baselines/da_v2.py fails:
File "moge/test/dataloader.py", line 96, in _load_instance
meta = read_meta(Path(path, 'meta.json'))
NameError: name 'read_meta' is not defined
moge/train/dataloader.py uses read_json for the same path; moge/utils/io.py defines read_json but not read_meta.
Suggested fix: read_meta → read_json in moge/test/dataloader.py.
Note: a PyPI package named pipeline in the same venv can shadow MoGe's import pipeline in the test dataloader.
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 in moge/test/dataloader.py at _load_instance and compare its metadata loading with moge/train/dataloader.py and moge/utils/io.py. Run moge/scripts/eval_baseline.py with configs/eval/benchmarks/diode.json and baselines/da_v2.py; done means the NameError is gone and the evaluation proceeds without the environment's pipeline package shadowing MoGe's import.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Quiet
- Clarity
- Clearly specified
- Newbie friendliness
- 86/100