Skip to content

Evaluation on Windows fails due to missing ninja (use standard COCOeval) #1837

Open
@cmaranes

Description

@cmaranes

On Windows, the evaluation step tries to import the optimized Cython version (COCOeval_opt), which in turn requires a working ninja install for JIT compilation. If ninja isn’t available, the import fails and the entire eval pipeline breaks.

🔧 Temporary Workaround

Force use of the pure-Python evaluator by swapping out the import. In
yolox/evaluators/coco_evaluator.py (around line 294):

from yolox.layers import COCOeval_opt as COCOeval

, replace:

- from yolox.evaluators.coco_opt import COCOeval_opt
+ from pycocotools.cocoeval import COCOeval

This change bypasses the ninja dependency and lets evaluation complete using the standard COCO API.

Feel free to let me know if you’d like a PR implementing the fallback logic!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions