Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Can we run inference on a non CUDA machine?

Open
  • Is something wrong?
#36 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
38/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Stale
Tech stack
python, pytorch
Domain
machine-learning

Research direction

Start by reproducing the supplied Python command on the reported macOS setup and inspect test_panoptic.py together with the torch.distributed.launch invocation. Determine whether the assertion comes from the zero-process configuration or missing non-CUDA support; done means the documented inference command runs without the AssertionError on a non-CUDA machine.

Written by the indexing model from the issue text.

Description

I am trying to run inference using the pre-trained models on a MacOS machine and getting an AssertionError thrown:

    assert self.local_world_size > 0
           ^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError

This is the command I am trying to run:
python3 -m torch.distributed.launch --nproc_per_node=0 test_panoptic.py --meta ../models/SeamSeg-R50-Vistas/metadata.bin --log_dir ../logs/ ../models/SeamSeg-R50-Vistas/config.ini ../models/SeamSeg-R50-Vistas/seamseg_r50_vistas.tar ../input/ ../output/

Any help will be much appreciated!

Dominant language
Python
Stars
301
Forks
53
No merged PRs in 30d

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from mapillary/seamseg

All issues in mapillary/seamseg

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.