Track script only works for slp files

[sheridana]

The track script currently only works for slp files:

num_videos = len(dataloader.dataset.slp_files)

outpath = os.path.join(
            outdir,
            f"{Path(pred_cfg.cfg.dataset.test_dataset.slp_files[i]).stem}_tracking_results",
)

I would add a check for video type and add logic to handle non slp_files (e.g for microscopy data).

[aaprasad]

yes, the inference script will need to be refactored. There are a lot of changes that have been made since we first wrote it and there are probably better ways to handle it.

[aaprasad]

Fixed in #51