Uniform predictions (identical saliency scores) during TVSum dataset evaluation with Lighthouse pipeline

Nobody has claimed this yet.

When evaluating the Lighthouse model on the TVSum dataset using the provided scripts, the model outputs identical highlight scores across all time windows, despite following the tutorial steps.
eval_command:
python /lighthouse/training/evaluate.py --model uvcom --dataset tvsum --feature i3d_clip --domain BK --split val --model_path checkpoints/results/uvcom/tvsum/i3d_clip/BK/best.ckpt --eval_path data/tvsum/tvsum_val_release.jsonl
I printed out the saliency score predictions during the evaluation, and a screenshot is attached below to show the output.


1.Are there known issues with TVSum evaluation in the current version?

2.Could the problem stem from data loading or post-processing steps or shape problem of loaded features? \
However, i downloaded all the checkpoints and extracted-features from the link on lighthouse repo page.
Appreciate your guidance to resolve this issue.

Start with training/evaluate.py and reproduce the issue using the provided TVSum evaluation command, checkpoint, and JSONL path. Inspect the loaded i3d_clip feature shapes, data loading, and post-processing while comparing the predicted scores across time windows. Done means identifying the cause of the identical predictions and confirming that evaluation produces non-uniform scores.

Written by the indexing model from the issue text.