Multi-Task-Transformer icon indicating copy to clipboard operation
Multi-Task-Transformer copied to clipboard
verified publisher icon prismformore

Metric of edge detection

Open Wyt-ong opened this issue 1 year ago • 1 comments

I am a beginner in multi-task learning and have a silly question: Why does the code use loss as the metric to evaluate edge detection, while the paper uses ODS-F? How is ODS-F calculated? Is this part present in the code? Looking forward to your explanation.

Wyt-ong avatar Dec 11 '24 05:12 Wyt-ong

Sorry, I didn't see the repo for the edge detection evaluation. I found it now.

Wyt-ong avatar Dec 13 '24 04:12 Wyt-ong