Segment-Everything-Everywhere-All-At-Once
Segment-Everything-Everywhere-All-At-Once copied to clipboard
Question about match id.
Thank you for your impressive work!
I am wondering how to compute these two IDs in codes?And how to decide which one to output if I use both text and visual prompts?
I am looking forward to your explanation.
Use interactive segmentation as an example, here is the matching code: https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/blob/7b2e76dbb17d0b7831c6813a921fe2bc8de22926/modeling/modules/matcher.py#L314, noted that as there are positive and negative examples so that masking is employed.