Segment-Everything-Everywhere-All-At-Once
Segment-Everything-Everywhere-All-At-Once copied to clipboard
Is there a test script? What do I do if I want to mass predict a photo set?
Is there a test script? What do I do if I want to mass predict a photo set?
I currently do not have a test script for SEEM, but you could try to modify from X-Decoder: https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/tree/v1.0/inference/xdecoder