Dillon Laird
Dillon Laird
I could not get the gradio app to work with the existing code. It would refresh the "Referring Input Cache" and the "Parsed Referring Input" twice so it would disappear....
Could you explain the pretrained models form this [page](https://github.com/qqlu/Entity/tree/main/Entityv2)? Were all of these models pretrained using the COCO dataset and the numbers are evaluation numbers on the EntitySeg-{semantic, instance, panoptic,...
The last out indice should be 7 instead of 6, at least for the SA12 architecture. On SA12 if we return index 6 as the final layer it skips the...