search

facebookresearch / ov-seg

This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.
Other
676 stars 61 forks source link

Where is visual prompt implemented #2

Closed RuoyuChen10 closed 1 year ago

RuoyuChen10 commented 1 year ago

Thanks for your great work. Can you tell me where the visual prompt is implemented? Thank you very much.

Jeff-LiangF commented 1 year ago

Hi @RuoyuChen10 ,

Thanks for your interest in OVSeg! The inference code of the mask prompt can be found here. The training code is implemented with CLIP, which we are still working on cleaning. Stay tuned!

Jeff-LiangF commented 1 year ago

Hi @RuoyuChen10 ,

Please check out the training code of mask prompt tuning. Feel free to reach out if you have any questions.