ZwwWayne / K-Net

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation
Apache License 2.0
467 stars 45 forks source link

Any demo script? #5

Open lucasjinreal opened 3 years ago

lucasjinreal commented 3 years ago

How to visualize final result? Feed single image and visualize?

ZwwWayne commented 3 years ago

You should be able to use the demo API in mmdetection. However, the visualization API in MMDet is still in progress, we will try to support that ASAP.

lucasjinreal commented 3 years ago

@ZwwWayne thank u. it would be better add vis support since we want see it's visualization result to verify the mask quality.

ZwwWayne commented 3 years ago

Sure, we will support that. This may be done at the end of this month.

Kenneth-X commented 2 years ago

any update for demo scrip? i tried to using mmdet demo.py but only get a mask like this: {'pan_results': array([[2047, 2047, 2047, ..., 2047, 2047, 2047], [2047, 2047, 2047, ..., 2047, 2047, 2047], [2047, 2047, 2047, ..., 2047, 2047, 2047], ..., [ 45, 45, 45, ..., 83, 83, 83], [ 45, 45, 45, ..., 83, 83, 83], [ 45, 45, 45, ..., 83, 83, 83]])} i do not know how to use it for instance box and sematic mask, could you help me ?thanks a lot

ZwwWayne commented 2 years ago

MMDet v2.22.0 supports demo scripts. This repo will be updated to be compatible with the newest mmdet soon. It already support panoptic visualization https://github.com/open-mmlab/mmdetection/pull/7247/files.