search

caoyunkang / Segment-Any-Anomaly

Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".
714 stars 75 forks source link

The Colab demo for the master branch (SAA) is not working due to the changes made to the default branch. #38

Open eycjur opened 1 week ago

eycjur commented 1 week ago

I propose changing the first cell of the Colab notebook at the following link as follows: https://colab.research.google.com/drive/1Rwio_KfziuLp79Qh_ugum64Hjnq4ZwsE?usp=sharing

- !git clone https://github.com/caoyunkang/GroundedSAM-zero-shot-anomaly-detection.git
+ !git clone -b master https://github.com/caoyunkang/GroundedSAM-zero-shot-anomaly-detection.git
caoyunkang commented 1 week ago

Thank you so much! But I would like to notify you that there are two branches in this repo, and the SAA-plus is the main and newest one. You can find the Colab demo there there.

eycjur commented 1 week ago

@caoyunkang Thank you for your reply. I am aware that the branches are different between master and SAA-plus. However, I understand that SAA-plus is not a complete superset, as it also requires input for Object Number and Mask Number. Therefore, I would appreciate it if the demo on the master branch could be run in cases where the Object Number or Mask Number is unknown.