How to get the Affinity Matrix separately instead of get the product AS

meng-tang / rloss

Regularized Losses (rloss) for Weakly-supervised CNN Segmentation

MIT License

207 stars 46 forks source link

How to get the Affinity Matrix separately instead of get the product AS #17

Open Sam1224 opened 3 years ago

Sam1224 commented 3 years ago

Hi, I'm also working on Normalized Cut loss, which requires the parameter d=W1, and I have no idea of how to get the affinity matrix from the cpp code.