Is it necessary to recalculate the adjacency matrix in each Grapher?

huawei-noah / Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

4.07k stars 708 forks source link

Is it necessary to recalculate the adjacency matrix in each Grapher? #98

Closed Land5cape closed 2 years ago

Land5cape commented 2 years ago

Why is the adjacency matrix recomputed in each Grapher by using the KNN algorithm and parameter 'relative_pos'? Does this mean that the graph structure of ViG is changing?