Adjacency matrix in multi-step time prediction

[lixhere]

I want to know why the Adjacency matrix in multi-step time prediction has been created, and how to create it? Is it the same method as single step time prediction?

[weneleven]

I have the same question,have you figured it out?

[2775791369]

i find the way ,it is generated by gen_adj_mx.py which is not be uploaded. try to go to the project "DCRNN" on github and find the dile reference link"https://www.cnblogs.com/transpaper/p/13954029.html"