RRWHM

class src.qap_solvers.rrwhm.RRWHM(max_iter=50, sk_iter=20, alpha=0.2, beta=30)

RRWHM solver for hyper graph matching, implemented by tensor power iteration with Sinkhorn reweighted jumps. Parameter: maximum iteration max_iter Input: input tensor H

maximum size of source graph num_src sizes of source graph in batch ns_src sizes of target graph in batch ns_tgt (optional) initialization vector v0. If not specified, v0 will be initialized with all 1.

Output: computed eigenvector v

forward(H, num_src, ns_src, ns_tgt, v0=None)

training: bool