pygmtools.pytorch_backend¶

Functions

`build_batch`	Pytorch implementation of building a batched tensor
`cao_fast_solver`	Pytorch implementation of CAO solver in fast config (mode="pc")
`cao_solver`	Pytorch implementation of CAO solver (mode="c")
`compute_affinity_score`	Pytorch implementation of computing affinity score
`dense_to_sparse`	Pytorch implementation of converting a dense adjacency matrix to a sparse matrix
`from_numpy`	Pytorch function from_numpy
`gamgm`	Pytorch implementation of Graduated Assignment for Multi-Graph Matching (with compatibility for 2GM and clustering)
`gamgm_real`	The real forward function of GAMGM
`gaussian_aff_fn`	Pytorch implementation of Gaussian affinity function
`generate_isomorphic_graphs`	Pytorch implementation of generate_isomorphic_graphs
`hungarian`	Pytorch implementation of Hungarian algorithm
`inner_prod_aff_fn`	Pytorch implementation of inner product affinity function
`ipfp`	Pytorch implementation of IPFP algorithm
`mgm_floyd_fast_solver`
`mgm_floyd_solver`
`permutation_loss`	Pytorch implementation of permutation_loss
`rrwm`	Pytorch implementation of RRWM algorithm.
`sinkhorn`	Pytorch implementation of Sinkhorn algorithm
`sm`	Pytorch implementation of SM algorithm.
`to_numpy`	Pytorch function to_numpy

Classes

Torch wrapper to support forward and backward pass (by black-box differentiation)