waxmorph.torch

Modules

waxmorph.torch.gnn	PyTorch Encode-Process-Decode graph network for cell-state updates.
waxmorph.torch.graph	PyTorch graph features with detached contact topology.
waxmorph.torch.losses	PyTorch losses for row-aligned or unordered point clouds.
waxmorph.torch.mlp	PyTorch MLP used by the graph network.
waxmorph.torch.warp_autograd	Torch autograd adapters for Warp mechanics and diffusion.

Default PyTorch backend.

Import waxmorph.jax explicitly for JAX. The backends differ in loss factories, graph return shapes, and Warp gradient bridges.