From the examples https://github.com/rusty1s/pytorch_sparse:
import torch
from torch_sparse import coalesce
index = torch.tensor([[1, 0, 1, 0, 2, 1],
[0, 1, 1, 1, 0, 0]])
value = torch.Tensor([[1, 2], [2, 3], [3, 4], [4, 5], [5, 6], [6, 7]])
index, value = coalesce(index, value, m=3, n=2)
What exactly is the purpose of m
and n
? They don’t seem to match the dimensions of the output and if I change them arbitrarily it doesn’t seem to make a difference, unless I make them small.