我的数据对象有 data.adj_t 参数，给我稀疏邻接矩阵。如何从中获取大小为 [2, num_edges] 的 edge_index 张量？
最佳答案
正如您在 docs 中看到的那样:
Since this feature is still experimental, some operations, e.g., graph pooling methods, may still require you to input the
edge_indexformat. You can convertadj_tback to(edge_index, edge_attr)via:row, col, edge_attr = adj_t.t().coo() edge_index = torch.stack([row, col], dim=0)
关于python - Pytorch 几何稀疏邻接矩阵到边索引张量，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/69091074/