dgl.sparse.bspmm

dgl.sparse.bspmm(A: SparseMatrix, X: Tensor) → Tensor[source]

将稀疏矩阵按批次乘以密集矩阵，等同于 A @ X。

Parameters:

A (SparseMatrix) – 形状为 (L, M) 的稀疏矩阵，其向量长度为 K
X (torch.Tensor) – 形状为 (M, N, K) 的密集矩阵

Returns:

形状为(L, N, K)的密集矩阵

Return type:

torch.Tensor

示例

>>> indices = torch.tensor([[0, 1, 1], [1, 0, 2]])
>>> val = torch.randn(len(row), 2)
>>> A = dglsp.spmatrix(indices, val, shape=(3, 3))
>>> X = torch.randn(3, 3, 2)
>>> result = dglsp.bspmm(A, X)
>>> type(result)
<class 'torch.Tensor'>
>>> result.shape
torch.Size([3, 3, 2])