torch.linalg.cross

torch.linalg.cross(input, other, *, dim=-1, out=None) Tensor

计算两个三维向量的叉乘。

支持浮点数、双精度浮点数、复数浮点数和复数双精度浮点数的数据类型作为输入。也支持向量的批量处理,并沿dim维度计算乘积。它会在批次维度上进行广播操作。

参数
  • input (Tensor) – 输入的第一个张量。

  • other (Tensor) – 输入的第二个张量。

  • dim (int, 可选) – 计算向量积的维度。默认值:-1

关键字参数

out (Tensor, optional) – 输出张量。默认为None,若未指定则忽略。

示例

>>> a = torch.randn(4, 3)
>>> a
tensor([[-0.3956,  1.1455,  1.6895],
        [-0.5849,  1.3672,  0.3599],
        [-1.1626,  0.7180, -0.0521],
        [-0.1339,  0.9902, -2.0225]])
>>> b = torch.randn(4, 3)
>>> b
tensor([[-0.0257, -1.4725, -1.2251],
        [-1.1479, -0.7005, -1.9757],
        [-1.3904,  0.3726, -1.1836],
        [-0.9688, -0.7153,  0.2159]])
>>> torch.linalg.cross(a, b)
tensor([[ 1.0844, -0.5281,  0.6120],
        [-2.4490, -1.5687,  1.9792],
        [-0.8304, -1.3037,  0.5650],
        [-1.2329,  1.9883,  1.0551]])
>>> a = torch.randn(1, 3)  # a is broadcast to match shape of b
>>> a
tensor([[-0.9941, -0.5132,  0.5681]])
>>> torch.linalg.cross(a, b)
tensor([[ 1.4653, -1.2325,  1.4507],
        [ 1.4119, -2.6163,  0.1073],
        [ 0.3957, -1.9666, -1.0840],
        [ 0.2956, -0.3357,  0.2139]])
本页目录