pytorch用到的函数记录一下(不定更新~)

"""
返回上三角矩阵
diagonal \in [0, min(d_w, d_h)-1]
diagonal表示对角线轴，为0表示主对角线（i,i）。大于0往上走，小于0往下走。最后结果会存储在out里面。
当out不等于None时，torch.triu(input, diagonal=0, out=None) is out，貌似用C语言实现的，类似指针的引用
"""
 torch.triu(input, diagonal=0, out=None) → Tensor
>>> b = torch.randn(4, 6)
>>> b
tensor([[ 0.5876, -0.0794, -1.8373,  0.6654,  0.2604,  1.5235],
        [-0.2447,  0.9556, -1.2919,  1.3378, -0.1768, -1.0857],
        [ 0.4333,  0.3146,  0.6576, -1.0432,  0.9348, -0.4410],
        [-0.9888,  1.0679, -1.3337, -1.6556,  0.4798,  0.2830]])
>>> torch.triu(b, diagonal=1)
tensor([[ 0.0000, -0.0794, -1.8373,  0.6654,  0.2604,  1.5235],
        [ 0.0000,  0.0000, -1.2919,  1.3378, -0.1768, -1.0857],
        [ 0.0000,  0.0000,  0.0000, -1.0432,  0.9348, -0.4410],
        [ 0.0000,  0.0000,  0.0000,  0.0000,  0.4798,  0.2830]])
>>> torch.triu(b, diagonal=-1)
tensor([[ 0.5876, -0.0794, -1.8373,  0.6654,  0.2604,  1.5235],
        [-0.2447,  0.9556, -1.2919,  1.3378, -0.1768, -1.0857],
        [ 0.0000,  0.3146,  0.6576, -1.0432,  0.9348, -0.4410],
        [ 0.0000,  0.0000, -1.3337, -1.6556,  0.4798,  0.2830]])

"""
逐个元素的比较input是否大于other，返回ByteTensor
"""
 torch.gt(input, other, out=None) → Tensor
 >>> torch.gt(torch.tensor([[1, 2], [3, 4]]), torch.tensor([[1, 1], [4, 4]]))
tensor([[ 0,  1],
        [ 0,  0]], dtype=torch.uint8)

"""
返回全1，大小和input相同。类似torch.zeros_like()
"""
 torch.ones_like(input, dtype=None, layout=None, device=None, requires_grad=False) → Tensor
>>> input = torch.empty(2, 3)
>>> torch.ones_like(input)
tensor([[ 1.,  1.,  1.],
        [ 1.,  1.,  1.]])

torch.matmul(tensor1, tensor2, out=None) → Tensor

1. 都是1维，返回常数值
2. 2维返回矩阵乘积
3. 如果第一个是一维，第二个是二维。一维增加一维然后矩阵乘积。
4. 如果第一个是二维，第二个是一维。向量和矩阵相乘。

>>> # vector x vector
>>> tensor1 = torch.randn(3)
>>> tensor2 = torch.randn(3)
>>> torch.matmul(tensor1, tensor2).size()
torch.Size([])
>>> # matrix x vector
>>> tensor1 = torch.randn(3, 4)
>>> tensor2 = torch.randn(4)
>>> torch.matmul(tensor1, tensor2).size()
torch.Size([3])
>>> # batched matrix x broadcasted vector
>>> tensor1 = torch.randn(10, 3, 4)
>>> tensor2 = torch.randn(4)
>>> torch.matmul(tensor1, tensor2).size()
torch.Size([10, 3])
>>> # batched matrix x batched matrix
>>> tensor1 = torch.randn(10, 3, 4)
>>> tensor2 = torch.randn(10, 4, 5)
>>> torch.matmul(tensor1, tensor2).size()
torch.Size([10, 3, 5])
>>> # batched matrix x broadcasted matrix
>>> tensor1 = torch.randn(10, 3, 4)
>>> tensor2 = torch.randn(4, 5)
>>> torch.matmul(tensor1, tensor2).size()
torch.Size([10, 3, 5])