pytourch基础学习4

1.matmul/@/mm（二维）矩阵相乘

import torch
a=torch.randn(4,2,3,8)
b=torch.randn(4,2,8,8)
print(torch.matmul(a,b).shape)

结果：torch.Size([4, 2, 3, 8])

2.pow/**

import torch
a=torch.full([2,2],9)
print(a)
b=a.pow(2)
print(b)
b=a.pow(0.5)
print(b)
b=a**2
print(b)
b=a**0.5
print(b)

结果：tensor([[9., 9.],
        [9., 9.]])
tensor([[81., 81.],
        [81., 81.]])
tensor([[3., 3.],
        [3., 3.]])
tensor([[81., 81.],
        [81., 81.]])
tensor([[3., 3.],
        [3., 3.]])

3.norm范数

import torch
a=torch.tensor([[2.,3.],[2.,3.]])
print(a)
print(a.norm(2))
print(a.norm(1))
print(a.norm(2,dim=0))
print(a.norm(1,dim=0))
print(a.norm(2,dim=1))
print(a.norm(1,dim=1))

结果：tensor([[2., 3.],
        [2., 3.]])
tensor(5.0990)
tensor(10.)
tensor([2.8284, 4.2426])
tensor([4., 6.])
tensor([3.6056, 3.6056])根号13=3.6056
tensor([5., 5.])