[Pytorch]矩阵的乘法运算

1. element-wise multiplication/按元素位置相乘
   a.mul(b)
   a * b

import torch
a = torch.tensor((1,2,3,4))
b = torch.tensor((5,6,7,8))
a * b # same as: a.mul(b)

# output: tensor([ 5, 12, 21, 32])

2. dot product/matrix multiplication/矩阵点乘
   torch.mm(a,b)
   torch.bmm(a,b) # b means batch
   torch.matmul() # 支持broadcast，一般用后两维计算，前面认为是batch
   a @ b

import torch
a = torch.tensor(((1,2,3,4),(4,3,2,1)))
b = torch.tensor(((5,6,7,8),(8,7,6,5)))
a @ b.T

# output: tensor([[70, 60],
#         		[60, 70]])