torch.matmul和torch.mm和*区别

a * b，要求两个矩阵维度完全一致，即两个矩阵对应元素相乘，输出的维度也和原矩阵维度相同：

import torch
a = torch.randn(2,3)
b = torch.randn(2,3)
print(a)
print(b)
c = a * b
print(c.size())
print(c)

结果：

tensor([[-0.6309, -1.4365, -0.8549],
        [ 1.1856,  0.8986,  1.6343]])
tensor([[-0.2452, -1.0548,  0.9490],
        [-1.7368,  1.2816, -0.2548]])
(2, 3)
tensor([[ 0.1547,  1.5153, -0.8113],
        [-2.0591,  1.1516, -0.4163]])

torch.mm(a,b)，要求两个矩阵维度是（n×m）和（m×p），即普通二维矩阵乘法

import torch
a = torch.randn(2,3)
b = torch.randn(3,2)
print(a)
print(b)

c = torch.mm(a,b)
print(c.size())
print(c)

结果：

tensor([[ 1.0326, -0.8577,  0.9282],
        [-0.161