[英]Tensor matrix multiplication returning vector einsum
I am confused about the following example of a matrix tensor multiplication that returns a vector.我对以下返回向量的矩阵张量乘法示例感到困惑。 At first glance I thought that it would mean multiplying the first dimension of the tensor dydx by the matrix dLdy but I don't get the expected results as depicted below.
乍一看,我认为这意味着将张量 dydx 的第一维乘以矩阵 dLdy,但我没有得到如下所示的预期结果。 So what is the meaning of this einsum?
那么这个einsum是什么意思呢?
import torch
import numpy as np
dLdy = torch.randn(2,2)
dydx = torch.randn(2,2,2)
torch.einsum('jk,jki->i', dLdy, dydx)
tensor([0.3115, 3.7255])
dLdy
tensor([[-0.4845, 0.6838],
[-1.1723, 1.4914]])
dydx
tensor([[[ 1.5496, -1.2722],
[ 0.1221, 1.0495]],
[[-1.4882, 0.0307],
[-0.5134, 1.6276]]])
(dLdy * dydx[0]).sum()
-0.1985
For A and B this is contraction (sum) over the first two dimensions jk, so res(i) = sum_{j,k} A(j,k)B(j,k,i)对于 A 和 B,这是前两个维度 jk 上的收缩(总和),所以 res(i) = sum_{j,k} A(j,k)B(j,k,i)
for example:例如:
import torch
import numpy as np
dLdy = torch.randn(2,2)
dydx = torch.randn(2,2,2)
print(torch.einsum('jk,jki->i', dLdy, dydx))
print((dLdy * dydx[:,:,0]).sum())
print((dLdy * dydx[:,:,1]).sum())
produces生产
tensor([4.6025, 1.8987])
tensor(4.6025)
tensor(1.8987)
ie (dLdy * dydx[:,:,0]).sum()
is the first element of the resulting vector, etc即
(dLdy * dydx[:,:,0]).sum()
是结果向量的第一个元素,等等
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.