Python 将两个高维张量（2,5,3）*（2,5）乘以（2,5,3）

我想把两个高维张量（2，5，3）*（2，5）乘以（2，5，3），每行向量乘以一个标量

例如

除了多for循环方式外，如何通过

PyTorch

api以简洁的方式实现它？

---

感谢您的改进。

您可以通过正确对齐两个张量的尺寸：

import torch
from torch.nn import Embedding

emb = Embedding(6, 3)
inp = torch.tensor([[1, 2, 3, 4, 5,],
                      [2, 3, 1, 4, 5,]])
input_emb = emb(inp)

inp[...,None] * input_emb

tensor([[[-0.3069, -0.7727, -0.3772],
         [-2.8308,  1.3438, -1.1167],
         [ 0.6366,  0.6509, -3.2282],
         [-4.3004,  3.2342, -0.6556],
         [-3.0045, -0.0191, -7.4436]],

        [[-2.8308,  1.3438, -1.1167],
         [ 0.6366,  0.6509, -3.2282],
         [-0.3069, -0.7727, -0.3772],
         [-4.3004,  3.2342, -0.6556],
         [-3.0045, -0.0191, -7.4436]]], grad_fn=<MulBackward0>)

导入火炬
从torch.nn导入嵌入
emb=嵌入（6,3）
inp=火炬张量（[[1,2,3,4,5,5]，
[2, 3, 1, 4, 5,]])
输入\u emb=emb（inp）
inp[…，无]*输入
张量（[-0.3069，-0.7727，-0.3772]，
[-2.8308,  1.3438, -1.1167],
[ 0.6366,  0.6509, -3.2282],
[-4.3004,  3.2342, -0.6556],
[-3.0045, -0.0191, -7.4436]],
[[-2.8308,  1.3438, -1.1167],
[ 0.6366,  0.6509, -3.2282],
[-0.3069, -0.7727, -0.3772],
[-4.3004,  3.2342, -0.6556],
[-3.0045，-0.0191，-7.4436]]，梯度fn=）

谢谢您的回答。如果你不介意的话，你能给我一些更多的操作例子或参考来对齐张量的尺寸吗？你在这篇文章或这里的文档中有一个例子。否则，这篇文章（更长）应该对@BowenPeng有用

// It is written in this way for convenience, not mathematical true. 

// multiply each row vector by a scalar
[[
         [-1.9114, -0.1580,  1.2186] * 1
         [ 0.4627,  0.9119, -1.1691] * 2
         [ 0.6452, -0.6944,  1.9659] * 3
         [-0.5048,  0.6411, -1.3568] * 4
         [-0.2328, -0.9498,  0.7216] * 5
] 
[
         [ 0.4627,  0.9119, -1.1691] * 2
         [ 0.6452, -0.6944,  1.9659] * 3
         [-1.9114, -0.1580,  1.2186] * 1
         [-0.5048,  0.6411, -1.3568] * 4
         [-0.2328, -0.9498,  0.7216] * 5
]]

import torch
from torch.nn import Embedding

emb = Embedding(6, 3)
inp = torch.tensor([[1, 2, 3, 4, 5,],
                      [2, 3, 1, 4, 5,]])
input_emb = emb(inp)

inp[...,None] * input_emb

tensor([[[-0.3069, -0.7727, -0.3772],
         [-2.8308,  1.3438, -1.1167],
         [ 0.6366,  0.6509, -3.2282],
         [-4.3004,  3.2342, -0.6556],
         [-3.0045, -0.0191, -7.4436]],

        [[-2.8308,  1.3438, -1.1167],
         [ 0.6366,  0.6509, -3.2282],
         [-0.3069, -0.7727, -0.3772],
         [-4.3004,  3.2342, -0.6556],
         [-3.0045, -0.0191, -7.4436]]], grad_fn=<MulBackward0>)