Question

我想将两个高维张量（2，5，3）*（2，5）乘以（2，5，3），将每个行向量乘以标量。

例如

emb = nn.Embedding(6, 3)

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


print(input.shape)
> torch.Size([2, 5])

print(input_emb.shape)
> torch.Size([2, 5, 3])

print(input_emb)
> tensor([[[-1.9114, -0.1580,  1.2186],
         [ 0.4627,  0.9119, -1.1691],
         [ 0.6452, -0.6944,  1.9659],
         [-0.5048,  0.6411, -1.3568],
         [-0.2328, -0.9498,  0.7216]],

        [[ 0.4627,  0.9119, -1.1691],
         [ 0.6452, -0.6944,  1.9659],
         [-1.9114, -0.1580,  1.2186],
         [-0.5048,  0.6411, -1.3568],
         [-0.2328, -0.9498,  0.7216]]], grad_fn=<EmbeddingBackward>)

我想乘以如下：

// 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
]]

除了“多循环”方式之外，如何通过PyTorch API以简洁的方式实现它？
预先感谢。

Answer 1

您可以通过正确对齐两个张量的尺寸来实现：

std::addressof

Pytorch：将两个高维张量（2，5，3）*（2，5）乘以（2，5，3）

1 个答案: