pytorch文檔中關于torch.matmul()的維度說明如下：

?

• If both tensors are 1-dimensional, the dot product (scalar) is returned.
• If both arguments are 2-dimensional, the matrix-matrix product is returned.
• If the first argument is 1-dimensional and the second argument is 2-dimensional, a 1 is prepended to its dimension for the purpose of the matrix multiply. After the matrix multiply, the prepended dimension is removed.
• If the first argument is 2-dimensional and the second argument is 1-dimensional, the matrix-vector product is returned.
• If both arguments are at least 1-dimensional and at least one argument is N-dimensional (where N > 2), then a batched matrix multiply is returned. If the first argument is 1-dimensional, a 1 is prepended to its dimension for the purpose of the batched matrix multiply and removed after. If the second argument is 1-dimensional, a 1 is appended to its dimension for the purpose of the batched matrix multiple and removed after. The non-matrix (i.e. batch) dimensions are?broadcasted?(and thus must be broadcastable).

最后一項可能光看文檔難以理解，下面舉個例子：

>>a = torch.arange(0,18).view(2,3,3)

>>b = torch.ones(3,dtype=torch.long)

>>c = torch.matmul(a,b)

>>d = torch.matmul(b,a)

>>a.size()

torch.Size([2, 3, 3])

>>b.size()

torch.Size([3])

>>c.size()

torch.Size([2, 3])

>>d.size()

torch.Size([2, 3])

>>a[0]

tensor([[0, 1, 2],

[3, 4, 5],

[6, 7, 8]])

>>a[1]

tensor([[ 9, 10, 11],

[12, 13, 14],

[15, 16, 17]])

>>c

tensor([[ 3, 12, 21],

[30, 39, 48]])

>>d

tensor([[ 9, 12, 15],

[36, 39, 42]])

通過分析上面的結果我們可以發現，c = torch.matmul(a,b)等價于將a[0]和a[1]這兩個(3,3)維的矩陣與b這個3維向量相乘：a[0]×b和a[1]×b，而d = torch.matmul(b,a)只是相乘順序相反：b×a[0]和b×a[1].

來源:https://blog.csdn.net/CVAIDL/article/details/107752697

總結

以上是生活随笔為你收集整理的[pytorch] 通过一个例子分析torch.matmul矩阵与向量相乘的维度的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。