如何在PyTorch中做矩阵乘积 [英] How to do product of matrices in PyTorch

问题描述

在numpy中，我可以像这样做一个简单的矩阵乘法:

In numpy I can do a simple matrix multiplication like this:

a = numpy.arange(2*3).reshape(3,2)
b = numpy.arange(2).reshape(2,1)
print(a)
print(b)
print(a.dot(b))

但是，当我使用PyTorch Tensors尝试此操作时，这不起作用:

However, when I am trying this with PyTorch Tensors, this does not work:

a = torch.Tensor([[1, 2, 3], [1, 2, 3]]).view(-1, 2)
b = torch.Tensor([[2, 1]]).view(2, -1)
print(a)
print(a.size())

print(b)
print(b.size())

print(torch.dot(a, b))

此代码引发以下错误:

RuntimeError:张量大小不一致 /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensorMath.c:503

RuntimeError: inconsistent tensor size at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensorMath.c:503

有什么想法可以在PyTorch中进行矩阵乘法吗?

Any ideas how matrix multiplication can be conducted in PyTorch?

推荐答案

您正在寻找

torch.mm(a,b)

请注意，torch.dot()的行为与np.dot()不同.在此处进行了一些讨论.具体来说，torch.dot()将a和b都视为一维向量(与它们的原始形状无关)，并计算其内积.引发错误，因为此行为使a为长度6的向量，而b为长度2的向量；因此无法计算其内积.对于PyTorch中的矩阵乘法，请使用torch.mm().相反，Numpy的np.dot()更为灵活.它计算1D数组的内积，并为2D数组执行矩阵乘法.

Note that torch.dot() behaves differently to np.dot(). There's been some discussion about what would be desirable here. Specifically, torch.dot() treats both a and b as 1D vectors (irrespective of their original shape) and computes their inner product. The error is thrown, because this behaviour makes your a a vector of length 6 and your b a vector of length 2; hence their inner product can't be computed. For matrix multiplication in PyTorch, use torch.mm(). Numpy's np.dot() in contrast is more flexible; it computes the inner product for 1D arrays and performs matrix multiplication for 2D arrays.

根据流行的需求，如果两个参数均为2D，则函数torch.matmul执行矩阵乘法，如果两个参数均为1D，则计算其点积.对于此类尺寸的输入，其行为与np.dot相同.它还允许您分批进行广播或matrix x matrix，matrix x vector和vector x vector操作.有关更多信息，请参见其文档.

By popular demand, the function torch.matmul performs matrix multiplications if both arguments are 2D and computes their dot product if both arguments are 1D. For inputs of such dimensions, its behaviour is the same as np.dot. It also lets you do broadcasting or matrix x matrix, matrix x vector and vector x vector operations in batches. For more info, see its docs.

# 1D inputs, same as torch.dot
a = torch.rand(n)
b = torch.rand(n)
torch.matmul(a, b) # torch.Size([])

# 2D inputs, same as torch.mm
a = torch.rand(m, k)
b = torch.rand(k, j)
torch.matmul(a, b) # torch.Size([m, j])

这篇关于如何在PyTorch中做矩阵乘积的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！