# 一、函数解释

torch/_C/_VariableFunctions.py的有该定义，意义就是实现一下公式：

$out = \beta \times mat + \alpha \times \left ( mat1 @ mat2 \right )$

    def addmm(self, beta=1, mat, alpha=1, mat1, mat2, out=None): # real signature unknown; restored from __doc__
"""
addmm(beta=1, mat, alpha=1, mat1, mat2, out=None) -> Tensor

Performs a matrix multiplication of the matrices :attr:mat1 and :attr:mat2.
The matrix :attr:mat is added to the final result.

If :attr:mat1 is a :math:(n \times m) tensor, :attr:mat2 is a
:math:(m \times p) tensor, then :attr:mat must be
:ref:broadcastable <broadcasting-semantics> with a :math:(n \times p) tensor
and :attr:out will be a :math:(n \times p) tensor.

:attr:alpha and :attr:beta are scaling factors on matrix-vector product between
:attr:mat1 and :attrmat2 and the added matrix :attr:mat respectively.

.. math::
out = \beta\ mat + \alpha\ (mat1_i \mathbin{@} mat2_i)

For inputs of type FloatTensor or DoubleTensor, arguments :attr:beta and
:attr:alpha must be real numbers, otherwise they should be integers.

Args:
beta (Number, optional): multiplier for :attr:mat (:math:\beta)
mat (Tensor): matrix to be added
alpha (Number, optional): multiplier for :math:mat1 @ mat2 (:math:\alpha)
mat1 (Tensor): the first matrix to be multiplied
mat2 (Tensor): the second matrix to be multiplied
out (Tensor, optional): the output tensor

Example::

>>> M = torch.randn(2, 3)
>>> mat1 = torch.randn(2, 3)
>>> mat2 = torch.randn(3, 3)
tensor([[-4.8716,  1.4671, -1.3746],
[ 0.7573, -3.9555, -2.8681]])
"""
pass

# 二、代码范例

1.先摆出代码，大家可以先复制粘贴运行一下，在之后博主会一一讲解

"""
@author:nickhuang1996
"""
import torch

rectangle_height = 3
rectangle_width = 3
inputs = torch.randn(rectangle_height, rectangle_width)
for i in range(rectangle_height):
for j in range(rectangle_width):
inputs[i] = i * torch.ones(rectangle_width)
'''
inputs and its transpose
-->inputs   =   tensor([[0., 0., 0.],
[1., 1., 1.],
[2., 2., 2.]])
-->inputs_t =   tensor([[0., 1., 2.],
[0., 1., 2.],
[0., 1., 2.]])
'''
print("inputs:\n", inputs)
inputs_t = inputs.t()
print("inputs_t:\n", inputs_t)
'''
inputs_t @ inputs_t    [[0., 1., 2.],       [[0., 1., 2.],          [[0., 3., 6.]
=   [0., 1., 2.],   @    [0., 1., 2.],     =     [0., 3., 6.]
[0., 1., 2.]]        [0., 1., 2.]]           [0., 3., 6.]]
'''

'''a, b, c and d = 1 * inputs + 1 * (inputs_t @ inputs_t)'''
c = torch.addmm(input=inputs, beta=1, mat1=inputs_t, mat2=inputs_t, alpha=1)
d = inputs.addmm(beta=1, mat1=inputs_t, mat2=inputs_t, alpha=1)
'''e and f = 1 * inputs + 1 * (inputs_t @ inputs_t)'''
'''1 * inputs + 1 * (inputs_t @ inputs_t)'''
'''2 * inputs + 1 * (inputs_t @ inputs_t)'''
'''h = 1 * inputs + 1 * (inputs_t @ inputs_t)'''
h = inputs.addmm(1, 1, inputs_t, inputs_t)
'''h12 = 1 * inputs + 2 * (inputs_t @ inputs_t)'''
h12 = inputs.addmm(1, 2, inputs_t, inputs_t)
'''h21 = 2 * inputs + 1 * (inputs_t @ inputs_t)'''
h21 = inputs.addmm(2, 1, inputs_t, inputs_t)
print("a:\n", a)
print("b:\n", b)
print("c:\n", c)
print("d:\n", d)

print("e:\n", e)
print("f:\n", f)

print("g:\n", g)
print("g2:\n", g2)

print("h:\n", h)
print("h12:\n", h12)
print("h21:\n", h21)
print("inputs:\n", inputs)
'''inputs = 1 * inputs - 2 * (inputs @ inputs_t)'''
'''
inputs @ inputs_t       [[0., 0., 0.],       [[0., 1., 2.],          [[0., 0., 0.]
=    [1., 1., 1.],   @    [0., 1., 2.],     =     [0., 3., 6.]
[2., 2., 2.]]        [0., 1., 2.]]           [0., 6., 12.]]
'''
inputs.addmm_(1, -2, inputs, inputs_t)  # In-place
print("inputs:\n", inputs)


2.其中

inputs是一个3×3的矩阵，为

tensor([[0., 0., 0.],
[1., 1., 1.],
[2., 2., 2.]])

inputs_t也是一个3×3的矩阵，是inputs转置矩阵，为

tensor([[0., 1., 2.],
[0., 1., 2.],
[0., 1., 2.]])

inputs_t @ inputs_t

'''
inputs_t @ inputs_t    [[0., 1., 2.],       [[0., 1., 2.],          [[0., 3., 6.]
=   [0., 1., 2.],   @    [0., 1., 2.],     =     [0., 3., 6.]
[0., 1., 2.]]        [0., 1., 2.]]           [0., 3., 6.]]
'''

3.代码中abcd展示的是完全形式，即标明了位置参数传入参数。可以看到input这个位置参数可以写在函数的前面，即

torch.addmm(input, mat1, mat2) = inputs.addmm(mat1, mat2)

1 × inputs + 1 ×（inputs_t @ inputs_t）

'''a, b, c and d = 1 * inputs + 1 * (inputs_t @ inputs_t)'''
c = torch.addmm(input=inputs, beta=1, mat1=inputs_t, mat2=inputs_t, alpha=1)
d = inputs.addmm(beta=1, mat1=inputs_t, mat2=inputs_t, alpha=1)
a:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
b:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
c:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
d:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])

4.下面的例子更好了说明了input参数的位置可变性，并且betaalpha缺省了：

1 × inputs + 1 ×（inputs_t @ inputs_t）

'''e and f = 1 * inputs + 1 * (inputs_t @ inputs_t)'''
f = inputs.addmm(inputs_t, inputs_t)
e:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
f:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])

5.加一个参数，实际上是添加了beta这个参数

g   = 1 × inputs + 1 ×（inputs_t @ inputs_t）

g2 = 2 × inputs + 1 ×（inputs_t @ inputs_t）

'''1 * inputs + 1 * (inputs_t @ inputs_t)'''
'''2 * inputs + 1 * (inputs_t @ inputs_t)'''
g2 = inputs.addmm(2, inputs_t, inputs_t)
g:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
g2:
tensor([[ 0.,  3.,  6.],
[ 2.,  5.,  8.],
[ 4.,  7., 10.]])

6.再加一个参数，实际上是添加了alpha这个参数

h   = 1 × inputs + 1 ×（inputs_t @ inputs_t）

h12 = 1 × inputs + 2 ×（inputs_t @ inputs_t）

h21 = 2 × inputs + 1 ×（inputs_t @ inputs_t）

'''h = 1 * inputs + 1 * (inputs_t @ inputs_t)'''
h = inputs.addmm(1, 1, inputs_t, inputs_t)
'''h12 = 1 * inputs + 2 * (inputs_t @ inputs_t)'''
h12 = inputs.addmm(1, 2, inputs_t, inputs_t)
'''h21 = 2 * inputs + 1 * (inputs_t @ inputs_t)'''
h21 = inputs.addmm(2, 1, inputs_t, inputs_t)
h:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
h12:
tensor([[ 0.,  6., 12.],
[ 1.,  7., 13.],
[ 2.,  8., 14.]])
h21:
tensor([[ 0.,  3.,  6.],
[ 2.,  5.,  8.],
[ 4.,  7., 10.]])


7.当然，以上的步骤inputs没有变化，还是为

inputs:
tensor([[0., 0., 0.],
[1., 1., 1.],
[2., 2., 2.]])

*inputs@ inputs_t

'''
inputs @ inputs_t       [[0., 0., 0.],       [[0., 1., 2.],          [[0., 0., 0.]
=    [1., 1., 1.],   @    [0., 1., 2.],     =     [0., 3., 6.]
[2., 2., 2.]]        [0., 1., 2.]]           [0., 6., 12.]]
'''

inputs   = 1 × inputs - 2 ×（inputs @ inputs_t）

'''inputs = 1 * inputs - 2 * (inputs @ inputs_t)'''
inputs.addmm_(1, -2, inputs, inputs_t)  # In-place
inputs:
tensor([[  0.,   0.,   0.],
[  1.,  -5., -11.],
[  2., -10., -22.]])

# 三、代码运行结果

inputs:
tensor([[0., 0., 0.],
[1., 1., 1.],
[2., 2., 2.]])
inputs_t:
tensor([[0., 1., 2.],
[0., 1., 2.],
[0., 1., 2.]])
a:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
b:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
c:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
d:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
e:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
f:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
g:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
g2:
tensor([[ 0.,  3.,  6.],
[ 2.,  5.,  8.],
[ 4.,  7., 10.]])
h:
tensor([[0., 3., 6.],
[1., 4., 7.],
[2., 5., 8.]])
h12:
tensor([[ 0.,  6., 12.],
[ 1.,  7., 13.],
[ 2.,  8., 14.]])
h21:
tensor([[ 0.,  3.,  6.],
[ 2.,  5.,  8.],
[ 4.,  7., 10.]])
inputs:
tensor([[0., 0., 0.],
[1., 1., 1.],
[2., 2., 2.]])
inputs:
tensor([[  0.,   0.,   0.],
[  1.,  -5., -11.],
[  2., -10., -22.]])

©️2019 CSDN 皮肤主题: 技术黑板 设计师: CSDN官方博客