torch.addcmul(input, value=1, tensor1, tensor2, out=None)的使用举例

参考链接: addcmul(value=1, tensor1, tensor2) → Tensor
参考链接: torch.addcmul(input, value=1, tensor1, tensor2, out=None) → Tensor

代码实验展示:

Microsoft Windows [版本 10.0.18363.1316]
(c) 2019 Microsoft Corporation。保留所有权利。

C:\Users\chenxuqi>conda activate ssd4pytorch1_2_0

(ssd4pytorch1_2_0) C:\Users\chenxuqi>python
Python 3.7.7 (default, May  6 2020, 11:45:54) [MSC v.1916 64 bit (AMD64)] :: Anaconda, Inc. on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> torch.manual_seed(seed=20200910)
<torch._C.Generator object at 0x00000202DCA2D330>
>>>
>>> t = torch.randn(1, 3)
>>> t1 = torch.randn(3, 1)
>>> t2 = torch.randn(1, 3)
>>>
>>> t
tensor([[ 0.2824, -0.3715,  0.9088]])
>>> t1
tensor([[-1.7601],
        [-0.1806],
        [ 2.0937]])
>>> t2
tensor([[ 1.0406, -1.7651,  1.1216]])
>>>
>>> torch.addcmul(t, 0.1, t1, t2)
tensor([[ 0.0992, -0.0608,  0.7114],
        [ 0.2636, -0.3396,  0.8885],
        [ 0.5003, -0.7410,  1.1436]])
>>>
>>> t.addcmul(0.1, t1, t2)
tensor([[ 0.0992, -0.0608,  0.7114],
        [ 0.2636, -0.3396,  0.8885],
        [ 0.5003, -0.7410,  1.1436]])
>>>
>>>
>>>
>>>