PyTorch torch.sin - torch.cos

torch
https://pytorch.org/docs/stable/torch.html

torch.sin() - torch.cos() 的 input (Tensor) 都是弧度制数据，不是角度制数据。

• torch.sin (Python function, in torch.sin)

• torch.Tensor.sin (Python method, in torch.Tensor.sin)

• torch.Tensor.sin_ (Python method, in torch.Tensor.sin_)

• torch.cos (Python function, in torch.cos)

• torch.Tensor.cos (Python method, in torch.Tensor.cos)

• torch.Tensor.cos_ (Python method, in torch.Tensor.cos_)

1. torch.sin

https://pytorch.org/docs/stable/generated/torch.sin.html

torch.sin(input, *, out=None) -> Tensor

Returns a new tensor with the sine of the elements of input.
返回一个新的张量 tensor , 其元素是张量 input 元素的正弦。

$${\text{out}}_i=\sin ({\text{input}}_i)$$

• Parameters

input (Tensor) - the input tensor.

• Keyword Arguments

out (Tensor, optional) - the output tensor.

1.1. Example

(pt-1.4_py-3.6) yongqiang@yongqiang:~$ python
Python 3.6.10 |Anaconda, Inc.| (default, May  8 2020, 02:54:21)
[GCC 7.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> import numpy as np
>>>
>>> data = np.array([0, 1/2.0, 1, 3/2.0, 2])
>>> data
array([0. , 0.5, 1. , 1.5, 2. ])
>>>
>>> data = data * np.pi
>>> data
array([0.        , 1.57079633, 3.14159265, 4.71238898, 6.28318531])
>>>
>>> torch.sin(data)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: sin(): argument 'input' (position 1) must be Tensor, not numpy.ndarray
>>>
>>> torch.sin(torch.Tensor(data))
tensor([ 0.0000e+00,  1.0000e+00, -8.7423e-08, -1.0000e+00,  1.7485e-07])
>>> exit()
(pt-1.4_py-3.6) yongqiang@yongqiang:~$

2. torch.cos

https://pytorch.org/docs/stable/generated/torch.cos.html

Returns a new tensor with the cosine of the elements of input.

$${\text{out}}_i=\cos ({\text{input}}_i)$$

• Parameters

input (Tensor) - the input tensor.

• Keyword Arguments

out (Tensor, optional) - the output tensor.

2.1. Example

(pt-1.4_py-3.6) yongqiang@yongqiang:~$ python
Python 3.6.10 |Anaconda, Inc.| (default, May  8 2020, 02:54:21)
[GCC 7.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> import numpy as np
>>>
>>> data = np.array([0.0, 1/2.0, 1.0, 3/2.0, 2.0])
>>> data
array([0. , 0.5, 1. , 1.5, 2. ])
>>>
>>> data = data * np.pi
>>> data
array([0.        , 1.57079633, 3.14159265, 4.71238898, 6.28318531])
>>>
>>> torch.cos(torch.Tensor(data))
tensor([ 1.0000e+00, -4.3711e-08, -1.0000e+00,  1.1925e-08,  1.0000e+00])
>>>
>>> torch.sin(torch.Tensor(data))
tensor([ 0.0000e+00,  1.0000e+00, -8.7423e-08, -1.0000e+00,  1.7485e-07])
>>>
>>> exit()
(pt-1.4_py-3.6) yongqiang@yongqiang:~$

References

[1] Yongqiang Cheng, https://yongqiang.blog.csdn.net/