torch.exp()的使用舉例

參考連接: torch.exp(input, out=None)
參考連接: exp()

代碼實驗展現:

Microsoft Windows [版本 10.0.18363.1256]
(c) 2019 Microsoft Corporation。保留全部權利。

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
>>> import math
>>> torch.manual_seed(seed=20200910)
<torch._C.Generator object at 0x0000023D74B6D330>
>>>
>>> torch.exp(torch.tensor([0, math.log(2.)]))
tensor([1., 2.])
>>>
>>> math.log(2.)
0.6931471805599453
>>> input = torch.tensor([[0,1,2],[3,4,5]],dtype=torch.float)
>>> input
tensor([[0., 1., 2.],
        [3., 4., 5.]])
>>> torch.exp(input)
tensor([[  1.0000,   2.7183,   7.3891],
        [ 20.0855,  54.5981, 148.4132]])
>>>
>>>
>>> input = torch.randn(3,5)
>>> input
tensor([[ 0.2824, -0.3715,  0.9088, -1.7601, -0.1806],
        [ 2.0937,  1.0406, -1.7651,  1.1216,  0.8440],
        [ 0.1783,  0.6859, -1.5942, -0.2006, -0.4050]])
>>> torch.exp(input)
tensor([[1.3263, 0.6897, 2.4813, 0.1720, 0.8348],
        [8.1147, 2.8310, 0.1712, 3.0699, 2.3256],
        [1.1952, 1.9855, 0.2031, 0.8183, 0.6669]])
>>>
>>>
>>>

本文同步分享在 博客「敲代碼的小風」（CSDN）。
若有侵權，請聯繫 support@oschina.cn 刪除。
本文參與「OSC源創計劃」，歡迎正在閱讀的你也加入，一塊兒分享。