博客
关于我
pytorch 激活函数
阅读量:89 次
发布时间:2019-02-26

本文共 627 字,大约阅读时间需要 2 分钟。

mobilefacenet:

prelu 平均106ms

relu 平均94ms,快12ms,快10%

relu6 平均97ms,收敛慢

leakyrelu,平均106ms,收敛更慢。

inplace=True会x把输入前的删掉了,都变成了输入后的,

没有inplace,输入还是输入,输出是新的了。

import torchimport torch.nn as nn#inplace为True,将会改变输入的数据 ,否则不会改变原输入,只会产生新的输出m = nn.LeakyReLU(inplace=True)input = torch.randn(7)print("输入处理前图片:")print(input)output = m(input)print("ReLU输出:")print(output)print("输入处理后图片:")print(input)

 

import torchimport torch.nn.functional as Fconf_mask = torch.FloatTensor([0.0, 1.0, 0.0, 1.0, 1.0])conf_data = torch.FloatTensor([-20.1, -0.9, 0.0, 0.2,0.5,0.99, 2.2])import torchimport torch.nn as nn#inplace为True,将会改变输入的数据 ,否则不会改变原输入,只会产生新的输出

转载地址:http://tpak.baihongyu.com/

你可能感兴趣的文章
Nmap扫描教程之Nmap基础知识
查看>>
nmap指纹识别要点以及又快又准之方法
查看>>
Nmap渗透测试指南之指纹识别与探测、伺机而动
查看>>
Nmap端口扫描工具Windows安装和命令大全(非常详细)零基础入门到精通,收藏这篇就够了
查看>>
NMAP网络扫描工具的安装与使用
查看>>
NMF(非负矩阵分解)
查看>>
nmon_x86_64_centos7工具如何使用
查看>>
NN&DL4.1 Deep L-layer neural network简介
查看>>
NN&DL4.3 Getting your matrix dimensions right
查看>>
NN&DL4.7 Parameters vs Hyperparameters
查看>>
NN&DL4.8 What does this have to do with the brain?
查看>>
nnU-Net 终极指南
查看>>
No 'Access-Control-Allow-Origin' header is present on the requested resource.
查看>>
No 'Access-Control-Allow-Origin' header is present on the requested resource.
查看>>
NO 157 去掉禅道访问地址中的zentao
查看>>
no available service ‘default‘ found, please make sure registry config corre seata
查看>>
No compiler is provided in this environment. Perhaps you are running on a JRE rather than a JDK?
查看>>
no connection could be made because the target machine actively refused it.问题解决
查看>>
No Datastore Session bound to thread, and configuration does not allow creation of non-transactional
查看>>
No fallbackFactory instance of type class com.ruoyi---SpringCloud Alibaba_若依微服务框架改造---工作笔记005
查看>>