Comments (3)
自编码器一般是基于重构误差最小化进行训练的,一般loss函数选用平方误差函数或者交叉熵误差函数。由于解码器输出端一般采用sigmoid激活,其输出范围在[0,1],所以为了能够获得较小的重构误差,输入数据最好也归一化到[0,1]
训练发散的原因一般是损失函数选择不对或者训练参数设置不合理吧,建议选择交叉熵损失函数和一个较小的学习率训练试试
from tutorials.
ok, the problem is fixed, I normalize the input into [-1,1].
Thank for your answer.
(PS: My Ubuntu doesn't input chinese .)
from tutorials.
@liuguiyangnwpu 麻烦问下你除了归一化外还做了其他的处理吗?我把输入除以255再减0.5以后归一化到了-0.5到0.5. 然后再用binary_crossentropy来训练发现loss为负,不知道你有没有遇到这样的问题,谢谢!
from tutorials.
Related Issues (20)
- visualize cpu history HOT 3
- lstm的batch_size要刚好被数据集整除么 HOT 1
- tensorflowTUT/tf12_plot_result/full_code.py NameError: name 'time' is not defined HOT 3
- ssl.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:777)5-classifier_example.py
- 有没有读取自己的图像训练集的代码呀
- 您好,sk9_cross_validation2.py中的实例在python3.6.6中运行报错
- Classification那一课 HOT 1
- 为什么我的没有画线 HOT 9
- 在tensorflow中的dropout中修改建议 HOT 1
- 建议
- 激活函数
- pandas values HOT 4
- 推荐增加一些简易的新算法
- 求助一下 tensorflow是2.0.0的 报错train中没有GradientDescentOptimizer
- 请问强化学习是怎么影响神经网络参数的
- Is this your website? https://www.echenshe.com/class/tensorflow/ HOT 1
- Qw
- tensorflow 还支持另外一种batch normalization 的方法 HOT 2
- tensorflow 2.1.0 error HOT 3
- 网站进不去了 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tutorials.