当前位置:网站首页>keras model.compile Loss function and optimizer
keras model.compile Loss function and optimizer
2020-11-06 01:22:00 【Elementary school students in IT field】
Loss function
summary
Loss function is the goal of model optimization , So it's also called objective function 、 Optimize the scoring function , stay keras in , Parameters for model compilation loss Class of loss function specified , There are two ways of specifying :
model.compile(loss='mean_squared_error', optimizer='sgd')
perhaps
from keras import losses
model.compile(loss=losses.mean_squared_error, optimizer='sgd')
Available loss function
Available loss objective function :
mean_squared_error or mse
mean_absolute_error or mae
mean_absolute_percentage_error or mape
mean_squared_logarithmic_error or msle
squared_hinge
hinge
categorical_hinge
binary_crossentropy( Also called logarithmic loss ,logloss)
logcosh
categorical_crossentropy: Also known as multi class logarithmic loss , Note when using this objective function , The label needs to be transformed into a shape like (nb_samples, nb_classes) Binary sequence of
sparse_categorical_crossentrop: Above , But accept sparse tags . Be careful , When using this function, you still need to have the same dimension as the output value , You may need to add a dimension to the tag data :np.expand_dims(y,-1)
kullback_leibler_divergence: From the probability distribution of predicted values Q To the truth probability distribution P Information gain of , To measure the difference between two distributions .
poisson: namely (predictions - targets * log(predictions)) The average of
cosine_proximity: That is, the inverse number between the predicted value and the average cosine distance of the real label
Loss function formula
https://zhuanlan.zhihu.com/p/34667893
Two classification - Report errors
On the loss function of the report error :
use Keras Do text classification , I always have mistakes like this ,
My category is 0 or 1, But the mistake told me it couldn't be 1.
See :Received a label value of 1 which is outside the valid range of [0, 1) - Python, Keras
loss function The problem of .
It used to be sparse_categorical_crossentropy,
Change it to binary_crossentropy Problem solving .
Optimizer
https://www.cnblogs.com/xiaobingqianrui/p/10756046.html
版权声明
本文为[Elementary school students in IT field]所创,转载请带上原文链接,感谢
边栏推荐
- Don't go! Here is a note: picture and text to explain AQS, let's have a look at the source code of AQS (long text)
- Just now, I popularized two unique skills of login to Xuemei
- Python download module to accelerate the implementation of recording
- git rebase的時候捅婁子了,怎麼辦?線上等……
- Summary of common algorithms of linked list
- 加速「全民直播」洪流,如何攻克延时、卡顿、高并发难题?
- Summary of common string algorithms
- Programmer introspection checklist
- Summary of common algorithms of binary tree
- I'm afraid that the spread sequence calculation of arbitrage strategy is not as simple as you think
猜你喜欢
Tool class under JUC package, its name is locksupport! Did you make it?
教你轻松搞懂vue-codemirror的基本用法:主要实现代码编辑、验证提示、代码格式化
合约交易系统开发|智能合约交易平台搭建
Python Jieba segmentation (stuttering segmentation), extracting words, loading words, modifying word frequency, defining thesaurus
Summary of common algorithms of binary tree
一篇文章带你了解CSS3图片边框
JVM memory area and garbage collection
How long does it take you to work out an object-oriented programming interview question from Ali school?
一篇文章带你了解SVG 渐变知识
Filecoin最新动态 完成重大升级 已实现四大项目进展!
随机推荐
Working principle of gradient descent algorithm in machine learning
Leetcode's ransom letter
2018中国云厂商TOP5:阿里云、腾讯云、AWS、电信、联通 ...
中小微企业选择共享办公室怎么样?
How do the general bottom buried points do?
Can't be asked again! Reentrantlock source code, drawing a look together!
6.3 handlerexceptionresolver exception handling (in-depth analysis of SSM and project practice)
6.5 request to view name translator (in-depth analysis of SSM and project practice)
Wiremock: a powerful tool for API testing
Flink的DataSource三部曲之二:内置connector
Just now, I popularized two unique skills of login to Xuemei
基於MVC的RESTFul風格API實戰
Python3 e-learning case 4: writing web proxy
hadoop 命令总结
Face to face Manual Chapter 16: explanation and implementation of fair lock of code peasant association lock and reentrantlock
快快使用ModelArts,零基礎小白也能玩轉AI!
Calculation script for time series data
Polkadot series (2) -- detailed explanation of mixed consensus
中国提出的AI方法影响越来越大,天大等从大量文献中挖掘AI发展规律
IPFS/Filecoin合法性:保护个人隐私不被泄露