KERAS: objective or loss functions
来源:互联网 发布:空之境界 知乎 编辑:程序博客网 时间:2024/05/22 03:06
An objective function (or loss function, or optimization score function) is one of the two parameters required to compile a model:
model.compile(loss='mean_squared_error', optimizer='sgd')
There are quite a few choices of such functions that can be found from the source code objectives.py as follows:
import numpy as np
from . import backend as K
def mean_squared_error(y_true, y_pred):
return K.mean(K.square(y_pred - y_true), axis=-1)
def mean_absolute_error(y_true, y_pred):
return K.mean(K.abs(y_pred - y_true), axis=-1)
def mean_absolute_percentage_error(y_true, y_pred):
diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true), K.epsilon(), np.inf))
return 100. * K.mean(diff, axis=-1)
def mean_squared_logarithmic_error(y_true, y_pred):
first_log = K.log(K.clip(y_pred, K.epsilon(), np.inf) + 1.)
second_log = K.log(K.clip(y_true, K.epsilon(), np.inf) + 1.)
return K.mean(K.square(first_log - second_log), axis=-1)
def squared_hinge(y_true, y_pred):
return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)
def hinge(y_true, y_pred):
return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)
def categorical_crossentropy(y_true, y_pred):
'''Expects a binary class matrix instead of a vector of scalar classes.
'''
return K.categorical_crossentropy(y_pred, y_true)
def sparse_categorical_crossentropy(y_true, y_pred):
'''expects an array of integer classes.
Note: labels shape must have the same number of dimensions as output shape.
If you get a shape error, add a length-1 dimension to labels.
'''
return K.sparse_categorical_crossentropy(y_pred, y_true)
def binary_crossentropy(y_true, y_pred):
return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
def kullback_leibler_divergence(y_true, y_pred):
y_true = K.clip(y_true, K.epsilon(), 1)
y_pred = K.clip(y_pred, K.epsilon(), 1)
return K.sum(y_true * K.log(y_true / y_pred), axis=-1)
def poisson(y_true, y_pred):
return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)
def cosine_proximity(y_true, y_pred):
y_true =K.l2_normalize(y_true, axis=-1)
y_pred =K.l2_normalize(y_pred, axis=-1)
return-K.mean(y_true * y_pred, axis=-1)
# aliases
mse =MSE= mean_squared_error
mae =MAE= mean_absolute_error
mape =MAPE= mean_absolute_percentage_error
msle =MSLE= mean_squared_logarithmic_error
kld =KLD= kullback_leibler_divergence
cosine = cosine_proximity
from .utils.generic_utils import get_from_module
def get(identifier):
return get_from_module(identifier, globals(), 'objective')
- KERAS: objective or loss functions
- loss functions for NN
- Usage of loss functions
- Face recognition-Loss Functions
- Keras笔记 -- objective
- Keras笔记 -- objective
- Surrogate Loss Functions in Machine Learning
- CS231N-Lecture3 Loss Functions and Optimization
- Objective-C Math functions
- keras Merge or merge
- my own objective of keras
- CS231n系列课程Lecture 3: Loss functions and Optimization
- keras 自定义 loss损失函数, sample在loss上的加权 和 metric
- keras: Why is the training loss much higher than the testing loss?
- Closure and anonymous functions in Objective-C
- objective-c: Functions and static keyword
- TF/02_TensorFlow_Way/03 Working with Multiple Layers04 Implementing Loss Functions
- keras
- Modeling System Behavior with Use Case(3)
- Android源码下载技巧
- 二叉树的先序遍历、中序遍历以及后序遍历(递归以及非递归方式)
- 安卓开发实现开机启动跳转到指定activity
- KUKA---US2电源的安全属性-------老款硬线连接实现的DRIVE安全STO SBC 、新款基于Safety over EtherCAT 网络帧实现的DRIVE安全STO SBC
- KERAS: objective or loss functions
- 一些实用的小模板
- jsp基础学习---jsp基础知识
- 蓝鸥原生JS:什么是BOM及BOM操作
- GNU ARM汇编--(三)ARM处理器的基本原则
- linux sed用法
- 数组连接concat()
- HDU 5901 Count primes (区间素数个数)
- 2D-slam 激光slam: 开源代码的比较HectorSLAM Gmapping KartoSLAM CoreSLAM LagoSLAM