keras自定义评价函数

注：不知道是否正确

示例一：

import keras.backend as K
from keras import Sequential
from keras.layers import Dense
import numpy as np

def getPrecision(y_true, y_pred):
    TP = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))#TP
    N = (-1)*K.sum(K.round(K.clip(y_true-K.ones_like(y_true), -1, 0)))#N
    TN=K.sum(K.round(K.clip((y_true-K.ones_like(y_true))*(y_pred-K.ones_like(y_pred)), 0, 1)))#TN
    FP=N-TN
    precision = TP / (TP + FP + K.epsilon())#TT/P
    return precision

def getRecall(y_true, y_pred):
    TP = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))#TP
    P=K.sum(K.round(K.clip(y_true, 0, 1)))
    FN = P-TP #FN=P-TP
    recall = TP / (TP + FN + K.epsilon())#TP/(TP+FN)
    return recall
model.compile(optimizer="sgd", loss="categorical_crossentropy",metrics=["acc",getRecall,getPrecision])

 来源：https://zhuanlan.zhihu.com/p/38080551

示例二：

from keras import backend as K
def Precision(y_true, y_pred):
    """精确率"""
    tp= K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))  # true positives
    pp= K.sum(K.round(K.clip(y_pred, 0, 1))) # predicted positives
    precision = tp/ (pp+ K.epsilon())
    return precision
    
def Recall(y_true, y_pred):
    """召回率"""
    tp = K.sum(K.round(K.clip(y_true * y_pred, 0, 1))) # true positives
    pp = K.sum(K.round(K.clip(y_true, 0, 1))) # possible positives
    recall = tp / (pp + K.epsilon())
    return recall
 
def F1(y_true, y_pred):
    """F1-score"""
    precision = Precision(y_true, y_pred)
    recall = Recall(y_true, y_pred)
    f1 = 2 * ((precision * recall) / (precision + recall + K.epsilon()))
    return f1

来源：https://blog.csdn.net/joleoy/article/details/85787457