原文：https://gist.github.com/yano/3a072e5e2b7a55703028751820bfacbf

import keras.backend as K
#precision
def P(y_true, y_pred):
    true_positives = K.sum(K.cast(K.greater(K.clip(y_true * y_pred, 0, 1), 0.20), 'float32'))
    pred_positives = K.sum(K.cast(K.greater(K.clip(y_pred, 0, 1), 0.20), 'float32'))

    precision = true_positives / (pred_positives + K.epsilon())
    return precision

#recall
def R(y_true, y_pred):
    true_positives = K.sum(K.cast(K.greater(K.clip(y_true * y_pred, 0, 1), 0.20), 'float32'))
    poss_positives = K.sum(K.cast(K.greater(K.clip(y_true, 0, 1), 0.20), 'float32'))

    recall = true_positives / (poss_positives + K.epsilon())
    return recall

#f-measure
def F(y_true, y_pred):
    p_val = P(y_true, y_pred)
    r_val = R(y_true, y_pred)
    f_val = 2*p_val*r_val / (p_val + r_val)

    return f_val
    
#以下代码未测试。
def fbeta_score(y_true, y_pred, beta=1):
    # Calculates the F score, the weighted harmonic mean of precision and recall.
 
    if beta < 0:
        raise ValueError('The lowest choosable beta is zero (only precision).')
        
    # If there are no true positives, fix the F score at 0 like sklearn.
    if K.sum(K.round(K.clip(y_true, 0, 1))) == 0:
        return 0
 
    p = P(y_true, y_pred)
    r = R(y_true, y_pred)
    bb = beta ** 2
    fbeta_score = (1 + bb) * (p * r) / (bb * p + r + K.epsilon())
    return fbeta_score
 
def fmeasure(y_true, y_pred):
    # Calculates the f-measure, the harmonic mean of precision and recall.

model.compile(optimizer=rms_prop, loss=“binary_crossentropy”, metrics=[P, R, F])