tensorflow2.0深度学习 keras AUC性能评估

借鉴：keras中自定义验证集的性能评估（ROC,AUC）

1. AUC 计算公式

from tensorflow.keras import backend as K

# AUC for a binary classifier
def auc(y_true, y_pred):
    ptas = tf.stack([binary_PTA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0)
    pfas = tf.stack([binary_PFA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0)
    pfas = tf.concat([tf.ones((1,)) ,pfas],axis=0)
    binSizes = -(pfas[1:]-pfas[:-1])
    s = ptas*binSizes
    return K.sum(s, axis=0)
#-----------------------------------------------------------------------------------------------------------------------------------------------------
# PFA, prob false alert for binary classifier
def binary_PFA(y_true, y_pred, threshold=K.variable(value=0.5)):
    y_pred = K.cast(y_pred >= threshold, 'float32')
    # N = total number of negative labels
    N = K.sum(1 - y_true)
    # FP = total number of false alerts, alerts from the negative class labels
    FP = K.sum(y_pred - y_pred * y_true)
    return FP/N
#-----------------------------------------------------------------------------------------------------------------------------------------------------
# P_TA prob true alerts for binary classifier
def binary_PTA(y_true, y_pred, threshold=K.variable(value=0.5)):
    y_pred = K.cast(y_pred >= threshold, 'float32')
    # P = total number of positive labels
    P = K.sum(y_true)
    # TP = total number of correct alerts, alerts from the positive class labels
    TP = K.sum(y_pred * y_true)
    return TP/P

2. 运行实例

# 构建
input1 = tf.keras.Input(shape=[x_train.shape[0],],dtype=float32)
X1 = tf.keras.layers.Flatten()(input1)
X1 = tf.keras.layers.BatchNormalization()(X1)
X1 = tf.keras.layers.Dense(16, activation=tf.keras.layers.LeakyReLU(alpha=0.3))(X1)
X1 = tf.keras.layers.Dropout(0.5)(X1)
output = tf.keras.layers.Dense(1, activation='sigmoid')(X1)

model = tf.keras.Model(inputs=input1,outputs=output)

model.sammary()

# 编译
model.compile(loss='binary_crossentropy',
			  optimizer='adam',
			  metrics=[auc]
)