keras用auc做metrics以及早停實(shí)例

更新時(shí)間：2020年07月02日 10:40:53 作者：ssswill

這篇文章主要介紹了keras用auc做metrics以及早停實(shí)例，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧

我就廢話(huà)不多說(shuō)了，大家還是直接看代碼吧~

import tensorflow as tf
from sklearn.metrics import roc_auc_score

def auroc(y_true, y_pred):
 return tf.py_func(roc_auc_score, (y_true, y_pred), tf.double)
# Build Model...

model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['accuracy', auroc])

完整例子：

def auc(y_true, y_pred):
 auc = tf.metrics.auc(y_true, y_pred)[1]
 K.get_session().run(tf.local_variables_initializer())
 return auc

def create_model_nn(in_dim,layer_size=200):
 model = Sequential()
 model.add(Dense(layer_size,input_dim=in_dim, kernel_initializer='normal'))
 model.add(BatchNormalization())
 model.add(Activation('relu'))
 model.add(Dropout(0.3))
 for i in range(2):
  model.add(Dense(layer_size))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(Dropout(0.3))
 model.add(Dense(1, activation='sigmoid'))
 adam = optimizers.Adam(lr=0.01)
 model.compile(optimizer=adam,loss='binary_crossentropy',metrics = [auc]) 
 return model
####cv train
folds = StratifiedKFold(n_splits=5, shuffle=False, random_state=15)
oof = np.zeros(len(df_train))
predictions = np.zeros(len(df_test))
for fold_, (trn_idx, val_idx) in enumerate(folds.split(df_train.values, target2.values)):
 print("fold n°{}".format(fold_))
 X_train = df_train.iloc[trn_idx][features]
 y_train = target2.iloc[trn_idx]
 X_valid = df_train.iloc[val_idx][features]
 y_valid = target2.iloc[val_idx]
 model_nn = create_model_nn(X_train.shape[1])
 callback = EarlyStopping(monitor="val_auc", patience=50, verbose=0, mode='max')
 history = model_nn.fit(X_train, y_train, validation_data = (X_valid ,y_valid),epochs=1000,batch_size=64,verbose=0,callbacks=[callback])
 print('\n Validation Max score : {}'.format(np.max(history.history['val_auc'])))
 predictions += model_nn.predict(df_test[features]).ravel()/folds.n_splits

補(bǔ)充知識(shí)：Keras可使用的評(píng)價(jià)函數(shù)

1：binary_accuracy（對(duì)二分類(lèi)問(wèn)題，計(jì)算在所有預(yù)測(cè)值上的平均正確率）