精密Keras定製判決門限和召回

Question

我正在使用Keras（與Tensorflow後端）的二元分類，我已經得到了約76％的精度和70％的召回。現在我想嘗試玩決定門檻。據我所知Keras使用決策閾值0.5。 Keras有沒有辦法使用自定義閾值進行決策精確度和召回？

謝謝你的時間！

Answer 1

創建自定義指標是這樣的：

編輯感謝@Marcin：創建功能與threshold_value爲參數

def precision_threshold(threshold=0.5): 
    def precision(y_true, y_pred): 
     """Precision metric. 
     Computes the precision over the whole batch using threshold_value. 
     """ 
     threshold_value = threshold 
     # Adaptation of the "round()" used before to get the predictions. Clipping to make sure that the predicted raw values are between 0 and 1. 
     y_pred = K.cast(K.greater(K.clip(y_pred, 0, 1), threshold_value), K.floatx()) 
     # Compute the number of true positives. Rounding in prevention to make sure we have an integer. 
     true_positives = K.round(K.sum(K.clip(y_true * y_pred, 0, 1))) 
     # count the predicted positives 
     predicted_positives = K.sum(y_pred) 
     # Get the precision ratio 
     precision_ratio = true_positives/(predicted_positives + K.epsilon()) 
     return precision_ratio 
    return precision 

def recall_threshold(threshold = 0.5): 
    def recall(y_true, y_pred): 
     """Recall metric. 
     Computes the recall over the whole batch using threshold_value. 
     """ 
     threshold_value = threshold 
     # Adaptation of the "round()" used before to get the predictions. Clipping to make sure that the predicted raw values are between 0 and 1. 
     y_pred = K.cast(K.greater(K.clip(y_pred, 0, 1), threshold_value), K.floatx()) 
     # Compute the number of true positives. Rounding in prevention to make sure we have an integer. 
     true_positives = K.round(K.sum(K.clip(y_true * y_pred, 0, 1))) 
     # Compute the number of positive targets. 
     possible_positives = K.sum(K.clip(y_true, 0, 1)) 
     recall_ratio = true_positives/(possible_positives + K.epsilon()) 
     return recall_ratio 
    return recall 

現在你可以在

model.compile(..., metrics = [precision_threshold(0.1), precision_threshold(0.2),precision_threshold(0.8), recall_threshold(0.2,...)]) 

使用這些返回所需的指標

我希望這有助於:)