def micro_recall(self, y_true, y_pred):
return K.sum(self.true_positive(y_true, y_pred)) / (K.sum(y_true) + K.epsilon())
def macro_f_measure(self, y_true, y_pred):
precision = self.macro_precision(y_true, y_pred)
recall = self.macro_recall(y_true, y_pred)
return (2 * precision * recall) / (precision + recall + K.epsilon())
def class_f_measure(self, class_label, y_true, y_pred):
precision = self.class_precision(class_label, y_true, y_pred)
recall = self.class_recall(class_label, y_true, y_pred)
return (2 * precision * recall) / (precision + recall + K.epsilon())
def micro_precision(self, y_true, y_pred):
y_pred = self.normalize_y_pred(y_pred)
return K.sum(self.true_positive(y_true, y_pred)) / (K.sum(y_pred) + K.epsilon())
def class_recall(self, class_label, y_true, y_pred):
return K.sum(self.class_true_positive(class_label, y_true, y_pred)) / (K.sum(y_true[:, class_label]) + K.epsilon())
def class_precision(self, class_label, y_true, y_pred):
y_pred = self.normalize_y_pred(y_pred)
return K.sum(self.class_true_positive(class_label, y_true, y_pred)) / (K.sum(y_pred[:, class_label]) + K.epsilon())
def f1_m(y_true, y_pred):
precision = precision_m(y_true, y_pred)
recall = recall_m(y_true, y_pred)
return 2 * ((precision * recall) / (precision + recall + K.epsilon()))
def precision_m(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def recall_m(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
recall = true_positives / (possible_positives + K.epsilon())
return recall