python 多分类 recall_多类CNN的宏度量（recall/F1…）

我使用CNN对不平衡数据集进行图像分类。我对tensorflow后端是全新的。这是一个多类问题(不是多标签问题)，我有16个类。类是一个热编码的。在

我想计算每个历元的宏指标：F1，精度和召回率。在class Metrics(Callback):

def on_train_begin(self, logs={}):

self.val_f1s = []

self.val_recalls = []

self.val_precisions = []

def on_epoch_end(self, epoch, logs={}):

val_predict = (np.asarray(self.model.predict(self.validation_data[0]))).round()

val_targ = self.validation_data[1]

_val_f1 = f1_score(val_targ, val_predict,average='macro')

_val_recall = recall_score(val_targ, val_predict,average='macro')

_val_precision = precision_score(val_targ, val_predict,average='macro')

self.val_f1s.append(_val_f1)

self.val_recalls.append(_val_recall)

self.val_precisions.append(_val_precision)

print (" — val_f1: %f — val_precision: %f — v