在keras里面实现计算f1-score的代码
我就废话不多说了,大家还是直接看代码吧!
###以下链接里面的code importnumpyasnp fromkeras.callbacksimportCallback fromsklearn.metricsimportconfusion_matrix,f1_score,precision_score,recall_score classMetrics(Callback): defon_train_begin(self,logs={}): self.val_f1s=[] self.val_recalls=[] self.val_precisions=[] defon_epoch_end(self,epoch,logs={}): val_predict=(np.asarray(self.model.predict(self.model.validation_data[0]))).round() val_targ=self.model.validation_data[1] _val_f1=f1_score(val_targ,val_predict) _val_recall=recall_score(val_targ,val_predict) _val_precision=precision_score(val_targ,val_predict) 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—val_recall%f”%(_val_f1,_val_precision,_val_recall) return metrics=Metrics() model.fit( train_instances.x, train_instances.y, batch_size, epochs, verbose=2, callbacks=[metrics], validation_data=(valid_instances.x,valid_instances.y), )
补充知识:Keras可使用的评价函数
1:binary_accuracy(对二分类问题,计算在所有预测值上的平均正确率)
binary_accuracy(y_true,y_pred)
2:categorical_accuracy(对多分类问题,计算在所有预测值上的平均正确率)
categorical_accuracy(y_true,y_pred)
3:sparse_categorical_accuracy(与categorical_accuracy相同,在对稀疏的目标值预测时有用)
sparse_categorical_accuracy(y_true,y_pred)
4:top_k_categorical_accuracy(计算top-k正确率,当预测值的前k个值中存在目标类别即认为预测正确)
top_k_categorical_accuracy(y_true,y_pred,k=5)
5:sparse_top_k_categorical_accuracy(与top_k_categorical_accracy作用相同,但适用于稀疏情况)
sparse_top_k_categorical_accuracy(y_true,y_pred,k=5)
以上这篇在keras里面实现计算f1-score的代码就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持毛票票。