keras中的History对象用法
keras中的fit_generator和fit函数均返回History对象，那么History怎么用呢？事实上History对象已经记录了运行输出。在了解之前，我们甚至自己定义回调函数记录损失和准确率等。
相关keras源码位于网址：
classHistory(Callback):
"""Callbackthatrecordseventsintoa`History`object.
Thiscallbackisautomaticallyappliedto
everyKerasmodel.The`History`object
getsreturnedbythe`fit`methodofmodels.
"""
defon_train_begin(self,logs=None):
self.epoch=[]
self.history={}
defon_epoch_end(self,epoch,logs=None):
logs=logsor{}
self.epoch.append(epoch)
fork,vinlogs.items():
self.history.setdefault(k,[]).append(v)
可以看出History类对象包含两个属性，分别为epoch和history，epoch为训练轮数。
根据compile参数metrics，history包含不同的内容。比如，当某一次metrics=['accuracy']时，运行如下部分代码我们可以看出，history字典类型，包含val_loss,val_acc,loss,acc四个key值。
####省略若干 history=model.fit_generator( mp.train_flow, steps_per_epoch=32, epochs=3, validation_data=mp.test_flow, validation_steps=32) print(history.history) print(history.epoch) print(history.history['val_loss'])
{‘val_loss':[0.4231100323200226,0.3713115310668945,0.3836631367206573],‘val_acc':[0.815,0.84,0.83],‘loss':[0.8348453622311354,0.5010451343324449,0.4296100065112114],‘acc':[0.630859375,0.7509920634920635,0.783203125]}
[0,1,2]
[0.4231100323200226,0.3713115310668945,0.3836631367206573]
补充知识：在ipython中使用%history快速查找历史命令
1、输出所有历史记录，且带有序号
%history-n 150:%cpaste 151:%cpaste 152:print(r">>>>>>>>>") 153:print(r'>>>>>>>>>') 154:print(r'>>>>>>>>><') 155:print(r'>') 156:print(r'>>') 157:print(r'>>>') ...
2、按序号，查找某些序号区间的历史纪录
%history-n168-170178185-190
168:planets
169:
formethod,groupinplanets.groupby('method'):
print(f'{method:30s}method={group}')
170:
formethod,groupinplanets.groupby('method'):
print(f'{method:30s}method={group.shape}')
178:%history?
185:%history-u
186:%history-n-u
187:?%history
188:%history-gmethod
189:%history-gmethodprint
190:%history-gformethod,
3、模糊查找
%history-gprint*metho*
120:
formethod,groupinplanets.groupby('method'):
print(f"{method:30s}shape={groupe.shape}")
121:
formethod,groupinplanets.groupby('method'):
print(f"{method:30s}shape={group.shape}")
169:
formethod,groupinplanets.groupby('method'):
print(f'{method:30s}method={group}')
170:
formethod,groupinplanets.groupby('method'):
print(f'{method:30s}method={group.shape}')
182:
formethod,groupinplanets.groupby('method'):
print(f"{method:30sshape=group.shape}")
198:%history-gprint*metho*
以上这篇keras中的History对象用法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。