基于keras中的回调函数用法说明

fit(
 self, 
 x, 
 y, 
 batch_size=32, 
 nb_epoch=10, 
 verbose=1, 
 callbacks=[], 
 validation_split=0.0, 
 validation_data=None, 
 shuffle=True, 
 class_weight=None, 
 sample_weight=None
)

keras.callbacks.ModelCheckpoint(
 filepath, 
 monitor='val_loss', 
 verbose=0, 
 save_best_only=False, 
 save_weights_only=False, 
 mode='auto', 
 period=1
)

from keras.callbacksimport EarlyStopping 

keras.callbacks.EarlyStopping(
 monitor='val_loss', 
 patience=0, 
 verbose=0, 
 mode='auto'
)

keras.callbacks.ReduceLROnPlateau(
 monitor='val_loss', 
 factor=0.1, 
 patience=10, 
 verbose=0, 
 mode='auto', 
 epsilon=0.0001, 
 cooldown=0, 
 min_lr=0
)

def step_decay(epoch):
 initial_lrate = 0.01
 drop = 0.5
 epochs_drop = 10.0
 lrate = initial_lrate * math.pow(drop,math.floor((1+epoch)/epochs_drop))
 return lrate
lrate = LearningRateScheduler(step_decay)
sgd = SGD(lr=0.0, momentum=0.9, decay=0.0, nesterov=False)
model.fit(train_set_x, train_set_y, validation_split=0.1, nb_epoch=200, batch_size=256, callbacks=[lrate])

hist=model.fit(train_set_x,train_set_y,batch_size=256,shuffle=True,nb_epoch=nb_epoch,validation_split=0.1)
with open('log_sgd_big_32.txt','w') as f:
 f.write(str(hist.history))

# checkpoint
checkpointer = ModelCheckpoint(filepath="./checkpoint.hdf5", verbose=1)
# learning rate adjust dynamic
lrate = ReduceLROnPlateau(min_lr=0.00001)

answer.compile(optimizer='rmsprop', loss='categorical_crossentropy',
    metrics=['accuracy'])
# Note: you could use a Graph model to avoid repeat the input twice
answer.fit(
 [inputs_train, queries_train, inputs_train], answers_train,
 batch_size=32,
 nb_epoch=5000,
 validation_data=([inputs_test, queries_test, inputs_test], answers_test),
 callbacks=[checkpointer, lrate]
)

keras.callbacks.TensorBoard(log_dir='./Graph', histogram_freq=0, 
   write_graph=True, write_images=True)

tbCallBack = keras.callbacks.TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True)
...
model.fit(...inputs and parameters..., callbacks=[tbCallBack])
tensorboard --logdir path_to_current_dir/Graph 

from keras.callbacks import TensorBoard

tensorboard = TensorBoard(log_dir='./logs', histogram_freq=0,
       write_graph=True, write_images=False)
# define model
model.fit(X_train, Y_train,
   batch_size=batch_size,
   epochs=nb_epoch,
   validation_data=(X_test, Y_test),
   shuffle=True,
   callbacks=[tensorboard])

import keras
callbacks_list=[
 keras.callbacks.EarlyStopping(
  monitor='acc',#监控精度
  patience=5,#5轮内不改善就中止
),
 keras.callbacks.ModelCheckpoint(
  filepath='C:/apple/my_model.h5',#模型保存路径
  monitor='val_loss',#检测验证集损失值
  save_best_only=True#是否只保存最佳模型
 )
]
model.compile(optimizer='rmsprop',
    loss='binary_crossentropy',
    metrics=['acc'])
model.fit(x,y,
   epochs=10,
   batch_size=32,
   callbacks=callbacks_list,#在这里放入callback函数
   validation_data=(x_val,y_val)
 )

import keras
 
callbacks_list=[
 keras.callbacks.ReduceLROnPlateau(
  monitor='val_loss',#监控精度
  patienece=5, # 5轮内不改善就改变
  factor=0.1#学习率变为原来的0.1
)
]
model.compile(optimizer='rmsprop',
    loss='binary_crossentropy',
    metrics=['acc'])
model.fit(x,y,
   epochs=10,
   batch_size=32,
   callbacks=callbacks_list,#在这里放入callback函数
   validation_data=(x_val,y_val)
 )