keras通过callback根据epoch自定义修改学习率以及根据loss停止训练

直接放上代码

from tensorflow.keras.callbacks import LearningRateScheduler, Callback

class EarlyStoppingByLossVal(Callback):
    def __init__(self, monitor='val_loss', value=0.00001, verbose=0):
        super(Callback, self).__init__()
        self.monitor = monitor
        self.value = value
        self.verbose = verbose

    def on_epoch_end(self, epoch, logs={}):
        current = logs.get(self.monitor)
        if current is None:
            warnings.warn("Early stopping requires %s available!" % self.monitor, RuntimeWarning)

        if current < self.value:
            if self.verbose > 0:
                print("Epoch %05d: early stopping THR" % epoch)
            self.model.stop_training = True




def step_decay(epoch, lr):
    # initial_lrate = 1.0 # no longer needed
    boundaries = [10,20] # 为不同的epoch范围设置不同的学习率
    values = [100.0, 0.0, 0.1]
    for idx,bd in enumerate(boundaries):
        if (epoch+1)

下面是调试结果

 

根据代码, 结果应该在第10个epoch(实际epoch==9)的时候,学习率变为0, 而在第20个poch(实际epoch==19)的时候,学习率变为0.1.  前面1个正确,不知道为啥后面1个不对???
EarlyStoppingByLossVal是根据传入的监视变量的大小, 来判断是否终止训练.
代码参考这里和这里.