Keras 在指定的历元数后提前停止KERA

在Keras中规定的历元数之后，是否可以应用提前停止。 例如，我想训练我的神经网络45个历元，然后开始使用EarlyStoping

到目前为止，我是这样做的：

early\u stop=earlystoping（监视器class='val\u loss'，模式class='min'，冗余=1，基线=0.1，耐心=3）

但这样做，只会产生一些用于训练的步骤图

---

有没有办法让我把这些都写在一起？非常感谢任何帮助

我认为我们可以使用Keras库中的自定义回调来实现这一点。按如下方式定义自定义回调：

# Custom Callback
class myCallback(keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if epoch == 45:
      self.model.stop_training = True
callback = myCallback()

opt = Adam(lr = .00001, beta_1=0.9, beta_2=0.999, epsilon=1e-8)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics = ['accuracy'])
# Include myCallback in callbacks so that the model stops training after 45th epoch
mod = model.fit_generator(train_batches, steps_per_epoch = 66, validation_data = valid_batches, validation_steps = 22, epochs = 50, callbacks = [early_stop, myCallback], verbose = 1)

---

回答你的问题了吗？不，我想在第45个纪元后申请提前停车，而不是在那个时候停车

# Custom Callback
class myCallback(keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if epoch == 45:
      self.model.stop_training = True
callback = myCallback()

opt = Adam(lr = .00001, beta_1=0.9, beta_2=0.999, epsilon=1e-8)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics = ['accuracy'])
# Include myCallback in callbacks so that the model stops training after 45th epoch
mod = model.fit_generator(train_batches, steps_per_epoch = 66, validation_data = valid_batches, validation_steps = 22, epochs = 50, callbacks = [early_stop, myCallback], verbose = 1)