诸神缄默不语-个人CSDN博文目录
1. 早停
early_stopping_callback = EarlyStopping(monitor='val_loss', patience=epochs_to_wait_for_improve)
这个是叠callback的写法:
early_stopping_callback = EarlyStopping(monitor='val_loss', patience=epochs_to_wait_for_improve)
checkpoint_callback = ModelCheckpoint(model_name+'.h5', monitor='val_loss', verbose=1, save_best_only=True, mode='min')
history = model.fit_generator(datagen.flow(X_train, y_train, batch_size=batch_size),steps_per_epoch=len(X_train) / batch_size, validation_data=(X_test, y_test),epochs=n_epochs, callbacks=[early_stopping_callback, checkpoint_callback])
手动停止模型训练:在Callback(keras.callbacks.Callback
)里面设置self.model.stop_training=True
,一般在on_batch_end()
中设置
设置在某个监视指标达到阈值后停止训练,可以参考:
def on_batch_end(self, epoch, logs=None):current = self.get_monitor_value(logs)if current is None:returnif self.monitor_op(current - self.min_delta, self.best):self.best = currentself.wait = 0if self.restore_best_weights:self.best_weights = self.model.get_weights()else:self.wait += 1if self.wait >= self.patience:self.stopped_epoch = epochself.model.stop_training = Trueif self.restore_best_weights:if self.verbose > 0:print('Restoring model weights from the end of ''the best epoch')self.model.set_weights(self.best_weights)
2. 获取预测值和真实值的数据
待补。参考资料:Keras 在fit-generator中获取验证数据的y_true和y_preds_valueerror: output of generator should be a tuple -CSDN博客 keras使用中fit_generator的一些问题 - 知乎
本文撰写过程中参考的网络资料
- python - Is there a way in Keras to immediately stop training? - Stack Overflow
- python - Keras: early stopping model saving - Stack Overflow
- python - How to tell Keras stop training based on loss value? - Stack Overflow:这个是希望限制loss小于指定值后就停止训练
- Keras笔记——ModelCheckpoint-CSDN博客:这个是关于模型checkpoint保存的
- keras的fit_generator与callback函数 - 简书
- https://github.com/keras-team/keras/blob/master/keras/callbacks.py
- 回调函数 Callbacks - Keras 中文文档