keras.callbacks

最新推荐文章于 2024-07-11 08:59:04 发布

原创最新推荐文章于 2024-07-11 08:59:04 发布 · 279 阅读

CC 4.0 BY-SA版权

文章标签：

14 篇文章

订阅专栏

博客参考腾讯云相关内容，介绍了Keras中模型训练时使用的回调工具。涵盖了多种回调类，如BaseLogger用于累积指标的epoch平均值，CSVLogger将结果流式传输到csv文件，EarlyStopping在监控指标无改善时停止训练等。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Callbacks: utilities called at certain points during model training.

class BaseLogger: Callback that accumulates epoch averages of metrics.
class CSVLogger: Callback that streams epoch results to a csv file.
class Callback: Abstract base class used to build new callbacks.
class EarlyStopping: Stop training when a monitored quantity has stopped improving.
class History: Callback that records events into a History object.
class LambdaCallback: Callback for creating simple, custom callbacks on-the-fly.
class LearningRateScheduler: Learning rate scheduler.
class ModelCheckpoint: Save the model after every epoch.
class ProgbarLogger: Callback that prints metrics to stdout.
class ReduceLROnPlateau: Reduce learning rate when a metric has stopped improving.
class RemoteMonitor: Callback used to stream events to a server.
class TensorBoard: Enable visualizations for TensorBoard.
class TerminateOnNaN: Callback that terminates training when a NaN loss is encountered.