RNN 训练的回调函数

使用语言模型输出添加 AR 和 TAR 正则化的回调函数

源代码

ModelResetter

 ModelResetter (after_create=None, before_fit=None, before_epoch=None,
                before_train=None, before_batch=None, after_pred=None,
                after_loss=None, before_backward=None,
                after_cancel_backward=None, after_backward=None,
                before_step=None, after_cancel_step=None, after_step=None,
                after_cancel_batch=None, after_batch=None,
                after_cancel_train=None, after_train=None,
                before_validate=None, after_cancel_validate=None,
                after_validate=None, after_cancel_epoch=None,
                after_epoch=None, after_cancel_fit=None, after_fit=None)

Callback 在每个验证/训练步骤重置模型的回调函数

源代码

RNNCallback

 RNNCallback (after_create=None, before_fit=None, before_epoch=None,
              before_train=None, before_batch=None, after_pred=None,
              after_loss=None, before_backward=None,
              after_cancel_backward=None, after_backward=None,
              before_step=None, after_cancel_step=None, after_step=None,
              after_cancel_batch=None, after_batch=None,
              after_cancel_train=None, after_train=None,
              before_validate=None, after_cancel_validate=None,
              after_validate=None, after_cancel_epoch=None,
              after_epoch=None, after_cancel_fit=None, after_fit=None)

保存原始输出和丢弃输出，仅保留真实输出用于损失计算

源代码

RNNRegularizer

 RNNRegularizer (alpha=0.0, beta=0.0)

添加 AR 和 TAR 正则化

源代码

rnn_cbs

 rnn_cbs (alpha=0.0, beta=0.0)

(可选地进行正则化的) RNN 训练所需的所有回调函数