athena.models.lm.nn_lm
¶
NN language model interface
Module Contents¶
Classes¶
Standard implementation of a RNNLM. Model mainly consists of embeding layer, |
- class athena.models.lm.nn_lm.NNLM¶
Bases:
athena.models.base.BaseModel
Standard implementation of a RNNLM. Model mainly consists of embeding layer, rnn layers(with dropout), and the full connection layer, which are all incuded in self.model_for_rnn
- abstract forward(inputs, inputs_length, training: bool = None)¶
do NN LM forward computation, for both train and decode.
- call(samples, training: bool = None)¶
call model
- save_model(path)¶
for saving model and current weight, path is h5 file name, like ‘my_model.h5’ usage: new_model = tf.keras.models.load_model(path)
- get_loss(logits, samples, training=None)¶
get loss
- get_ppl(loss)¶
loss is returned by self.get_loss(), and it is a tensor with none shape float value