A deep bidirectional LSTM classifie. More...
Inheritance diagram for nabu.neuralnetworks.models.ed_encoders.dblstm.DBLSTM:
Public Member Functions | |
| def | encode (self, inputs, input_seq_length, is_training) |
| Create the variables and do the forward computation. More... | |
 Public Member Functions inherited from nabu.neuralnetworks.models.ed_encoders.ed_encoder.EDEncoder | |
| def | __init__ (self, conf, constraint, name=None) |
| EDEncoder constructor. More... | |
| def | __call__ (self, inputs, input_seq_length, is_training) |
| Create the variables and do the forward computation. More... | |
| def | encode (self, inputs, input_seq_length, is_training) |
| Create the variables and do the forward computation. More... | |
| def | variables (self) |
| get a list of the models's variables | |
Additional Inherited Members | |
| Public Attributes inherited from nabu.neuralnetworks.models.ed_encoders.ed_encoder.EDEncoder | |
| conf | |
| scope | |
Detailed Description
A deep bidirectional LSTM classifie.
Member Function Documentation
§ encode()
| def nabu.neuralnetworks.models.ed_encoders.dblstm.DBLSTM.encode | ( | self, | |
| inputs, | |||
| input_seq_length, | |||
| is_training | |||
| ) |
Create the variables and do the forward computation.
- Parameters
-
inputs the inputs to the neural network, this is a dictionary of [batch_size x time x ...] tensors input_seq_length The sequence lengths of the input utterances, this is a dictionary of [batch_size] vectors is_training whether or not the network is in training mode
- Returns
- the outputs of the encoder as a dictionary of [bath_size x time x ...] tensors
- the sequence lengths of the outputs as a dictionary of [batch_size] tensors
The documentation for this class was generated from the following file:
