a general class for an encoder decoder system
More...
|
def | __init__ (self, conf, trainlabels, constraint) |
| Model constructor. More...
|
|
def | __call__ (self, inputs, input_seq_length, targets, target_seq_length, is_training) |
| Add the neural net variables and operations to the graph. More...
|
|
def | variables (self) |
| get a list of the models's variables
|
|
|
| conf |
|
| input_names |
|
| output_names |
|
| output_dims |
|
| encoder |
|
| decoder |
|
a general class for an encoder decoder system
§ __init__()
def nabu.neuralnetworks.models.model.Model.__init__ |
( |
|
self, |
|
|
|
conf, |
|
|
|
trainlabels, |
|
|
|
constraint |
|
) |
| |
Model constructor.
- Parameters
-
conf | The model configuration as a configparser object |
trainlabels | the number of extra labels required by the trainer |
constraint | a constraint for the model paramaters |
§ __call__()
def nabu.neuralnetworks.models.model.Model.__call__ |
( |
|
self, |
|
|
|
inputs, |
|
|
|
input_seq_length, |
|
|
|
targets, |
|
|
|
target_seq_length, |
|
|
|
is_training |
|
) |
| |
Add the neural net variables and operations to the graph.
- 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 |
targets | the targets to the neural network, this is a dictionary of [batch_size x time x ...] tensors. |
target_seq_length | The sequence lengths of the target utterances, this is a dictionary of [batch_size] vectors |
is_training | whether or not the network is in training mode |
- Returns
- output logits, which is a dictionary of [batch_size x time x ...]
-
tensors
- the output logits sequence lengths which is a dictionary of [batch_size] vectors
The documentation for this class was generated from the following file: