athena.models.vad.vad_marblenet
¶
Module Contents¶
Classes¶
Tensorflow ReflectionPad1d module. |
|
Tensorflow BN_Residual_Block module. |
|
implementation of a frame level or segment speech classification |
- class athena.models.vad.vad_marblenet.TFReflectionPad1d(padding_size, padding_type='CONSTANT', **kwargs)¶
Bases:
tensorflow.keras.layers.Layer
Tensorflow ReflectionPad1d module.
- call(x)¶
Calculate forward propagation. :param x: Input tensor (B, T, C). :type x: Tensor
- Returns
Padded tensor (B, T + 2 * padding_size, C).
- Return type
Tensor
- class athena.models.vad.vad_marblenet.BNResidualBlock(repeat_times, kernel_size, filters, dilation_rate, strides, zoneout_rate, nonlinear_activation, nonlinear_activation_params, is_weight_norm, padding_type='REFLECT', **kwargs)¶
Bases:
tensorflow.keras.layers.Layer
Tensorflow BN_Residual_Block module.
- call(x)¶
Calculate forward propagation. :param x: Input tensor (B, T, C). :type x: Tensor
- Returns
Output tensor (B, T, C).
- Return type
Tensor
- _apply_weightnorm(list_layers)¶
Try apply weightnorm for all layer in list_layers.
- class athena.models.vad.vad_marblenet.BNResidualBlocks(config)¶
Bases:
tensorflow.keras.layers.Layer
- default_config¶
- call(x)¶
Calculate forward propagation. :param x: Input tensor (B, T, C). :type x: Tensor
- Returns
Output tensor (B, T, C).
- Return type
Tensor
- class athena.models.vad.vad_marblenet.VadMarbleNet(data_descriptions, config=None)¶
Bases:
athena.models.base.BaseModel
implementation of a frame level or segment speech classification
- default_config¶
- call(samples, training=None)¶
call model
- build_model(data_descriptions)¶
- get_loss(outputs, samples, training=None)¶
get loss