- class das.kapre.filterbank.Filterbank(*args, **kwargs)#
- `kapre.filterbank.Filterbank(n_fbs, trainable_fb, sr=None, init=’mel’, fmin=0., fmax=None,
bins_per_octave=12, image_data_format=’default’, **kwargs)`
- #### Notes
Input/output are 2D image format. E.g., if channel_first,
(None, n_ch, n_freqs, n_time)
(None, n_ch, n_mels, n_time)
#### Parameters * n_fbs: int
Number of filterbanks
- sr: int
sampling rate. It is used to initialize
- init: str
'mel', init with mel center frequencies and stds.
- fmin: float
min frequency of filterbanks.
init == 'log', fmin should be > 0. Use
Noneif you got no idea.
- fmax: float
max frequency of filterbanks.
init == 'log', fmax is ignored.
- trainable_fb: bool,
Whether the filterbanks are trainable or not.
TODO: is sr necessary? is fmax necessary? init with None?
Creates the variables of the layer (optional, for subclass implementers).
This is a method that implementers of subclasses of
Modelcan override if they need a state-creation step in-between layer instantiation and layer call.
This is typically used to create the weights of
input_shape – Instance of
TensorShape, or list of instances of
TensorShapeif the layer expects a list of inputs (one instance per input).
This is where the layer’s logic lives.
Note here that
tf.kerasis little bit different from
kerasAPI, you can pass support masking for layers as additional arguments. Whereas
compute_mask()method to support masking.
Input tensor, or dict/list/tuple of input tensors. The first positional
inputsargument is subject to special rules: -
inputsmust be explicitly passed. A layer cannot have zero
inputscannot be provided via the default value of a keyword argument.
NumPy array or Python scalar values in
inputsget cast as tensors.
Keras mask metadata is only collected from
Layers are built (
build(input_shape)method) using shape info from
input_speccompatibility is only checked against
Mixed precision input casting is only applied to
inputs. If a layer has tensor arguments in
**kwargs, their casting behavior in mixed precision should be handled manually.
The SavedModel input specification is generated using
Integration with various ecosystem packages like TFMOT, TFLite, TF.js, etc is only supported for
inputsand not for tensors in positional and keyword arguments.
*args – Additional positional arguments. May contain tensors, although this is not recommended, for the reasons above.
Additional keyword arguments. May contain tensors, although this is not recommended, for the reasons above. The following optional keyword arguments are reserved: -
training: Boolean scalar tensor of Python boolean indicating
callis meant for training or inference.
mask: Boolean input mask. If the layer’s
call()method takes a
maskargument, its default value will be set to the mask generated for
inputsby the previous layer (if
inputdid come from a layer that generated a corresponding mask, i.e. if it came from a Keras layer with masking support).
A tensor or list/tuple of tensors.
Computes the output shape of the layer.
If the layer has not been built, this method will call
buildon the layer. This assumes that the layer will later be used with inputs that match the input shape provided here.
input_shape – Shape tuple (tuple of integers) or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
An input shape tuple.
Returns the config of the layer.
A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.
The config of a layer does not include connectivity information, nor the layer class name. These are handled by
Network(one layer of abstraction above).
get_config()does not guarantee to return a fresh copy of dict every time it is called. The callers should make a copy of the returned dict if they want to modify it.