asteroid.masknn.base module

class asteroid.masknn.base.BaseUNet(encoders, decoders, *, output_layer=None)

Bases: sphinx.ext.autodoc.importer._MockObject

Base class for u-nets with skip connections between encoders and decoders.

(For u-nets without skip connections, simply use a nn.Sequential.)

Parameters:

• encoders (List[torch.nn.Module] of length N) – List of encoders
• decoders (List[torch.nn.Module] of length N - 1) – List of decoders
• output_layer (Optional[torch.nn.Module], optional) – Layer after last decoder.

forward(x)

class asteroid.masknn.base.BaseDCUMaskNet(encoders, decoders, output_layer=None, mask_bound='tanh', **kwargs)

Bases: asteroid.masknn.base.BaseUNet

Base class for DCU-style mask nets. Used for DCUMaskNet and DCCRMaskNet.

The preferred way to instantiate this class is to use the default_architecture() classmethod.

Parameters:

• encoders (List[torch.nn.Module]) – List of encoders
• decoders (List[torch.nn.Module]) – List of decoders
• output_layer (Optional[torch.nn.Module], optional) – Layer after last decoder, before mask application.
• mask_bound (Optional[str], optional) – Type of mask bound to use, as defined in [1]. Valid values are “tanh” (“BDT mask”), “sigmoid” (“BDSS mask”), None (unbounded mask).

References

• [1] : “Phase-aware Speech Enhancement with Deep Complex U-Net”,

Hyeong-Seok Choi et al. https://arxiv.org/abs/1903.03107

classmethod default_architecture(architecture: str, n_src=1, **kwargs)

Create a masknet instance from a predefined, named architecture.

Parameters:

• architecture (str) – Name of predefined architecture. Valid values are dependent on the concrete subclass of BaseDCUMaskNet.
• n_src (int, optional) – Number of sources
• kwargs (optional) – Passed to __init__.

forward(x)

fix_input_dims(x)

Overwrite this in subclasses to implement input dimension checks.

fix_output_dims(y, x)

Overwrite this in subclasses to implement output dimension checks. y is the output and x was the input (passed to use the shape).