deeperwin.model.MLP

class deeperwin.model.MLP(*args, **kwargs)[source]

Bases: haiku._src.module.Module

__init__(output_sizes: Iterable[int], config: Optional[deeperwin.configuration.MLPConfig] = None, output_bias: bool = True, linear_out: bool = False, residual=False, name: Optional[str] = None)[source]

Initializes the current module with the given name.

Subclasses should call this constructor before creating other modules or variables such that those modules are named correctly.

Parameters: name – An optional string name for the class. Must be a valid Python identifier. If name is not provided then the class name for the current instance is converted to lower_snake_case and used instead.

Methods

__init__(output_sizes[, config, ...])

Initializes the current module with the given name.