param

Contents

param#

class brainstate.nn.init.param(parameter, sizes, batch_size=None, allow_none=True, allow_scalar=True)#

Initialize parameters.

Parameters:

  • parameter (Callable | Array | ndarray | bool | number | bool | int | float | complex | Quantity | State) – The initialization of the parameter. - If it is None, the created parameter will be None. - If it is a callable function \(f\), the f(size) will be returned. - If it is an instance of init.Initializer`, the f(size) will be returned. - If it is a tensor, then this function check whether tensor.shape is equal to the given size.

  • sizes (int | Sequence[int]) – The shape of the parameter.

  • batch_size (int | None) – The batch size.

  • allow_none (bool) – Whether allow the parameter is None.

  • allow_scalar (bool) – Whether allow the parameter is a scalar value.

Returns:

param – The initialized parameter.

Return type:

ArrayType, float, int, bool, None

See also

noise, state

Contents