Dynamic

class brainpy.Dynamic(size, keep_size=False, sharding=None, name=None, mode=None, method='exp_auto')

Base class to model dynamics.

There are several essential attributes:

• size: the geometry of the neuron group. For example, (10, ) denotes a line of neurons, (10, 10) denotes a neuron group aligned in a 2D space, (10, 15, 4) denotes a 3-dimensional neuron group.

• num: the flattened number of neurons in the group. For example, size=(10, ) => num=10, size=(10, 10) => num=100, size=(10, 15, 4) => num=600.

Parameters:

• size (TypeVar(Shape, int, Tuple[int, ...])) – The neuron group geometry.

• name (Optional[str]) – The name of the dynamic system.

• keep_size (bool) – Whether keep the geometry information.

• mode (Optional[Mode]) – The computing mode.

clear_input(*args, **kwargs)

Empty function of clearing inputs.

init_param(param, shape=None, sharding=None)

Initialize parameters.

If sharding is provided and param is array, this function will partition the parameter across the default device mesh.

See device_mesh() for the mesh setting.

init_variable(var_data, batch_or_mode, shape=None, sharding=None)

Initialize variables.

If sharding is provided and var_data is array, this function will partition the variable across the default device mesh.

See device_mesh() for the mesh setting.

update(*args, **kwargs)

The function to specify the updating rule.

property varshape

The shape of variables in the neuron group.