brainpy.Sequential#

class brainpy.Sequential(*modules_as_tuple, name=None, mode=None, **modules_as_dict)[source]#

A sequential input-output module.

Modules will be added to it in the order they are passed in the constructor. Alternatively, an dict of modules can be passed in. The update() method of Sequential accepts any input and forwards it to the first module it contains. It then “chains” outputs to inputs sequentially for each subsequent module, finally returning the output of the last module.

The value a Sequential provides over manually calling a sequence of modules is that it allows treating the whole container as a single module, such that performing a transformation on the Sequential applies to each of the modules it stores (which are each a registered submodule of the Sequential).

What’s the difference between a Sequential and a Container? A Container is exactly what it sounds like–a container to store DynamicalSystem s! On the other hand, the layers in a Sequential are connected in a cascading way.

Examples

>>> import brainpy as bp
>>> import brainpy.math as bm
>>>
>>> # composing ANN models
>>> l = bp.Sequential(bp.layers.Dense(100, 10),
>>>                   bm.relu,
>>>                   bp.layers.Dense(10, 2))
>>> l({}, bm.random.random((256, 100)))
>>>
>>> # Using Sequential with Dict. This is functionally the
>>> # same as the above code
>>> l = bp.Sequential(l1=bp.layers.Dense(100, 10),
>>>                   l2=bm.relu,
>>>                   l3=bp.layers.Dense(10, 2))
>>> l({}, bm.random.random((256, 100)))

Parameters

name (str) – The object name.
mode (Mode) – The object computing context/mode. Default is batching.

__init__(*modules_as_tuple, name=None, mode=None, **modules_as_dict)[source]#

Methods

`__init__`(*modules_as_tuple[, name, mode])
`clear_input`()	Clear inputs in the children classes.
`cpu`()	Move all variable into the CPU device.
`cuda`()	Move all variables into the GPU device.
`get_delay_data`(identifier, delay_step, *indices)	Get delay data according to the provided delay steps.
`load_state_dict`(state_dict[, warn])	Copy parameters and buffers from `state_dict` into this module and its descendants.
`load_states`(filename[, verbose])	Load the model states.
`nodes`([method, level, include_self])	Collect all children nodes.
`offline_fit`(target, fit_record)
`offline_init`()
`online_fit`(target, fit_record)
`online_init`()
`register_delay`(identifier, delay_step, ...)	Register delay variable.
`register_implicit_nodes`(*nodes[, node_cls])
`register_implicit_vars`(*variables, ...)
`reset`([batch_size])	Reset function which reset the whole variables in the model.
`reset_local_delays`([nodes])	Reset local delay variables.
`reset_state`([batch_size])	Reset function which reset the states in the model.
`save_states`(filename[, variables])	Save the model states.
`state_dict`()	Returns a dictionary containing a whole state of the module.
`to`(device)	Moves all variables into the given device.
`tpu`()	Move all variables into the TPU device.
`train_vars`([method, level, include_self])	The shortcut for retrieving all trainable variables.
`tree_flatten`()	Flattens the object as a PyTree.
`tree_unflatten`(aux, dynamic_values)	New in version 2.3.1.
`unique_name`([name, type_])	Get the unique name for this object.
`update`(s, x)	Update function of a sequential model.
`update_local_delays`([nodes])	Update local delay variables.
`vars`([method, level, include_self, ...])	Collect all variables in this node and the children nodes.

Attributes

`global_delay_data`	Global delay data, which stores the delay variables and corresponding delay targets.
`mode`	Mode of the model, which is useful to control the multiple behaviors of the model.
`name`	Name of the model.