nn.modules.ExpSynExodus
- class nn.modules.ExpSynExodus(*args, **kwargs)[source]
Bases:
rockpool.nn.modules.torch.lif_torch.LIFBaseTorch
Attributes overview
alias of TypeVar('T_destination', bound=
Mapping
[str
,torch.Tensor
])Class name of
self
This allows better BC support for
load_state_dict()
.The full name of this module (class plus module name)
The name of this module, or an empty string if
None
The shape of this module
(DEPRECATED) The output size of this module
The input size of this module
The output size of this module
If
True
, this module receives spiking input.If
True
, this module sends spiking output.Methods overview
__init__
(shape[, tau, noise_std, dt])Instantiate an exponential synapse module using the Exodus backend
add_module
(name, module)Adds a child module to the current module.
apply
(fn)Applies
fn
recursively to every submodule (as returned by.children()
) as well as self.as_graph
()Convert this module to a computational graph
attributes_named
(name)Search for attributes of this or submodules by time
bfloat16
()Casts all floating point parameters and buffers to
bfloat16
datatype.buffers
([recurse])Returns an iterator over module buffers.
children
()Returns an iterator over immediate children modules.
cpu
()Moves all model parameters and buffers to the CPU.
cuda
([device])Moves all model parameters and buffers to the GPU.
double
()Casts all floating point parameters and buffers to
double
datatype.eval
()Sets the module in evaluation mode.
evolve
(input_data[, record])Implement the Rockpool low-level evolution API
Set the extra representation of the module
float
()Casts all floating point parameters and buffers to
float
datatype.forward
(data)forward method for processing data through this layer Adds inputs to the synaptic states
from_torch
(obj[, retain_torch_api])Convert a torch module into a Rockpool
TorchModule
in-placeget_buffer
(target)Returns the buffer given by
target
if it exists, otherwise throws an error.Returns any extra state to include in the module's state_dict.
get_parameter
(target)Returns the parameter given by
target
if it exists, otherwise throws an error.get_submodule
(target)Returns the submodule given by
target
if it exists, otherwise throws an error.half
()Casts all floating point parameters and buffers to
half
datatype.json_to_param
(jparam)load
(fn)load_state_dict
(state_dict[, strict])Copies parameters and buffers from
state_dict
into this module and its descendants.merge
(a, b)modules
(*args, **kwargs)Return a dictionary of all sub-modules of this module
named_buffers
([prefix, recurse])Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules
([memo, prefix, remove_duplicate])Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters
([prefix, recurse])Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
param_to_json
(param)parameters
([family])Return a nested dictionary of module and submodule Parameters
register_backward_hook
(hook)Registers a backward hook on the module.
register_buffer
(name, tensor[, persistent])Adds a buffer to the module.
register_forward_hook
(hook)Registers a forward hook on the module.
Registers a forward pre-hook on the module.
Registers a backward hook on the module.
register_parameter
(name, param)Adds a parameter to the module.
requires_grad_
([requires_grad])Change if autograd should record operations on parameters in this module.
Reset all parameters in this module
Reset the state of this module
save
(fn)set_attributes
(new_attributes)Set the attributes and sub-module attributes from a dictionary
set_extra_state
(state)This function is called from
load_state_dict()
to handle any extra state found within thestate_dict
.See
torch.Tensor.share_memory_()
simulation_parameters
([family])Return a nested dictionary of module and submodule SimulationParameters
state
([family])Return a nested dictionary of module and submodule States
state_dict
([destination, prefix, keep_vars])Returns a dictionary containing a whole state of the module.
timed
([output_num, dt, add_events])Convert this module to a
TimedModule
to
(*args, **kwargs)Moves and/or casts the parameters and buffers.
to_empty
(*, device)Moves the parameters and buffers to the specified device without copying storage.
to_json
()to_torch
([use_torch_call])Convert the module to use the torch.nn.Module API
train
([mode])Sets the module in training mode.
type
(dst_type)Casts all parameters and buffers to
dst_type
.xpu
([device])Moves all model parameters and buffers to the XPU.
zero_grad
([set_to_none])Sets gradients of all model parameters to zero.
- T_destination
alias of TypeVar(‘T_destination’, bound=
Mapping
[str
,torch.Tensor
])
- __init__(shape: tuple, tau: Union[float, rockpool.parameters.ParameterBase] = 0.05, noise_std: Union[float, rockpool.parameters.ParameterBase] = 0.0, dt: float = 0.001, *args, **kwargs)[source]
Instantiate an exponential synapse module using the Exodus backend
Uses the Exodus accelerated CUDA module to implement an exponential synapse. A CUDA device is required to instantiate this module.
The output of evolving this module is the synaptic currents.
Warning
Exodus does not support noise injection.
Examples
Instantitate an exponential synapse module with 2 synapses.
>>> mod = LIFExodus(2)
Specify the synaptic time constants, as well as time-step
dt
.>>> mod = LIFExodus(2, tau_syn = 10e-3, dt = 10e-3)
Specify multiple synaptic time constants.
>>> mod = LIFExodus(2, tau_syn = [10e-3, 20e-3])
Pass the model and data to the same cuda device, since it is required to use CUDA on this module.
>>> data = torch.ones((1, 10, 4)) >>> device = 'cuda: 1' >>> mod.to(device) >>> data = data.to(device) >>> output = mod(data)
- Parameters
shape (tuple) – The shape of this module
tau_syn (float) – An optional array with concrete initialisation data for the synaptic time constants. If not provided, 50ms will be used by default.
dt (float) – Time step in seconds. Default: 1 ms.
- _abc_impl = <_abc_data object>
- _apply(fn)
- _auto_batch(data: torch.Tensor, states: Tuple = (), target_shapes: Optional[Tuple] = None) Tuple[torch.Tensor, Tuple[torch.Tensor]]
Automatically replicate states over batches and verify input dimensions
- Usage:
>>> data, (state0, state1, state2) = self._auto_batch(data, (self.state0, self.state1, self.state2))
This will verify that
data
has the correct final dimension (i.e.self.size_in
). Ifdata
has only two dimensions(T, Nin)
, then it will be augmented to(1, T, Nin)
. The individual states will be replicated out from shape(a, b, c, ...)
to(n_batches, a, b, c, ...)
and returned.
- Parameters
data (torch.Tensor) – Input data tensor. Either
(batches, T, Nin)
or(T, Nin)
states (Tuple) – Tuple of state variables. Each will be replicated out over batches by prepending a batch dimension
- Returns
(torch.Tensor, Tuple[torch.Tensor]) data, states
- _call_impl(*input, **kwargs)
- _force_set_attributes
(bool) If
True
, do not sanity-check attributes when setting.
- _get_all_leak_params()
Calculate and return all decay parameters, depending on leak mode
- _get_attribute_family(type_name: str, family: Optional[Union[Tuple, List, str]] = None) dict
Search for attributes of this module and submodules that match a given family
This method can be used to conveniently get all weights for a network; or all time constants; or any other family of parameters. Parameter families are defined simply by a string:
"weights"
for weights;"taus"
for time constants, etc. These strings are arbitrary, but if you follow the conventions then future developers will thank you (that includes you in six month’s time).- Parameters
type_name (str) – The class of parameters to search for. Must be one of
["Parameter", "SimulationParameter", "State"]
or another future subclass ofParameterBase
family (Union[str, Tuple[str]]) – A string or list or tuple of strings, that define one or more attribute families to search for
- Returns
A nested dictionary of attributes that match the provided
type_name
andfamily
- Return type
dict
- _get_attribute_registry() Tuple[Dict, Dict]
Return or initialise the attribute registry for this module
- Returns
registered_attributes, registered_modules
- Return type
(tuple)
- _get_backward_hooks()
Returns the backward hooks for use in the call function. It returns two lists, one with the full backward hooks and one with the non-full backward hooks.
- _get_name()
- _has_registered_attribute(name: str) bool
Check if the module has a registered attribute
- Parameters
name (str) – The name of the attribute to check
- Returns
True
if the attributename
is in the attribute registry,False
otherwise.- Return type
bool
- _in_Module_init
(bool) If exists and
True
, indicates that the module is in the__init__
chain.
- _is_full_backward_hook: Optional[bool]
- _load_from_state_dict(state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs)
Copies parameters and buffers from
state_dict
into only this module, but not its descendants. This is called on every submodule inload_state_dict()
. Metadata saved for this module in inputstate_dict
is provided aslocal_metadata
. For state dicts without metadata,local_metadata
is empty. Subclasses can achieve class-specific backward compatible loading using the version number atlocal_metadata.get("version", None)
.Note
state_dict
is not the same object as the inputstate_dict
toload_state_dict()
. So it can be modified.- Parameters
state_dict (dict) – a dict containing parameters and persistent buffers.
prefix (str) – the prefix for parameters and buffers used in this module
local_metadata (dict) – a dict containing the metadata for this module. See
strict (bool) – whether to strictly enforce that the keys in
state_dict
withprefix
match the names of parameters and buffers in this modulemissing_keys (list of str) – if
strict=True
, add missing keys to this listunexpected_keys (list of str) – if
strict=True
, add unexpected keys to this listerror_msgs (list of str) – error messages should be added to this list, and will be reported together in
load_state_dict()
- _maybe_warn_non_full_backward_hook(inputs, result, grad_fn)
- _name: Optional[str]
Name of this module, if assigned
- _named_members(get_members_fn, prefix='', recurse=True)
Helper method for yielding various names + members of modules.
- _register_attribute(name: str, val: rockpool.parameters.ParameterBase)
Record an attribute in the attribute registry
- Parameters
name (str) – The name of the attribute to register
val (ParameterBase) – The
ParameterBase
subclass object to register. e.g.Parameter
,SimulationParameter
orState
.
- _register_load_state_dict_pre_hook(hook, with_module=False)
These hooks will be called with arguments:
state_dict
,prefix
,local_metadata
,strict
,missing_keys
,unexpected_keys
,error_msgs
, before loadingstate_dict
intoself
. These arguments are exactly the same as those of_load_from_state_dict
.If
with_module
isTrue
, then the first argument to the hook is an instance of the module.- Parameters
hook (Callable) – Callable hook that will be invoked before loading the state dict.
with_module (bool, optional) – Whether or not to pass the module instance to the hook as the first parameter.
- _register_module(name: str, mod)
Add a submodule to the module registry
- Parameters
name (str) – The name of the submodule, extracted from the assigned attribute name
mod (TorchModule) – The submodule to register
- Raises
ValueError – If the assigned submodule is not a
TorchModule
- _register_state_dict_hook(hook)
These hooks will be called with arguments:
self
,state_dict
,prefix
,local_metadata
, after thestate_dict
ofself
is set. Note that only parameters and buffers ofself
or its children are guaranteed to exist instate_dict
. The hooks may modifystate_dict
inplace or return a new one.
- _replicate_for_data_parallel()
- _reset_attribute(name: str) rockpool.nn.modules.module.ModuleBase
Reset an attribute to its initialisation value
- Parameters
name (str) – The name of the attribute to reset
- Returns
For compatibility with the functional API
- Return type
self (
Module
)
- _save_to_state_dict(destination, prefix, keep_vars)
Saves module state to
destination
dictionary, containing a state of the module, but not its descendants. This is called on every submodule instate_dict()
.In rare cases, subclasses can achieve class-specific behavior by overriding this method with custom logic.
- Parameters
destination (dict) – a dict where state will be stored
prefix (str) – the prefix for parameters and buffers used in this module
- _set_leak_param(name, value)
Set the value of a named decay parameter, depending on leak mode
- _shape
The shape of this module
- _slow_forward(*input, **kwargs)
- _spiking_input: bool
Whether this module receives spiking input
- _spiking_output: bool
Whether this module produces spiking output
- _submodulenames: List[str]
Registry of sub-module names
- _version: int = 1
- _wrap_recorded_state(recorded_dict: dict, t_start: float) Dict[str, rockpool.timeseries.TimeSeries]
Convert a recorded dictionary to a
TimeSeries
representationThis method is optional, and is provided to make the
timed()
conversion to aTimedModule
work better. You should override this method in your customModule
, to wrap each element of your recorded state dictionary as aTimeSeries
- Parameters
state_dict (dict) – A recorded state dictionary as returned by
evolve()
t_start (float) – The initial time of the recorded state, to use as the starting point of the time series
- Returns
The mapped recorded state dictionary, wrapped as
TimeSeries
objects- Return type
Dict[str, TimeSeries]
- add_module(name: str, module: Optional[torch.nn.modules.module.Module]) None
Adds a child module to the current module.
The module can be accessed as an attribute using the given name.
- Parameters
name (string) – name of the child module. The child module can be accessed from this module using the given name
module (Module) – child module to be added to the module.
- alpha: P_tensor
(Tensor) Membrane decay factor
(Nout,)
or()
- apply(fn: Callable[[torch.nn.modules.module.Module], None]) torch.nn.modules.module.T
Applies
fn
recursively to every submodule (as returned by.children()
) as well as self. Typical use includes initializing the parameters of a model (see also nn-init-doc).- Parameters
fn (
Module
-> None) – function to be applied to each submodule- Returns
self
- Return type
Example:
>>> @torch.no_grad() >>> def init_weights(m): >>> print(m) >>> if type(m) == nn.Linear: >>> m.weight.fill_(1.0) >>> print(m.weight) >>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2)) >>> net.apply(init_weights) Linear(in_features=2, out_features=2, bias=True) Parameter containing: tensor([[ 1., 1.], [ 1., 1.]]) Linear(in_features=2, out_features=2, bias=True) Parameter containing: tensor([[ 1., 1.], [ 1., 1.]]) Sequential( (0): Linear(in_features=2, out_features=2, bias=True) (1): Linear(in_features=2, out_features=2, bias=True) ) Sequential( (0): Linear(in_features=2, out_features=2, bias=True) (1): Linear(in_features=2, out_features=2, bias=True) )
- as_graph() rockpool.graph.graph_base.GraphModuleBase
Convert this module to a computational graph
- Returns
The computational graph corresponding to this module
- Return type
- Raises
NotImplementedError – If
as_graph()
is not implemented for this subclass
- attributes_named(name: Union[Tuple[str], List[str], str]) dict
Search for attributes of this or submodules by time
- Parameters
name (Union[str, Tuple[str]) – The name of the attribute to search for
- Returns
A nested dictionary of attributes that match
name
- Return type
dict
- beta: P_tensor
(Tensor) Synaptic decay factor
(Nin,)
or()
- bfloat16() torch.nn.modules.module.T
Casts all floating point parameters and buffers to
bfloat16
datatype.Note
This method modifies the module in-place.
- Returns
self
- Return type
- bias: P_tensor
(Tensor) Neuron biases
(Nout,)
or()
- buffers(recurse: bool = True) Iterator[torch.Tensor]
Returns an iterator over module buffers.
- Parameters
recurse (bool) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.
- Yields
torch.Tensor – module buffer
Example:
>>> for buf in model.buffers(): >>> print(type(buf), buf.size()) <class 'torch.Tensor'> (20L,) <class 'torch.Tensor'> (20L, 1L, 5L, 5L)
- children() Iterator[torch.nn.modules.module.Module]
Returns an iterator over immediate children modules.
- Yields
Module – a child module
- property class_name: str
Class name of
self
- Type
str
- cpu() torch.nn.modules.module.T
Moves all model parameters and buffers to the CPU.
Note
This method modifies the module in-place.
- Returns
self
- Return type
- cuda(device: Optional[Union[int, torch.device]] = None) torch.nn.modules.module.T
Moves all model parameters and buffers to the GPU.
This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.
Note
This method modifies the module in-place.
- Parameters
device (int, optional) – if specified, all parameters will be copied to that device
- Returns
self
- Return type
- dash_mem: P_tensor
(Tensor) membrane bitshift in xylo
(Nout,)
or()
- dash_syn: P_tensor
(Tensor) synaptic bitshift in xylo
(Nout,)
or()
- double() torch.nn.modules.module.T
Casts all floating point parameters and buffers to
double
datatype.Note
This method modifies the module in-place.
- Returns
self
- Return type
- dt: P_float
(float) Euler simulator time-step in seconds
- dump_patches: bool = False
This allows better BC support for
load_state_dict()
. Instate_dict()
, the version number will be saved as in the attribute_metadata
of the returned state dict, and thus pickled._metadata
is a dictionary with keys that follow the naming convention of state dict. See_load_from_state_dict
on how to use this information in loading.If new parameters/buffers are added/removed from a module, this number shall be bumped, and the module’s
_load_from_state_dict
method can compare the version number and do appropriate changes if the state dict is from before the change.
- eval() torch.nn.modules.module.T
Sets the module in evaluation mode.
This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g.
Dropout
,BatchNorm
, etc.This is equivalent with
self.train(False)
.See locally-disable-grad-doc for a comparison between
eval()
and several similar mechanisms that may be confused with it.- Returns
self
- Return type
- evolve(input_data: torch.Tensor, record: bool = False) Tuple[Any, Any, Any]
Implement the Rockpool low-level evolution API
evolve()
is provided byTorchModule
to connect the Rockpool low-level API to the Torch API (i.e.forward()
etc.). You should not overrideevolve()
if usingTorchModule
directly, but should implement the Torch API to perform evaluation of the module.evolve()
will automatically set the_record
flag according to the input argument toevolve()
. You can use this within yourforward()
method, and should build a dictionary_record_dict
. This will be returned automatically fromevolve()
, if requested.- Parameters
input_data – This might be a numpy array or Torch tensor, containing the input data to evolve over
record (bool) – Iff
True
, return a dictionary of state variables asrecord_dict
, containing the time series of those state variables over evolution. Default:False
, do not record state during evolution
- Returns
- (output_data, new_states, record_dict)
output_data
is the output from theTorchModule
, probably as a torchTensor
.new_states
is a dictionary containing the updated state for this module, post evolution. If therecord
argument isTrue
,record_dict
is a dictionary containing the recorded state variables for this and all submodules, recorded over evolution.
- Return type
(array, dict, dict)
- extra_repr() str
Set the extra representation of the module
To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.
- float() torch.nn.modules.module.T
Casts all floating point parameters and buffers to
float
datatype.Note
This method modifies the module in-place.
- Returns
self
- Return type
- forward(data: torch.Tensor) torch.Tensor [source]
forward method for processing data through this layer Adds inputs to the synaptic states
- Parameters
data (torch.Tensor) – Data takes the shape of (batch, time_steps, n_synapses)
- Returns
Out of spikes with the shape (batch, time_steps, n_synapses)
- Return type
torch.Tensor
- classmethod from_torch(obj: torch.nn.modules.module.Module, retain_torch_api: bool = False) None
Convert a torch module into a Rockpool
TorchModule
in-place- Parameters
obj (torch.nn.Module) – Torch module to convert to a Rockpool
retain_torch_api (bool) – If
True
, calling the resulting module will use the Torch API. Default:False
, convert the module to the Rockpool low-level API for__call__()
.
- property full_name: str
The full name of this module (class plus module name)
- Type
str
- get_buffer(target: str) torch.Tensor
Returns the buffer given by
target
if it exists, otherwise throws an error.See the docstring for
get_submodule
for a more detailed explanation of this method’s functionality as well as how to correctly specifytarget
.- Parameters
target – The fully-qualified string name of the buffer to look for. (See
get_submodule
for how to specify a fully-qualified string.)- Returns
The buffer referenced by
target
- Return type
torch.Tensor
- Raises
AttributeError – If the target string references an invalid path or resolves to something that is not a buffer
- get_extra_state() Any
Returns any extra state to include in the module’s state_dict. Implement this and a corresponding
set_extra_state()
for your module if you need to store extra state. This function is called when building the module’sstate_dict()
.Note that extra state should be pickleable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.
- Returns
Any extra state to store in the module’s state_dict
- Return type
object
- get_parameter(target: str) torch.nn.parameter.Parameter
Returns the parameter given by
target
if it exists, otherwise throws an error.See the docstring for
get_submodule
for a more detailed explanation of this method’s functionality as well as how to correctly specifytarget
.- Parameters
target – The fully-qualified string name of the Parameter to look for. (See
get_submodule
for how to specify a fully-qualified string.)- Returns
The Parameter referenced by
target
- Return type
torch.nn.Parameter
- Raises
AttributeError – If the target string references an invalid path or resolves to something that is not an
nn.Parameter
- get_submodule(target: str) torch.nn.modules.module.Module
Returns the submodule given by
target
if it exists, otherwise throws an error.For example, let’s say you have an
nn.Module
A
that looks like this:(The diagram shows an
nn.Module
A
.A
has a nested submodulenet_b
, which itself has two submodulesnet_c
andlinear
.net_c
then has a submoduleconv
.)To check whether or not we have the
linear
submodule, we would callget_submodule("net_b.linear")
. To check whether we have theconv
submodule, we would callget_submodule("net_b.net_c.conv")
.The runtime of
get_submodule
is bounded by the degree of module nesting intarget
. A query againstnamed_modules
achieves the same result, but it is O(N) in the number of transitive modules. So, for a simple check to see if some submodule exists,get_submodule
should always be used.- Parameters
target – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
- Returns
The submodule referenced by
target
- Return type
torch.nn.Module
- Raises
AttributeError – If the target string references an invalid path or resolves to something that is not an
nn.Module
- half() torch.nn.modules.module.T
Casts all floating point parameters and buffers to
half
datatype.Note
This method modifies the module in-place.
- Returns
self
- Return type
- isyn: P_tensor
(Tensor) Synaptic currents
(Nin,)
- json_to_param(jparam)
- leak_mode
(str) The mode by which leaks are determined for this module.
- learning_window: P_tensor
(float) Learning window cutoff for surrogate gradient function
- load(fn)
- load_state_dict(state_dict: OrderedDict[str, Tensor], strict: bool = True)
Copies parameters and buffers from
state_dict
into this module and its descendants. Ifstrict
isTrue
, then the keys ofstate_dict
must exactly match the keys returned by this module’sstate_dict()
function.- Parameters
state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in
state_dict
match the keys returned by this module’sstate_dict()
function. Default:True
- Returns
missing_keys is a list of str containing the missing keys
unexpected_keys is a list of str containing the unexpected keys
- Return type
NamedTuple
withmissing_keys
andunexpected_keys
fields
Note
If a parameter or buffer is registered as
None
and its corresponding key exists instate_dict
,load_state_dict()
will raise aRuntimeError
.
- max_spikes_per_dt: P_float
(float) Maximum number of events that can be produced in each time-step
- merge(a, b)
- modules(*args, **kwargs)
Return a dictionary of all sub-modules of this module
- Returns
A dictionary containing all sub-modules. Each item will be named with the sub-module name.
- Return type
dict
- n_synapses: P_int
(int) Number of input synapses per neuron
- property name: str
The name of this module, or an empty string if
None
- Type
str
- named_buffers(prefix: str = '', recurse: bool = True) Iterator[Tuple[str, torch.Tensor]]
Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
- Parameters
prefix (str) – prefix to prepend to all buffer names.
recurse (bool) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.
- Yields
(string, torch.Tensor) – Tuple containing the name and buffer
Example:
>>> for name, buf in self.named_buffers(): >>> if name in ['running_var']: >>> print(buf.size())
- named_children() Iterator[Tuple[str, torch.nn.modules.module.Module]]
Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
- Yields
(string, Module) – Tuple containing a name and child module
Example:
>>> for name, module in model.named_children(): >>> if name in ['conv4', 'conv5']: >>> print(module)
- named_modules(memo: Optional[Set[torch.nn.modules.module.Module]] = None, prefix: str = '', remove_duplicate: bool = True)
Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
- Parameters
memo – a memo to store the set of modules already added to the result
prefix – a prefix that will be added to the name of the module
remove_duplicate – whether to remove the duplicated module instances in the result
not (or) –
- Yields
(string, Module) – Tuple of name and module
Note
Duplicate modules are returned only once. In the following example,
l
will be returned only once.Example:
>>> l = nn.Linear(2, 2) >>> net = nn.Sequential(l, l) >>> for idx, m in enumerate(net.named_modules()): print(idx, '->', m) 0 -> ('', Sequential( (0): Linear(in_features=2, out_features=2, bias=True) (1): Linear(in_features=2, out_features=2, bias=True) )) 1 -> ('0', Linear(in_features=2, out_features=2, bias=True))
- named_parameters(prefix: str = '', recurse: bool = True) Iterator[Tuple[str, torch.nn.parameter.Parameter]]
Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
- Parameters
prefix (str) – prefix to prepend to all parameter names.
recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
- Yields
(string, Parameter) – Tuple containing the name and parameter
Example:
>>> for name, param in self.named_parameters(): >>> if name in ['bias']: >>> print(param.size())
- noise_std: P_float
(float) Noise std.dev. injected onto the membrane of each neuron during evolution
- param_to_json(param)
- parameters(family: Optional[Union[Tuple, List, str]] = None) Dict
Return a nested dictionary of module and submodule Parameters
Use this method to inspect the Parameters from this and all submodules. The optional argument
family
allows you to search for Parameters in a particular family — for example"weights"
for all weights of this module and nested submodules.Although the
family
argument is an arbitrary string, reasonable choises are"weights"
,"taus"
for time constants,"biases"
for biases…Examples
Obtain a dictionary of all Parameters for this module (including submodules):
>>> mod.parameters() dict{ ... }
Obtain a dictionary of Parameters from a particular family:
>>> mod.parameters("weights") dict{ ... }
- Parameters
family (str) – The family of Parameters to search for. Default:
None
; return all parameters.- Returns
A nested dictionary of Parameters of this module and all submodules
- Return type
dict
- register_backward_hook(hook: Callable[[torch.nn.modules.module.Module, Union[Tuple[torch.Tensor, ...], torch.Tensor], Union[Tuple[torch.Tensor, ...], torch.Tensor]], Union[None, torch.Tensor]]) torch.utils.hooks.RemovableHandle
Registers a backward hook on the module.
This function is deprecated in favor of
register_full_backward_hook()
and the behavior of this function will change in future versions.- Returns
a handle that can be used to remove the added hook by calling
handle.remove()
- Return type
torch.utils.hooks.RemovableHandle
- register_buffer(name: str, tensor: torch.Tensor, persistent: bool = True, *args, **kwargs) None
Adds a buffer to the module.
This is typically used to register a buffer that should not to be considered a model parameter. For example, BatchNorm’s
running_mean
is not a parameter, but is part of the module’s state. Buffers, by default, are persistent and will be saved alongside parameters. This behavior can be changed by settingpersistent
toFalse
. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’sstate_dict
.Buffers can be accessed as attributes using given names.
- Parameters
name (string) – name of the buffer. The buffer can be accessed from this module using the given name
tensor (Tensor or None) – buffer to be registered. If
None
, then operations that run on buffers, such ascuda
, are ignored. IfNone
, the buffer is not included in the module’sstate_dict
.persistent (bool) – whether the buffer is part of this module’s
state_dict
.
Example:
>>> self.register_buffer('running_mean', torch.zeros(num_features))
- register_forward_hook(hook: Callable[[...], None]) torch.utils.hooks.RemovableHandle
Registers a forward hook on the module.
The hook will be called every time after
forward()
has computed an output. It should have the following signature:hook(module, input, output) -> None or modified output
The input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the
forward
. The hook can modify the output. It can modify the input inplace but it will not have effect on forward since this is called afterforward()
is called.- Returns
a handle that can be used to remove the added hook by calling
handle.remove()
- Return type
torch.utils.hooks.RemovableHandle
- register_forward_pre_hook(hook: Callable[[...], None]) torch.utils.hooks.RemovableHandle
Registers a forward pre-hook on the module.
The hook will be called every time before
forward()
is invoked. It should have the following signature:hook(module, input) -> None or modified input
The input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the
forward
. The hook can modify the input. User can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned(unless that value is already a tuple).- Returns
a handle that can be used to remove the added hook by calling
handle.remove()
- Return type
torch.utils.hooks.RemovableHandle
- register_full_backward_hook(hook: Callable[[torch.nn.modules.module.Module, Union[Tuple[torch.Tensor, ...], torch.Tensor], Union[Tuple[torch.Tensor, ...], torch.Tensor]], Union[None, torch.Tensor]]) torch.utils.hooks.RemovableHandle
Registers a backward hook on the module.
The hook will be called every time the gradients with respect to module inputs are computed. The hook should have the following signature:
hook(module, grad_input, grad_output) -> tuple(Tensor) or None
The
grad_input
andgrad_output
are tuples that contain the gradients with respect to the inputs and outputs respectively. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the input that will be used in place ofgrad_input
in subsequent computations.grad_input
will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries ingrad_input
andgrad_output
will beNone
for all non-Tensor arguments.For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.
Warning
Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.
- Returns
a handle that can be used to remove the added hook by calling
handle.remove()
- Return type
torch.utils.hooks.RemovableHandle
- register_parameter(name: str, param: torch.nn.parameter.Parameter) None
Adds a parameter to the module.
The parameter can be accessed as an attribute using given name.
- Parameters
name (string) – name of the parameter. The parameter can be accessed from this module using the given name
param (Parameter or None) – parameter to be added to the module. If
None
, then operations that run on parameters, such ascuda
, are ignored. IfNone
, the parameter is not included in the module’sstate_dict
.
- requires_grad_(requires_grad: bool = True) torch.nn.modules.module.T
Change if autograd should record operations on parameters in this module.
This method sets the parameters’
requires_grad
attributes in-place.This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).
See locally-disable-grad-doc for a comparison between
requires_grad_()
and several similar mechanisms that may be confused with it.- Parameters
requires_grad (bool) – whether autograd should record operations on parameters in this module. Default:
True
.- Returns
self
- Return type
- reset_parameters()
Reset all parameters in this module
- Returns
The updated module is returned for compatibility with the functional API
- Return type
- reset_state() rockpool.nn.modules.module.ModuleBase
Reset the state of this module
- Returns
The updated module is returned for compatibility with the functional API
- Return type
- save(fn)
- set_attributes(new_attributes: dict) rockpool.nn.modules.module.ModuleBase
Set the attributes and sub-module attributes from a dictionary
This method can be used with the dictionary returned from module evolution to set the new state of the module. It can also be used to set multiple parameters of a module and submodules.
Examples
Use the functional API to evolve, obtain new states, and set those states:
>>> _, new_state, _ = mod(input) >>> mod = mod.set_attributes(new_state)
Obtain a parameter dictionary, modify it, then set the parameters back:
>>> params = mod.parameters() >>> params['w_input'] *= 0. >>> mod.set_attributes(params)
- Parameters
new_attributes (dict) – A nested dictionary containing parameters of this module and sub-modules.
- set_extra_state(state: Any)
This function is called from
load_state_dict()
to handle any extra state found within thestate_dict
. Implement this function and a correspondingget_extra_state()
for your module if you need to store extra state within itsstate_dict
.- Parameters
state (dict) – Extra state from the
state_dict
- property shape: tuple
The shape of this module
- Type
tuple
See
torch.Tensor.share_memory_()
- simulation_parameters(family: Optional[Union[Tuple, List, str]] = None) Dict
Return a nested dictionary of module and submodule SimulationParameters
Use this method to inspect the SimulationParameters from this and all submodules. The optional argument
family
allows you to search for SimulationParameters in a particular family.Examples
Obtain a dictionary of all SimulationParameters for this module (including submodules):
>>> mod.simulation_parameters() dict{ ... }
- Parameters
family (str) – The family of SimulationParameters to search for. Default:
None
; return all SimulationParameter attributes.- Returns
A nested dictionary of SimulationParameters of this module and all submodules
- Return type
dict
- property size: int
(DEPRECATED) The output size of this module
- Type
int
- property size_in: int
The input size of this module
- Type
int
- property size_out: int
The output size of this module
- Type
int
- spike_generation_fn: P_Callable
(Callable) Spike generation function with surrograte gradient
- spikes: P_tensor
(Tensor) Spikes
(Nin,)
- property spiking_input: bool
If
True
, this module receives spiking input. IfFalse
, this module expects continuous input.- Type
bool
- property spiking_output
If
True
, this module sends spiking output. IfFalse
, this module sends continuous output.- Type
bool
- state(family: Optional[Union[Tuple, List, str]] = None) Dict
Return a nested dictionary of module and submodule States
Use this method to inspect the States from this and all submodules. The optional argument
family
allows you to search for States in a particular family.Examples
Obtain a dictionary of all States for this module (including submodules):
>>> mod.state() dict{ ... }
- Parameters
family (str) – The family of States to search for. Default:
None
; return all State attributes.- Returns
A nested dictionary of States of this module and all submodules
- Return type
dict
- state_dict(destination=None, prefix='', keep_vars=False)
Returns a dictionary containing a whole state of the module.
Both parameters and persistent buffers (e.g. running averages) are included. Keys are corresponding parameter and buffer names. Parameters and buffers set to
None
are not included.- Returns
a dictionary containing a whole state of the module
- Return type
dict
Example:
>>> module.state_dict().keys() ['bias', 'weight']
- tau_mem: P_tensor
(Tensor) Membrane time constants
(Nout,)
or()
- tau_syn: P_tensor
(Tensor) Synaptic time constants
(Nin,)
or()
- threshold: P_tensor
(Tensor) Firing threshold for each neuron
(Nout,)
- timed(output_num: int = 0, dt: Optional[float] = None, add_events: bool = False)
Convert this module to a
TimedModule
- Parameters
output_num (int) – Specify which output of the module to take, if the module returns multiple output series. Default:
0
, take the first (or only) output.dt (float) – Used to provide a time-step for this module, if the module does not already have one. If
self
already defines a time-step, thenself.dt
will be used. Default:None
add_events (bool) – Iff
True
, theTimedModule
will add events occurring on a single timestep on input and output. Default:False
, don’t add time steps.
Returns:
TimedModule
: A timed module that wraps this module
- to(*args, **kwargs)
Moves and/or casts the parameters and buffers.
This can be called as
- to(device=None, dtype=None, non_blocking=False)
- to(dtype, non_blocking=False)
- to(tensor, non_blocking=False)
- to(memory_format=torch.channels_last)
Its signature is similar to
torch.Tensor.to()
, but only accepts floating point or complexdtype
s. In addition, this method will only cast the floating point or complex parameters and buffers todtype
(if given). The integral parameters and buffers will be moveddevice
, if that is given, but with dtypes unchanged. Whennon_blocking
is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.See below for examples.
Note
This method modifies the module in-place.
- Parameters
device (
torch.device
) – the desired device of the parameters and buffers in this moduledtype (
torch.dtype
) – the desired floating point or complex dtype of the parameters and buffers in this moduletensor (torch.Tensor) – Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module
memory_format (
torch.memory_format
) – the desired memory format for 4D parameters and buffers in this module (keyword only argument)
- Returns
self
- Return type
Examples:
>>> linear = nn.Linear(2, 2) >>> linear.weight Parameter containing: tensor([[ 0.1913, -0.3420], [-0.5113, -0.2325]]) >>> linear.to(torch.double) Linear(in_features=2, out_features=2, bias=True) >>> linear.weight Parameter containing: tensor([[ 0.1913, -0.3420], [-0.5113, -0.2325]], dtype=torch.float64) >>> gpu1 = torch.device("cuda:1") >>> linear.to(gpu1, dtype=torch.half, non_blocking=True) Linear(in_features=2, out_features=2, bias=True) >>> linear.weight Parameter containing: tensor([[ 0.1914, -0.3420], [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1') >>> cpu = torch.device("cpu") >>> linear.to(cpu) Linear(in_features=2, out_features=2, bias=True) >>> linear.weight Parameter containing: tensor([[ 0.1914, -0.3420], [-0.5112, -0.2324]], dtype=torch.float16) >>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble) >>> linear.weight Parameter containing: tensor([[ 0.3741+0.j, 0.2382+0.j], [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128) >>> linear(torch.ones(3, 2, dtype=torch.cdouble)) tensor([[0.6122+0.j, 0.1150+0.j], [0.6122+0.j, 0.1150+0.j], [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)
- to_empty(*, device: Union[str, torch.device]) torch.nn.modules.module.T
Moves the parameters and buffers to the specified device without copying storage.
- Parameters
device (
torch.device
) – The desired device of the parameters and buffers in this module.- Returns
self
- Return type
- to_json()
- to_torch(use_torch_call: bool = True)
Convert the module to use the torch.nn.Module API
This method exposes the torch API for
.__call__()
,.parameters()
and.__repr__()
methods, recursively. By default,.__call__()
is only replaced on the top-level module. This is to ensure that the nested.forward()
methods do not break.- Parameters
use_torch_call (bool) – Use the torch-type
__call__()
method for this object- Returns
The converted object
- train(mode: bool = True) torch.nn.modules.module.T
Sets the module in training mode.
This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g.
Dropout
,BatchNorm
, etc.- Parameters
mode (bool) – whether to set training mode (
True
) or evaluation mode (False
). Default:True
.- Returns
self
- Return type
- training: bool
- type(dst_type: Union[torch.dtype, str]) torch.nn.modules.module.T
Casts all parameters and buffers to
dst_type
.Note
This method modifies the module in-place.
- Parameters
dst_type (type or string) – the desired type
- Returns
self
- Return type
- vmem: P_tensor
(Tensor) Membrane potentials
(Nout,)
- w_rec: P_tensor
(Tensor) Recurrent weights
(Nout, Nin)
- xpu(device: Optional[Union[int, torch.device]] = None) torch.nn.modules.module.T
Moves all model parameters and buffers to the XPU.
This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.
Note
This method modifies the module in-place.
- Parameters
device (int, optional) – if specified, all parameters will be copied to that device
- Returns
self
- Return type
- zero_grad(set_to_none: bool = False) None
Sets gradients of all model parameters to zero. See similar function under
torch.optim.Optimizer
for more context.- Parameters
set_to_none (bool) – instead of setting to zero, set the grads to None. See
torch.optim.Optimizer.zero_grad()
for details.