Inner Hair Cell Models

Inner hair cell (IHC) models for envelope extraction and physiological simulation.

IHCEnvelope

class torch_amt.IHCEnvelope(fs, cutoff=None, order=1, method='dau1996', learnable=False, dtype=torch.float32)

Bases: Module

Inner hair cell envelope extraction.

Models the signal transduction of inner hair cells (IHC) by extracting the envelope of the basilar membrane motion through half-wave rectification followed by low-pass filtering.

Algorithm Overview

The IHC envelope extraction consists of two main stages:

1. Half-wave rectification: Models the directional sensitivity of stereocilia deflection. Only positive deflections generate response:

   \[x_{\text{rect}}(t) = \max(x(t), 0)\]

2. Butterworth low-pass filtering: Models the loss of phase-locking at high frequencies in auditory nerve fibers:

   \[y(t) = \text{IIR}(x_{\text{rect}}(t), b, a)\]

   where \(b, a\) are Butterworth filter coefficients.

For the breebaart2001 method, the filter is applied iteratively 5 times, reducing the effective cutoff frequency from 2000 Hz to approximately 770 Hz.

param fs:

Sampling rate in Hz.

type fs:

float

param cutoff:

Cutoff frequency for the low-pass filter in Hz. If None, uses method-specific default. Default: None.

type cutoff:

float | None

param order:

Order of the Butterworth filter. Typically 1 for most methods. Default: 1.

type order:

int

param method:

Preset configuration for the extraction method:

• 'dau1996': 1st order Butterworth at 1000 Hz (1 iteration).

• 'breebaart2001': 1st order Butterworth at 2000 Hz (5 iterations, effective ~770 Hz cutoff).

• 'king2019': 1st order Butterworth at 1500 Hz (1 iteration).

• 'lindemann': 1st order Butterworth at 800 Hz (1 iteration).

Default: 'dau1996'.

type method:

str

param learnable:

If True, filter coefficients b and a become learnable parameters. If False, they are registered as buffers. Default: False.

type learnable:

bool

param dtype:

Data type for internal computations. Default: torch.float32.

type dtype:

dtype

fs

Sampling rate in Hz.

Type:

float

method

Preset method name.

Type:

str

cutoff

Cutoff frequency in Hz (after preset selection).

Type:

float

order

Filter order (always 1 for implemented presets).

Type:

int

iterations

Number of times the filter is applied (5 for breebaart2001, 1 otherwise).

Type:

int

b

Numerator coefficients of IIR filter. Shape: (order+1,).

Type:

torch.Tensor or nn.Parameter

a

Denominator coefficients of IIR filter. Shape: (order+1,).

Type:

torch.Tensor or nn.Parameter

learnable

Whether filter coefficients are learnable.

Type:

bool

dtype

Data type for computations.

Type:

torch.dtype

Shape

-----

- Input

where \(B\) is batch size, \(F\) is frequency channels, \(T\) is time samples.

Type:

\((B, F, T)\) or \((F, T)\)

- Output

Type:

Same shape as input.

Notes

Preset Differences

Method	Cutoff (Hz)	Order	Iterations	Effective Cutoff
dau1996	1000	1	1	1000 Hz
breebaart2001	2000	1	5	~770 Hz
king2019	1500	1	1	1500 Hz
lindemann	800	1	1	800 Hz

Successive Filtering (breebaart2001)

The breebaart2001 method applies a 2000 Hz 1st-order lowpass filter 5 times in series. This is equivalent to a higher-order filter with reduced cutoff. The effective -3dB cutoff frequency is approximately 770 Hz, as documented in Breebaart’s thesis (2001, p. 94).

See also

IHCPaulick2024

Physiologically detailed IHC transduction (CASP model)

GammatoneFilterbank

Gammatone peripheral filtering (typical input source)

DRNLFilterbank

Dual-resonance non-linear filterbank (alternative input)

AdaptLoop

Auditory nerve adaptation (downstream processing)

modfilterbank

Modulation filterbank (downstream processing)

headphonefilter

Free-field to headphone transfer function

middleearfilter

Middle ear transfer function

Examples

Basic usage with default preset:

>>> import torch
>>> from torch_amt.common.ihc import IHCEnvelope
>>> ihc = IHCEnvelope(fs=44100, method='dau1996')
>>> x = torch.randn(1, 31, 44100)  # Gammatone filterbank output
>>> y = ihc(x)
>>> print(y.shape)
torch.Size([1, 31, 44100])

Comparing different presets:

>>> # Dau 1996 (1000 Hz)
>>> ihc_dau = IHCEnvelope(fs=16000, method='dau1996')
>>> # Breebaart 2001 (effective ~770 Hz)
>>> ihc_bree = IHCEnvelope(fs=16000, method='breebaart2001')
>>> # Lindemann 1986 (800 Hz)
>>> ihc_lind = IHCEnvelope(fs=16000, method='lindemann')
>>>
>>> x = torch.randn(2, 31, 16000)
>>> y_dau = ihc_dau(x)
>>> y_bree = ihc_bree(x)
>>> y_lind = ihc_lind(x)

Learnable IHC parameters for model training:

>>> ihc_learn = IHCEnvelope(fs=44100, method='dau1996', learnable=True)
>>> print(f"Learnable params: {sum(p.numel() for p in ihc_learn.parameters())}")
Learnable params: 4
>>> # Coefficients b, a can be optimized during training
>>> optimizer = torch.optim.Adam(ihc_learn.parameters(), lr=1e-3)

References

[1]

T. Dau, D. Püschel, and A. Kohlrausch, “A quantitative model of the ‘effective’ signal processing in the auditory system. I. Model structure,” J. Acoust. Soc. Am., vol. 99, no. 6, pp. 3615-3622, 1996.

[2]

J. Breebaart, S. van de Par, and A. Kohlrausch, “Binaural processing model based on contralateral inhibition. I. Model structure,” J. Acoust. Soc. Am., vol. 110, no. 2, pp. 1074-1088, 2001.

[3]

W. Lindemann, “Extension of a binaural cross-correlation model by contralateral inhibition. I. Simulation of lateralization for stationary signals,” J. Acoust. Soc. Am., vol. 80, no. 6, pp. 1608-1622, 1986.

[4]

A. J. King, J. W. H. Schnupp, and A. R. D. Thornton, “Localization of sounds in the median sagittal plane with and without spectral cues,” J. Acoust. Soc. Am., vol. 145, no. 3, pp. 1437-1447, 2019.

__init__(fs, cutoff=None, order=1, method='dau1996', learnable=False, dtype=torch.float32)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• fs (float)

• cutoff (float | None)

• order (int)

• method (str)

• learnable (bool)

• dtype (dtype)

forward(x)

Process the input signal through IHC envelope extraction.

Applies half-wave rectification followed by Butterworth low-pass filtering. For the breebaart2001 method, the filter is applied 5 times iteratively.

Parameters:

x (Tensor) – Input signal (typically Gammatone or DRNL filterbank output). Shape: \((B, F, T)\) or \((F, T)\) where \(B\) is batch size, \(F\) is frequency channels, \(T\) is time samples.

Returns:

Envelope signal. Same shape as input.

Return type:

Tensor

Notes

The computation follows these steps:

1. Half-wave rectification: \(x_{\text{rect}} = \max(x, 0)\)

2. Butterworth low-pass filtering (applied iterations times)

The filter coefficients b and a are automatically moved to the same device as the input tensor.

extra_repr()

Extra representation string for module printing.

Returns:

String containing key module parameters.

Return type:

str

T_destination = ~T_destination

add_module(name, module)

Add a child module to the current module.

The module can be accessed as an attribute using the given name.

Args:

name (str): 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.

Parameters:

• name (str)

• module (Module | None)

Return type:

None

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

Typical use includes initializing the parameters of a model (see also torch.nn.init).

Args:

fn (Module -> None): function to be applied to each submodule

Returns:

Module: self

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) is 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.]], requires_grad=True)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)

Parameters:

fn (Callable[[Module], None])

Return type:

Self

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

buffers(recurse=True)

Return an iterator over module buffers.

Args:

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:

>>> # xdoctest: +SKIP("undefined vars")
>>> for buf in model.buffers():
>>>     print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

Parameters:

recurse (bool)

Return type:

Iterator[Tensor]

call_super_init: bool = False

children()

Return an iterator over immediate children modules.

Return type:

Iterator[Module]

Yields:

Module: a child module

compile(*args, **kwargs)

Compile this Module’s forward using torch.compile().

This Module’s __call__ method is compiled and all arguments are passed as-is to torch.compile().

See torch.compile() for details on the arguments for this function.

Return type:

None

cpu()

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

cuda(device=None)

Move all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing the optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Args:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

double()

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

dump_patches: bool = False

eval()

Set the module in evaluation mode.

This has an effect only on certain modules. See the documentation of particular modules for details of their behaviors in training/evaluation mode, i.e. whether they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See Locally disabling gradient computation for a comparison between .eval() and several similar mechanisms that may be confused with it.

Return type:

Self

Returns:

Module: self

float()

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Args:

target: The fully-qualified string name of the buffer

to look for. (See get_submodule for how to specify a fully-qualified string.)

Returns:

torch.Tensor: The buffer referenced by target

Raises:

AttributeError: If the target string references an invalid

path or resolves to something that is not a buffer

Parameters:

target (str)

Return type:

Tensor

get_extra_state()

Return 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’s state_dict().

Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.

Return type:

Any

Returns:

object: Any extra state to store in the module’s state_dict

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Args:

target: The fully-qualified string name of the Parameter

to look for. (See get_submodule for how to specify a fully-qualified string.)

Returns:

torch.nn.Parameter: The Parameter referenced by target

Raises:

AttributeError: If the target string references an invalid

path or resolves to something that is not an nn.Parameter

Parameters:

target (str)

Return type:

Parameter

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A which has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To check whether or not we have the linear submodule, we would call get_submodule("net_b.linear"). To check whether we have the conv submodule, we would call get_submodule("net_b.net_c.conv").

The runtime of get_submodule is bounded by the degree of module nesting in target. A query against named_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.

Args:

target: The fully-qualified string name of the submodule

to look for. (See above example for how to specify a fully-qualified string.)

Returns:

torch.nn.Module: The submodule referenced by target

Raises:

AttributeError: If at any point along the path resulting from

the target string the (sub)path resolves to a non-existent attribute name or an object that is not an instance of nn.Module.

Parameters:

target (str)

Return type:

Module

half()

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

ipu(device=None)

Move all model parameters and buffers to the IPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing the optimizer if the module will live on IPU while being optimized.

Note

This method modifies the module in-place.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

load_state_dict(state_dict, strict=True, assign=False)

Copy parameters and buffers from state_dict into this module and its descendants.

If strict is True, then the keys of state_dict must exactly match the keys returned by this module’s state_dict() function.

Warning

If assign is True the optimizer must be created after the call to load_state_dict unless get_swap_module_params_on_conversion() is True.

Args:

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’s state_dict() function. Default: True

assign (bool, optional): When set to False, the properties of the tensors

in the current module are preserved whereas setting it to True preserves properties of the Tensors in the state dict. The only exception is the requires_grad field of Parameter for which the value from the module is preserved. Default: False

Returns:

NamedTuple with missing_keys and unexpected_keys fields:

• missing_keys is a list of str containing any keys that are expected

  by this module but missing from the provided state_dict.

• unexpected_keys is a list of str containing the keys that are not

  expected by this module but present in the provided state_dict.

Note:

If a parameter or buffer is registered as None and its corresponding key exists in state_dict, load_state_dict() will raise a RuntimeError.

Parameters:

• state_dict (Mapping[str, Any])

• strict (bool)

• assign (bool)

modules()

Return an iterator over all modules in the network.

Return type:

Iterator[Module]

Yields:

Module: a module in the network

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.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 -> Linear(in_features=2, out_features=2, bias=True)

mtia(device=None)

Move all model parameters and buffers to the MTIA.

This also makes associated parameters and buffers different objects. So it should be called before constructing the optimizer if the module will live on MTIA while being optimized.

Note

This method modifies the module in-place.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

named_buffers(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

Args:

prefix (str): prefix to prepend to all buffer names. recurse (bool, optional): if True, then yields buffers of this module

and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.

remove_duplicate (bool, optional): whether to remove the duplicated buffers in the result. Defaults to True.

Yields:

(str, torch.Tensor): Tuple containing the name and buffer

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, buf in self.named_buffers():
>>>     if name in ['running_var']:
>>>         print(buf.size())

Parameters:

• prefix (str)

• recurse (bool)

• remove_duplicate (bool)

Return type:

Iterator[tuple[str, Tensor]]

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

Return type:

Iterator[tuple[str, Module]]

Yields:

(str, Module): Tuple containing a name and child module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, module in model.named_children():
>>>     if name in ['conv4', 'conv5']:
>>>         print(module)

named_modules(memo=None, prefix='', remove_duplicate=True)

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

Args:

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

or not

Yields:

(str, 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))

Parameters:

• memo (set[Module] | None)

• prefix (str)

• remove_duplicate (bool)

named_parameters(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

Args:

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.

remove_duplicate (bool, optional): whether to remove the duplicated

parameters in the result. Defaults to True.

Yields:

(str, Parameter): Tuple containing the name and parameter

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, param in self.named_parameters():
>>>     if name in ['bias']:
>>>         print(param.size())

Parameters:

• prefix (str)

• recurse (bool)

• remove_duplicate (bool)

Return type:

Iterator[tuple[str, Parameter]]

parameters(recurse=True)

Return an iterator over module parameters.

This is typically passed to an optimizer.

Args:

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:

Parameter: module parameter

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

Parameters:

recurse (bool)

Return type:

Iterator[Parameter]

register_backward_hook(hook)

Register 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:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

hook (Callable[[Module, tuple[Tensor, ...] | Tensor, tuple[Tensor, ...] | Tensor], None | tuple[Tensor, ...] | Tensor])

Return type:

RemovableHandle

register_buffer(name, tensor, persistent=True)

Add a buffer to the module.

This is typically used to register a buffer that should not 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 setting persistent to False. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’s state_dict.

Buffers can be accessed as attributes using given names.

Args:

name (str): 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 as cuda, are ignored. If None, the buffer is not included in the module’s state_dict.

persistent (bool): whether the buffer is part of this module’s

state_dict.

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> self.register_buffer('running_mean', torch.zeros(num_features))

Parameters:

• name (str)

• tensor (Tensor | None)

• persistent (bool)

Return type:

None

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)

Register a forward hook on the module.

The hook will be called every time after forward() has computed an output.

If with_kwargs is False or not specified, 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 after forward() is called. The hook should have the following signature:

hook(module, args, output) -> None or modified output

If with_kwargs is True, the forward hook will be passed the kwargs given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:

hook(module, args, kwargs, output) -> None or modified output

Args:

hook (Callable): The user defined hook to be registered. prepend (bool): If True, the provided hook will be fired

before all existing forward hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.Module. Note that global forward hooks registered with register_module_forward_hook() will fire before all hooks registered by this method. Default: False

with_kwargs (bool): If True, the hook will be passed the

kwargs given to the forward function. Default: False

always_call (bool): If True the hook will be run regardless of

whether an exception is raised while calling the Module. Default: False

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[TypeVar(T, bound= Module), tuple[Any, ...], Any], Any | None] | Callable[[TypeVar(T, bound= Module), tuple[Any, ...], dict[str, Any], Any], Any | None])

• prepend (bool)

• with_kwargs (bool)

• always_call (bool)

Return type:

RemovableHandle

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)

Register a forward pre-hook on the module.

The hook will be called every time before forward() is invoked.

If with_kwargs is false or not specified, 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). The hook should have the following signature:

hook(module, args) -> None or modified input

If with_kwargs is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:

hook(module, args, kwargs) -> None or a tuple of modified input and kwargs

Args:

hook (Callable): The user defined hook to be registered. prepend (bool): If true, the provided hook will be fired before

all existing forward_pre hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.Module. Note that global forward_pre hooks registered with register_module_forward_pre_hook() will fire before all hooks registered by this method. Default: False

with_kwargs (bool): If true, the hook will be passed the kwargs

given to the forward function. Default: False

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[TypeVar(T, bound= Module), tuple[Any, ...]], Any | None] | Callable[[TypeVar(T, bound= Module), tuple[Any, ...], dict[str, Any]], tuple[Any, dict[str, Any]] | None])

• prepend (bool)

• with_kwargs (bool)

Return type:

RemovableHandle

register_full_backward_hook(hook, prepend=False)

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, and its firing rules are as follows:

1. Ordinarily, the hook fires when the gradients are computed with respect to the module inputs.

2. If none of the module inputs require gradients, the hook will fire when the gradients are computed with respect to module outputs.

3. If none of the module outputs require gradients, then the hooks will not fire.

The hook should have the following signature:

hook(module, grad_input, grad_output) -> tuple(Tensor) or None

The grad_input and grad_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 of grad_input in subsequent computations. grad_input will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries in grad_input and grad_output will be None 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.

Args:

hook (Callable): The user-defined hook to be registered. prepend (bool): If true, the provided hook will be fired before

all existing backward hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[Module, tuple[Tensor, ...] | Tensor, tuple[Tensor, ...] | Tensor], None | tuple[Tensor, ...] | Tensor])

• prepend (bool)

Return type:

RemovableHandle

register_full_backward_pre_hook(hook, prepend=False)

Register a backward pre-hook on the module.

The hook will be called every time the gradients for the module are computed. The hook should have the following signature:

hook(module, grad_output) -> tuple[Tensor, ...], Tensor or None

The grad_output is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place of grad_output in subsequent computations. Entries in grad_output will be None 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 inplace is not allowed when using backward hooks and will raise an error.

Args:

hook (Callable): The user-defined hook to be registered. prepend (bool): If true, the provided hook will be fired before

all existing backward_pre hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.Module. Note that global backward_pre hooks registered with register_module_full_backward_pre_hook() will fire before all hooks registered by this method.

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[Module, tuple[Tensor, ...] | Tensor], None | tuple[Tensor, ...] | Tensor])

• prepend (bool)

Return type:

RemovableHandle

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module’s load_state_dict() is called.

It should have the following signature::

hook(module, incompatible_keys) -> None

The module argument is the current module that this hook is registered on, and the incompatible_keys argument is a NamedTuple consisting of attributes missing_keys and unexpected_keys. missing_keys is a list of str containing the missing keys and unexpected_keys is a list of str containing the unexpected keys.

The given incompatible_keys can be modified inplace if needed.

Note that the checks performed when calling load_state_dict() with strict=True are affected by modifications the hook makes to missing_keys or unexpected_keys, as expected. Additions to either set of keys will result in an error being thrown when strict=True, and clearing out both missing and unexpected keys will avoid an error.

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module’s load_state_dict() is called.

It should have the following signature::

hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -> None # noqa: B950

Arguments:

hook (Callable): Callable hook that will be invoked before

loading the state dict.

register_module(name, module)

Alias for add_module().

Parameters:

• name (str)

• module (Module | None)

Return type:

None

register_parameter(name, param)

Add a parameter to the module.

The parameter can be accessed as an attribute using given name.

Args:

name (str): 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 as cuda, are ignored. If None, the parameter is not included in the module’s state_dict.

Parameters:

• name (str)

• param (Parameter | None)

Return type:

None

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::

hook(module, state_dict, prefix, local_metadata) -> None

The registered hooks can modify the state_dict inplace.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

It should have the following signature::

hook(module, prefix, keep_vars) -> None

The registered hooks can be used to perform pre-processing before the state_dict call is made.

requires_grad_(requires_grad=True)

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 disabling gradient computation for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Args:

requires_grad (bool): whether autograd should record operations on

parameters in this module. Default: True.

Returns:

Module: self

Parameters:

requires_grad (bool)

Return type:

Self

set_extra_state(state)

Set extra state contained in the loaded state_dict.

This function is called from load_state_dict() to handle any extra state found within the state_dict. Implement this function and a corresponding get_extra_state() for your module if you need to store extra state within its state_dict.

Args:

state (dict): Extra state from the state_dict

Parameters:

state (Any)

Return type:

None

set_submodule(target, module, strict=False)

Set the submodule given by target if it exists, otherwise throw an error.

Note

If strict is set to False (default), the method will replace an existing submodule or create a new submodule if the parent module exists. If strict is set to True, the method will only attempt to replace an existing submodule and throw an error if the submodule does not exist.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(3, 3, 3)
        )
        (linear): Linear(3, 3)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To override the Conv2d with a new submodule Linear, you could call set_submodule("net_b.net_c.conv", nn.Linear(1, 1)) where strict could be True or False

To add a new submodule Conv2d to the existing net_b module, you would call set_submodule("net_b.conv", nn.Conv2d(1, 1, 1)).

In the above if you set strict=True and call set_submodule("net_b.conv", nn.Conv2d(1, 1, 1), strict=True), an AttributeError will be raised because net_b does not have a submodule named conv.

Args:

target: The fully-qualified string name of the submodule

to look for. (See above example for how to specify a fully-qualified string.)

module: The module to set the submodule to. strict: If False, the method will replace an existing submodule

or create a new submodule if the parent module exists. If True, the method will only attempt to replace an existing submodule and throw an error if the submodule doesn’t already exist.

Raises:

ValueError: If the target string is empty or if module is not an instance of nn.Module. AttributeError: If at any point along the path resulting from

the target string the (sub)path resolves to a non-existent attribute name or an object that is not an instance of nn.Module.

Parameters:

• target (str)

• module (Module)

• strict (bool)

Return type:

None

share_memory()

See torch.Tensor.share_memory_().

Return type:

Self

state_dict(*args, destination=None, prefix='', keep_vars=False)

Overloads:

• self, destination (T_destination), prefix (str), keep_vars (bool) → T_destination

• self, prefix (str), keep_vars (bool) → dict[str, Any]

Return a dictionary containing references to the 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.

Note

The returned object is a shallow copy. It contains references to the module’s parameters and buffers.

Warning

Currently state_dict() also accepts positional arguments for destination, prefix and keep_vars in order. However, this is being deprecated and keyword arguments will be enforced in future releases.

Warning

Please avoid the use of argument destination as it is not designed for end-users.

Args:

destination (dict, optional): If provided, the state of module will

be updated into the dict and the same object is returned. Otherwise, an OrderedDict will be created and returned. Default: None.

prefix (str, optional): a prefix added to parameter and buffer

names to compose the keys in state_dict. Default: ''.

keep_vars (bool, optional): by default the Tensor s

returned in the state dict are detached from autograd. If it’s set to True, detaching will not be performed. Default: False.

Returns:

dict:

a dictionary containing a whole state of the module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> module.state_dict().keys()
['bias', 'weight']

to(*args, **kwargs)

Overloads:

• self, device (DeviceLikeType | None), dtype (dtype | None), non_blocking (bool) → Self

• self, dtype (dtype), non_blocking (bool) → Self

• self, tensor (Tensor), non_blocking (bool) → Self

Move and/or cast 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 complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_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.

Args:

device (torch.device): the desired device of the parameters

and buffers in this module

dtype (torch.dtype): the desired floating point or complex dtype of

the parameters and buffers in this module

tensor (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:

Module: self

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> 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)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> 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, recurse=True)

Move the parameters and buffers to the specified device without copying storage.

Args:

device (torch.device): The desired device of the parameters

and buffers in this module.

recurse (bool): Whether parameters and buffers of submodules should

be recursively moved to the specified device.

Returns:

Module: self

Parameters:

• device (str | device | int | None)

• recurse (bool)

Return type:

Self

train(mode=True)

Set the module in training mode.

This has an effect only on certain modules. See the documentation of particular modules for details of their behaviors in training/evaluation mode, i.e., whether they are affected, e.g. Dropout, BatchNorm, etc.

Args:

mode (bool): whether to set training mode (True) or evaluation

mode (False). Default: True.

Returns:

Module: self

Parameters:

mode (bool)

Return type:

Self

type(dst_type)

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

Args:

dst_type (type or string): the desired type

Returns:

Module: self

Parameters:

dst_type (dtype | str)

Return type:

Self

xpu(device=None)

Move 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.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

zero_grad(set_to_none=True)

Reset gradients of all model parameters.

See similar function under torch.optim.Optimizer for more context.

Args:

set_to_none (bool): instead of setting to zero, set the grads to None.

See torch.optim.Optimizer.zero_grad() for details.

Parameters:

set_to_none (bool)

Return type:

None

training: bool

IHCPaulick2024

class torch_amt.IHCPaulick2024(fs, learnable=False, dtype=torch.float32)

Bases: Module

Physiologically detailed inner hair cell transduction for CASP model.

Converts basilar membrane velocity to receptor potential using a detailed physiological model of inner hair cell (IHC) mechano-electrical transduction (MET) and electrical circuit dynamics.

Algorithm Overview

The IHC transduction process consists of four main stages:

1. Stereocilia displacement scaling: Convert BM velocity to displacement.

   \[d_{\text{ster}}(t) = \alpha \cdot v_{\text{BM}}(t)\]

   where \(\alpha = 10^{-105/20}\) (db2mag scaling factor).

2. MET channel conductance: Double-exponential sigmoid function fitted to physiological data.

   \[G(d) = \frac{G_{\max}}{1 + \exp\left(\frac{x_0 - d}{s_1}\right) \left(1 + \exp\left(\frac{x_0 - d}{s_0}\right)\right)}\]

   where \(G_{\max} = 30\) nS, \(x_0 = 20\) nm (bias), \(s_0 = 16\) nm (fast sensitivity), \(s_1 = 35\) nm (slow sensitivity).

3. Pre-charging: Simulate 50 ms of activity with fixed conductance to reach steady-state resting potential \(V_{\text{rest}} = -57.03\) mV before processing the signal.

4. Electrical circuit ODE: Forward Euler integration of membrane potential.

   \[C_m \frac{dV}{dt} = I_{\text{MET}} + I_{K,f} + I_{K,s}\]

   where:

   • \(I_{\text{MET}} = -G(t) (V - E_P)\) (MET current)

   • \(I_{K,f} = -G_{K,f} (V - E_{K,f})\) (fast K+ current)

   • \(I_{K,s} = -G_{K,s} (V - E_{K,s})\) (slow K+ current)

param fs:

Sampling rate in Hz.

type fs:

float

param learnable:

If True, all 13 physiological parameters become trainable nn.Parameter objects. If False, they are registered as buffers. Default: False.

type learnable:

bool

param dtype:

Data type for computations. Recommended: torch.float32 for device compatibility (MPS, CUDA), torch.float64 for maximum numerical precision in ODE integration. Default: torch.float32.

type dtype:

dtype

fs

Sampling rate in Hz.

Type:

float

learnable

Whether parameters are trainable.

Type:

bool

dtype

Data type for computations (default: float32).

Type:

torch.dtype

scaling_factor

Stereocilia displacement scaling (\(10^{-105/20}\)). Units: dimensionless.

Type:

torch.Tensor or nn.Parameter

Gmet_max

Maximum MET channel conductance (30 nS). Units: Siemens (S).

Type:

torch.Tensor or nn.Parameter

x0

Displacement bias (20 nm). Units: meters (m).

Type:

torch.Tensor or nn.Parameter

s0

Fast sensitivity parameter (16 nm). Units: meters (m).

Type:

torch.Tensor or nn.Parameter

s1

Slow sensitivity parameter (35 nm). Units: meters (m).

Type:

torch.Tensor or nn.Parameter

EP

Endocochlear potential (90 mV). Units: Volts (V).

Type:

torch.Tensor or nn.Parameter

Cm

Membrane capacitance (12.5 pF). Units: Farads (F).

Type:

torch.Tensor or nn.Parameter

Gkf

Fast K+ channel conductance (19.8 nS). Units: Siemens (S).

Type:

torch.Tensor or nn.Parameter

Gks

Slow K+ channel conductance (19.8 nS). Units: Siemens (S).

Type:

torch.Tensor or nn.Parameter

Ekf

Fast K+ reversal potential (-71 mV). Units: Volts (V).

Type:

torch.Tensor or nn.Parameter

Eks

Slow K+ reversal potential (-78 mV). Units: Volts (V).

Type:

torch.Tensor or nn.Parameter

V_rest

Resting potential (-57.03 mV). Units: Volts (V).

Type:

torch.Tensor or nn.Parameter

G_precharge

Pre-charge conductance (3.3514 nS). Units: Siemens (S).

Type:

torch.Tensor or nn.Parameter

precharge_duration

Duration of pre-charge simulation (50 ms). Units: seconds (s).

Type:

float

Shape

-----

- Input

where \(B\) is batch size, \(F\) is frequency channels (typically 50 for CASP), \(T\) is time samples.

Type:

\((B, F, T)\) or \((F, T)\)

- Output

Receptor potential in Volts, relative to pre-charge steady-state level.

Type:

Same shape as input.

Notes

Physiological Parameters

All parameters are derived from physiological measurements and modeling studies. The MET channel parameters (\(G_{\max}\), \(x_0\), \(s_0\), \(s_1\)) are fitted to match hair cell transduction data.

Pre-charging Mechanism

The 50 ms pre-charge simulates the steady-state condition of the IHC at rest. This ensures the membrane potential starts at a physiologically realistic resting state (\(V_{\text{rest}} = -57.03\) mV) rather than an arbitrary initial condition. The output voltage is computed relative to this pre-charge level to represent deviations from rest.

Numerical Stability

The ODE integration uses Forward Euler method with timestep \(\Delta t = 1/f_s\). Float64 precision is required to avoid accumulation of numerical errors over long signals. Using torch.float32 may lead to instability or divergence.

Computational Complexity

The computational cost is \(O(B \cdot F \cdot (T + T_{\text{pre}}))\) where \(T_{\text{pre}} = 0.05 \cdot f_s\) is the pre-charge duration. For \(f_s = 44100\) Hz, the pre-charge adds 2205 samples per batch x channel.

Due to the sequential nature of ODE integration (each timestep depends on the previous), this implementation is CPU-optimized. GPU execution may not provide significant speedup and could be slower due to kernel launch overhead.

Connection to DRNL

This IHC model is designed to work with the output of DRNLFilterbank, which provides basilar membrane velocity. The CASP pipeline is:

Audio → DRNLFilterbank → IHCPaulick2024 → AdaptLoop → Modulation

See also

IHCEnvelope

Classical IHC envelope extraction (simpler, faster)

DRNLFilterbank

Dual-resonance non-linear filterbank (typical input source)

AdaptLoop

Auditory nerve adaptation (downstream processing)

modfilterbank

Modulation filterbank (downstream processing)

Examples

Basic usage with DRNL velocity input:

>>> import torch
>>> from torch_amt.common.ihc import IHCPaulick2024
>>> ihc = IHCPaulick2024(fs=44100)
>>> vel = torch.randn(2, 50, 44100, dtype=torch.float64)  # BM velocity from DRNL
>>> V = ihc(vel)  # Receptor potential
>>> print(V.shape, V.dtype)
torch.Size([2, 50, 44100]) torch.float64

Batch processing with different batch sizes:

>>> ihc = IHCPaulick2024(fs=16000)
>>> # Single sample
>>> vel_single = torch.randn(1, 50, 16000, dtype=torch.float64)
>>> V_single = ihc(vel_single)
>>> # Large batch
>>> vel_batch = torch.randn(8, 50, 16000, dtype=torch.float64)
>>> V_batch = ihc(vel_batch)

Learnable physiological parameters for model fitting:

>>> ihc_learn = IHCPaulick2024(fs=44100, learnable=True)
>>> print(f"Learnable params: {sum(p.numel() for p in ihc_learn.parameters())}")
Learnable params: 13
>>> # All 13 physiological parameters can be optimized
>>> optimizer = torch.optim.Adam(ihc_learn.parameters(), lr=1e-5)
>>> # Note: May require constraints to ensure physiological plausibility

References

[1]

L. Paulick, H. Relaño-Iborra, and T. Dau, “The Computational Auditory Signal Processing and Perception Model (CASP): A Revised Version,” bioRxiv, 2024, doi: 10.1101/2024.02.02.578582.

[2]

T. Dau, B. Kollmeier, and A. Kohlrausch, “Modeling auditory processing of amplitude modulation. II. Spectral and temporal integration,” J. Acoust. Soc. Am., vol. 102, no. 5, pp. 2906-2919, 1997.

__init__(fs, learnable=False, dtype=torch.float32)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• fs (float)

• learnable (bool)

• dtype (dtype)

T_destination = ~T_destination

add_module(name, module)

Add a child module to the current module.

The module can be accessed as an attribute using the given name.

Args:

name (str): 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.

Parameters:

• name (str)

• module (Module | None)

Return type:

None

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

Typical use includes initializing the parameters of a model (see also torch.nn.init).

Args:

fn (Module -> None): function to be applied to each submodule

Returns:

Module: self

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) is 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.]], requires_grad=True)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)

Parameters:

fn (Callable[[Module], None])

Return type:

Self

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

buffers(recurse=True)

Return an iterator over module buffers.

Args:

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:

>>> # xdoctest: +SKIP("undefined vars")
>>> for buf in model.buffers():
>>>     print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

Parameters:

recurse (bool)

Return type:

Iterator[Tensor]

call_super_init: bool = False

children()

Return an iterator over immediate children modules.

Return type:

Iterator[Module]

Yields:

Module: a child module

compile(*args, **kwargs)

Compile this Module’s forward using torch.compile().

This Module’s __call__ method is compiled and all arguments are passed as-is to torch.compile().

See torch.compile() for details on the arguments for this function.

Return type:

None

cpu()

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

cuda(device=None)

Move all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing the optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Args:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

double()

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

dump_patches: bool = False

eval()

Set the module in evaluation mode.

This has an effect only on certain modules. See the documentation of particular modules for details of their behaviors in training/evaluation mode, i.e. whether they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See Locally disabling gradient computation for a comparison between .eval() and several similar mechanisms that may be confused with it.

Return type:

Self

Returns:

Module: self

float()

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Args:

target: The fully-qualified string name of the buffer

to look for. (See get_submodule for how to specify a fully-qualified string.)

Returns:

torch.Tensor: The buffer referenced by target

Raises:

AttributeError: If the target string references an invalid

path or resolves to something that is not a buffer

Parameters:

target (str)

Return type:

Tensor

get_extra_state()

Return 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’s state_dict().

Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.

Return type:

Any

Returns:

object: Any extra state to store in the module’s state_dict

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Args:

target: The fully-qualified string name of the Parameter

to look for. (See get_submodule for how to specify a fully-qualified string.)

Returns:

torch.nn.Parameter: The Parameter referenced by target

Raises:

AttributeError: If the target string references an invalid

path or resolves to something that is not an nn.Parameter

Parameters:

target (str)

Return type:

Parameter

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A which has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To check whether or not we have the linear submodule, we would call get_submodule("net_b.linear"). To check whether we have the conv submodule, we would call get_submodule("net_b.net_c.conv").

The runtime of get_submodule is bounded by the degree of module nesting in target. A query against named_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.

Args:

target: The fully-qualified string name of the submodule

to look for. (See above example for how to specify a fully-qualified string.)

Returns:

torch.nn.Module: The submodule referenced by target

Raises:

AttributeError: If at any point along the path resulting from

the target string the (sub)path resolves to a non-existent attribute name or an object that is not an instance of nn.Module.

Parameters:

target (str)

Return type:

Module

half()

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:

Module: self

Return type:

Self

ipu(device=None)

Move all model parameters and buffers to the IPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing the optimizer if the module will live on IPU while being optimized.

Note

This method modifies the module in-place.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

load_state_dict(state_dict, strict=True, assign=False)

Copy parameters and buffers from state_dict into this module and its descendants.

If strict is True, then the keys of state_dict must exactly match the keys returned by this module’s state_dict() function.

Warning

If assign is True the optimizer must be created after the call to load_state_dict unless get_swap_module_params_on_conversion() is True.

Args:

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’s state_dict() function. Default: True

assign (bool, optional): When set to False, the properties of the tensors

in the current module are preserved whereas setting it to True preserves properties of the Tensors in the state dict. The only exception is the requires_grad field of Parameter for which the value from the module is preserved. Default: False

Returns:

NamedTuple with missing_keys and unexpected_keys fields:

• missing_keys is a list of str containing any keys that are expected

  by this module but missing from the provided state_dict.

• unexpected_keys is a list of str containing the keys that are not

  expected by this module but present in the provided state_dict.

Note:

If a parameter or buffer is registered as None and its corresponding key exists in state_dict, load_state_dict() will raise a RuntimeError.

Parameters:

• state_dict (Mapping[str, Any])

• strict (bool)

• assign (bool)

modules()

Return an iterator over all modules in the network.

Return type:

Iterator[Module]

Yields:

Module: a module in the network

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.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 -> Linear(in_features=2, out_features=2, bias=True)

mtia(device=None)

Move all model parameters and buffers to the MTIA.

This also makes associated parameters and buffers different objects. So it should be called before constructing the optimizer if the module will live on MTIA while being optimized.

Note

This method modifies the module in-place.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

named_buffers(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

Args:

prefix (str): prefix to prepend to all buffer names. recurse (bool, optional): if True, then yields buffers of this module

and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.

remove_duplicate (bool, optional): whether to remove the duplicated buffers in the result. Defaults to True.

Yields:

(str, torch.Tensor): Tuple containing the name and buffer

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, buf in self.named_buffers():
>>>     if name in ['running_var']:
>>>         print(buf.size())

Parameters:

• prefix (str)

• recurse (bool)

• remove_duplicate (bool)

Return type:

Iterator[tuple[str, Tensor]]

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

Return type:

Iterator[tuple[str, Module]]

Yields:

(str, Module): Tuple containing a name and child module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, module in model.named_children():
>>>     if name in ['conv4', 'conv5']:
>>>         print(module)

named_modules(memo=None, prefix='', remove_duplicate=True)

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

Args:

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

or not

Yields:

(str, 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))

Parameters:

• memo (set[Module] | None)

• prefix (str)

• remove_duplicate (bool)

named_parameters(prefix='', recurse=True, remove_duplicate=True)

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

Args:

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.

remove_duplicate (bool, optional): whether to remove the duplicated

parameters in the result. Defaults to True.

Yields:

(str, Parameter): Tuple containing the name and parameter

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, param in self.named_parameters():
>>>     if name in ['bias']:
>>>         print(param.size())

Parameters:

• prefix (str)

• recurse (bool)

• remove_duplicate (bool)

Return type:

Iterator[tuple[str, Parameter]]

parameters(recurse=True)

Return an iterator over module parameters.

This is typically passed to an optimizer.

Args:

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:

Parameter: module parameter

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

Parameters:

recurse (bool)

Return type:

Iterator[Parameter]

register_backward_hook(hook)

Register 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:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

hook (Callable[[Module, tuple[Tensor, ...] | Tensor, tuple[Tensor, ...] | Tensor], None | tuple[Tensor, ...] | Tensor])

Return type:

RemovableHandle

register_buffer(name, tensor, persistent=True)

Add a buffer to the module.

This is typically used to register a buffer that should not 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 setting persistent to False. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’s state_dict.

Buffers can be accessed as attributes using given names.

Args:

name (str): 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 as cuda, are ignored. If None, the buffer is not included in the module’s state_dict.

persistent (bool): whether the buffer is part of this module’s

state_dict.

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> self.register_buffer('running_mean', torch.zeros(num_features))

Parameters:

• name (str)

• tensor (Tensor | None)

• persistent (bool)

Return type:

None

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)

Register a forward hook on the module.

The hook will be called every time after forward() has computed an output.

If with_kwargs is False or not specified, 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 after forward() is called. The hook should have the following signature:

hook(module, args, output) -> None or modified output

If with_kwargs is True, the forward hook will be passed the kwargs given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:

hook(module, args, kwargs, output) -> None or modified output

Args:

hook (Callable): The user defined hook to be registered. prepend (bool): If True, the provided hook will be fired

before all existing forward hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.Module. Note that global forward hooks registered with register_module_forward_hook() will fire before all hooks registered by this method. Default: False

with_kwargs (bool): If True, the hook will be passed the

kwargs given to the forward function. Default: False

always_call (bool): If True the hook will be run regardless of

whether an exception is raised while calling the Module. Default: False

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[TypeVar(T, bound= Module), tuple[Any, ...], Any], Any | None] | Callable[[TypeVar(T, bound= Module), tuple[Any, ...], dict[str, Any], Any], Any | None])

• prepend (bool)

• with_kwargs (bool)

• always_call (bool)

Return type:

RemovableHandle

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)

Register a forward pre-hook on the module.

The hook will be called every time before forward() is invoked.

If with_kwargs is false or not specified, 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). The hook should have the following signature:

hook(module, args) -> None or modified input

If with_kwargs is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:

hook(module, args, kwargs) -> None or a tuple of modified input and kwargs

Args:

hook (Callable): The user defined hook to be registered. prepend (bool): If true, the provided hook will be fired before

all existing forward_pre hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.Module. Note that global forward_pre hooks registered with register_module_forward_pre_hook() will fire before all hooks registered by this method. Default: False

with_kwargs (bool): If true, the hook will be passed the kwargs

given to the forward function. Default: False

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[TypeVar(T, bound= Module), tuple[Any, ...]], Any | None] | Callable[[TypeVar(T, bound= Module), tuple[Any, ...], dict[str, Any]], tuple[Any, dict[str, Any]] | None])

• prepend (bool)

• with_kwargs (bool)

Return type:

RemovableHandle

register_full_backward_hook(hook, prepend=False)

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, and its firing rules are as follows:

1. Ordinarily, the hook fires when the gradients are computed with respect to the module inputs.

2. If none of the module inputs require gradients, the hook will fire when the gradients are computed with respect to module outputs.

3. If none of the module outputs require gradients, then the hooks will not fire.

The hook should have the following signature:

hook(module, grad_input, grad_output) -> tuple(Tensor) or None

The grad_input and grad_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 of grad_input in subsequent computations. grad_input will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries in grad_input and grad_output will be None 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.

Args:

hook (Callable): The user-defined hook to be registered. prepend (bool): If true, the provided hook will be fired before

all existing backward hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[Module, tuple[Tensor, ...] | Tensor, tuple[Tensor, ...] | Tensor], None | tuple[Tensor, ...] | Tensor])

• prepend (bool)

Return type:

RemovableHandle

register_full_backward_pre_hook(hook, prepend=False)

Register a backward pre-hook on the module.

The hook will be called every time the gradients for the module are computed. The hook should have the following signature:

hook(module, grad_output) -> tuple[Tensor, ...], Tensor or None

The grad_output is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place of grad_output in subsequent computations. Entries in grad_output will be None 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 inplace is not allowed when using backward hooks and will raise an error.

Args:

hook (Callable): The user-defined hook to be registered. prepend (bool): If true, the provided hook will be fired before

all existing backward_pre hooks on this torch.nn.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.Module. Note that global backward_pre hooks registered with register_module_full_backward_pre_hook() will fire before all hooks registered by this method.

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

Parameters:

• hook (Callable[[Module, tuple[Tensor, ...] | Tensor], None | tuple[Tensor, ...] | Tensor])

• prepend (bool)

Return type:

RemovableHandle

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module’s load_state_dict() is called.

It should have the following signature::

hook(module, incompatible_keys) -> None

The module argument is the current module that this hook is registered on, and the incompatible_keys argument is a NamedTuple consisting of attributes missing_keys and unexpected_keys. missing_keys is a list of str containing the missing keys and unexpected_keys is a list of str containing the unexpected keys.

The given incompatible_keys can be modified inplace if needed.

Note that the checks performed when calling load_state_dict() with strict=True are affected by modifications the hook makes to missing_keys or unexpected_keys, as expected. Additions to either set of keys will result in an error being thrown when strict=True, and clearing out both missing and unexpected keys will avoid an error.

Returns:

torch.utils.hooks.RemovableHandle:

a handle that can be used to remove the added hook by calling handle.remove()

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module’s load_state_dict() is called.

It should have the following signature::

hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -> None # noqa: B950

Arguments:

hook (Callable): Callable hook that will be invoked before

loading the state dict.

register_module(name, module)

Alias for add_module().

Parameters:

• name (str)

• module (Module | None)

Return type:

None

register_parameter(name, param)

Add a parameter to the module.

The parameter can be accessed as an attribute using given name.

Args:

name (str): 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 as cuda, are ignored. If None, the parameter is not included in the module’s state_dict.

Parameters:

• name (str)

• param (Parameter | None)

Return type:

None

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

It should have the following signature::

hook(module, state_dict, prefix, local_metadata) -> None

The registered hooks can modify the state_dict inplace.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

It should have the following signature::

hook(module, prefix, keep_vars) -> None

The registered hooks can be used to perform pre-processing before the state_dict call is made.

requires_grad_(requires_grad=True)

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 disabling gradient computation for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Args:

requires_grad (bool): whether autograd should record operations on

parameters in this module. Default: True.

Returns:

Module: self

Parameters:

requires_grad (bool)

Return type:

Self

set_extra_state(state)

Set extra state contained in the loaded state_dict.

This function is called from load_state_dict() to handle any extra state found within the state_dict. Implement this function and a corresponding get_extra_state() for your module if you need to store extra state within its state_dict.

Args:

state (dict): Extra state from the state_dict

Parameters:

state (Any)

Return type:

None

set_submodule(target, module, strict=False)

Set the submodule given by target if it exists, otherwise throw an error.

Note

If strict is set to False (default), the method will replace an existing submodule or create a new submodule if the parent module exists. If strict is set to True, the method will only attempt to replace an existing submodule and throw an error if the submodule does not exist.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(3, 3, 3)
        )
        (linear): Linear(3, 3)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To override the Conv2d with a new submodule Linear, you could call set_submodule("net_b.net_c.conv", nn.Linear(1, 1)) where strict could be True or False

To add a new submodule Conv2d to the existing net_b module, you would call set_submodule("net_b.conv", nn.Conv2d(1, 1, 1)).

In the above if you set strict=True and call set_submodule("net_b.conv", nn.Conv2d(1, 1, 1), strict=True), an AttributeError will be raised because net_b does not have a submodule named conv.

Args:

target: The fully-qualified string name of the submodule

to look for. (See above example for how to specify a fully-qualified string.)

module: The module to set the submodule to. strict: If False, the method will replace an existing submodule

or create a new submodule if the parent module exists. If True, the method will only attempt to replace an existing submodule and throw an error if the submodule doesn’t already exist.

Raises:

ValueError: If the target string is empty or if module is not an instance of nn.Module. AttributeError: If at any point along the path resulting from

the target string the (sub)path resolves to a non-existent attribute name or an object that is not an instance of nn.Module.

Parameters:

• target (str)

• module (Module)

• strict (bool)

Return type:

None

share_memory()

See torch.Tensor.share_memory_().

Return type:

Self

state_dict(*args, destination=None, prefix='', keep_vars=False)

Overloads:

• self, destination (T_destination), prefix (str), keep_vars (bool) → T_destination

• self, prefix (str), keep_vars (bool) → dict[str, Any]

Return a dictionary containing references to the 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.

Note

The returned object is a shallow copy. It contains references to the module’s parameters and buffers.

Warning

Currently state_dict() also accepts positional arguments for destination, prefix and keep_vars in order. However, this is being deprecated and keyword arguments will be enforced in future releases.

Warning

Please avoid the use of argument destination as it is not designed for end-users.

Args:

destination (dict, optional): If provided, the state of module will

be updated into the dict and the same object is returned. Otherwise, an OrderedDict will be created and returned. Default: None.

prefix (str, optional): a prefix added to parameter and buffer

names to compose the keys in state_dict. Default: ''.

keep_vars (bool, optional): by default the Tensor s

returned in the state dict are detached from autograd. If it’s set to True, detaching will not be performed. Default: False.

Returns:

dict:

a dictionary containing a whole state of the module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> module.state_dict().keys()
['bias', 'weight']

to(*args, **kwargs)

Overloads:

• self, device (DeviceLikeType | None), dtype (dtype | None), non_blocking (bool) → Self

• self, dtype (dtype), non_blocking (bool) → Self

• self, tensor (Tensor), non_blocking (bool) → Self

Move and/or cast 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 complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_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.

Args:

device (torch.device): the desired device of the parameters

and buffers in this module

dtype (torch.dtype): the desired floating point or complex dtype of

the parameters and buffers in this module

tensor (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:

Module: self

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> 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)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> 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, recurse=True)

Move the parameters and buffers to the specified device without copying storage.

Args:

device (torch.device): The desired device of the parameters

and buffers in this module.

recurse (bool): Whether parameters and buffers of submodules should

be recursively moved to the specified device.

Returns:

Module: self

Parameters:

• device (str | device | int | None)

• recurse (bool)

Return type:

Self

train(mode=True)

Set the module in training mode.

This has an effect only on certain modules. See the documentation of particular modules for details of their behaviors in training/evaluation mode, i.e., whether they are affected, e.g. Dropout, BatchNorm, etc.

Args:

mode (bool): whether to set training mode (True) or evaluation

mode (False). Default: True.

Returns:

Module: self

Parameters:

mode (bool)

Return type:

Self

type(dst_type)

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

Args:

dst_type (type or string): the desired type

Returns:

Module: self

Parameters:

dst_type (dtype | str)

Return type:

Self

xpu(device=None)

Move 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.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

Parameters:

device (int | device | None)

Return type:

Self

zero_grad(set_to_none=True)

Reset gradients of all model parameters.

See similar function under torch.optim.Optimizer for more context.

Args:

set_to_none (bool): instead of setting to zero, set the grads to None.

See torch.optim.Optimizer.zero_grad() for details.

Parameters:

set_to_none (bool)

Return type:

None

training: bool

forward(vel)

Convert basilar membrane velocity to receptor potential.

Applies the complete IHC transduction pipeline: scaling → MET conductance → pre-charging → ODE integration.

Parameters:

vel (Tensor) – Basilar membrane velocity in m/s (typically from DRNLFilterbank). Shape: \((B, F, T)\) or \((F, T)\) where \(B\) is batch size, \(F\) is frequency channels, \(T\) is time samples.

Returns:

Receptor potential in Volts (relative to resting potential). Same shape as input.

Return type:

Tensor

Notes

The processing steps are:

1. Scale velocity to stereocilia displacement

2. Compute MET channel conductance \(G(d)\)

3. Pre-charge circuit to steady-state (50 ms simulation)

4. Integrate ODE for membrane potential

For 2D input \((F, T)\), a batch dimension is temporarily added and removed after processing.

Timing: For \(f_s = 44100\) Hz and 1 second signal with 50 channels:

• Pre-charge: 2205 samples x 50 channels = 110,250 operations

• Main ODE: 44100 samples x 50 channels = 2,205,000 operations

• Total: ~2.3M operations per batch item

extra_repr()

Extra representation string for module printing.

Returns:

String containing key module parameters.

Return type:

str