HooksHandle

class hybrid_learning.concepts.models.model_extension.HooksHandle(model, module_ids=None)

Bases: Module, ABC

Wrapper that registers and unregisters hooks from model that save intermediate output. For this, the pytorch hook mechanism is used.

Public Data Attributes:

registered_submodules

List of IDs of the registered sub-modules.

Inherited from : py: class:Module

dump_patches	This allows better BC support for load_state_dict().
T_destination	alias of TypeVar('T_destination', bound=Mapping[str, Tensor])

Public Methods:

register_submodule(module_id)	Register further submodule of to extract intermediate output from.
unregister_submodule(module_id)	Unregister a submodule for intermediate output retrieval.
get_module_by_id(m_id)	Get actual sub-module object within wrapped model by module ID.
forward(*inps)	Pytorch forward method.

Inherited from : py: class:Module

forward(*inps)	Pytorch forward method.
register_buffer(name, tensor[, persistent])	Adds a buffer to the module.
register_parameter(name, param)	Adds a parameter to the module.
add_module(name, module)	Adds a child module to the current module.
get_submodule(target)	Returns the submodule given by target if it exists, otherwise throws an error.
get_parameter(target)	Returns the parameter given by target if it exists, otherwise throws an error.
get_buffer(target)	Returns the buffer given by target if it exists, otherwise throws an error.
apply(fn)	Applies fn recursively to every submodule (as returned by .children()) as well as self.
cuda([device])	Moves all model parameters and buffers to the GPU.
xpu([device])	Moves all model parameters and buffers to the XPU.
cpu()	Moves all model parameters and buffers to the CPU.
type(dst_type)	Casts all parameters and buffers to dst_type.
float()	Casts all floating point parameters and buffers to float datatype.
double()	Casts all floating point parameters and buffers to double datatype.
half()	Casts all floating point parameters and buffers to half datatype.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
to_empty(*, device)	Moves the parameters and buffers to the specified device without copying storage.
to(*args, **kwargs)	Moves and/or casts the parameters and buffers.
register_backward_hook(hook)	Registers a backward hook on the module.
register_full_backward_hook(hook)	Registers a backward hook on the module.
register_forward_pre_hook(hook)	Registers a forward pre-hook on the module.
register_forward_hook(hook)	Registers a forward hook on the module.
state_dict([destination, prefix, keep_vars])	Returns a dictionary containing a whole state of the module.
load_state_dict(state_dict[, strict])	Copies parameters and buffers from state_dict into this module and its descendants.
parameters([recurse])	Returns an iterator over module parameters.
named_parameters([prefix, recurse])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
buffers([recurse])	Returns an iterator over module buffers.
named_buffers([prefix, recurse])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
children()	Returns an iterator over immediate children modules.
named_children()	Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
modules()	Returns an iterator over all modules in the network.
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.
train([mode])	Sets the module in training mode.
eval()	Sets the module in evaluation mode.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
zero_grad([set_to_none])	Sets gradients of all model parameters to zero.
share_memory()	See torch.Tensor.share_memory_()
extra_repr()	Set the extra representation of the module

Special Methods:

__init__(model[, module_ids])	Init.
__del__()	Unregister all hooks held by this handle on handle delete.

Inherited from : py: class:Module

__init__(model[, module_ids])	Init.
__call__(*input, **kwargs)	Call self as a function.
__setstate__(state)
__getattr__(name)
__setattr__(name, value)	Implement setattr(self, name, value).
__delattr__(name)	Implement delattr(self, name).
__repr__()	Return repr(self).
__dir__()	Default dir() implementation.

---

Parameters

• model (Module) –

• module_ids (Iterable[str]) –

__del__()

Unregister all hooks held by this handle on handle delete.

__init__(model, module_ids=None)

Init.

Parameters

• model (Module) – the model to wrap

• module_ids (Optional[Iterable[str]]) –

  the IDs of sub-modules to obtain intermediate output from;

  Note

  If a sub-module is used several times, its output can only be captured after the first call.

abstract forward(*inps)

Pytorch forward method.

get_module_by_id(m_id)

Get actual sub-module object within wrapped model by module ID.

register_submodule(module_id)

Register further submodule of to extract intermediate output from. The module_id must be a valid name of a sub-module of wrapped_model.

Parameters

module_id (str) –

Return type

None

unregister_submodule(module_id)

Unregister a submodule for intermediate output retrieval.

Parameters

module_id (str) –

Return type

None

hook_handles: Dict[str, torch.utils.hooks.RemovableHandle]

Dictionary of hooks; for each sub-module to grab output from, a hook is registered. On each forward, the hook for a sub-module of ID m writes the intermediate output of the sub-module into _intermediate_outs[m]. The dictionary saves for the sub-module ID the hook handle.

property registered_submodules: List[str]

List of IDs of the registered sub-modules.

training: bool

wrapped_model: torch.nn.modules.module.Module

Original model from which intermediate and final output are retrieved.