ConceptClassificationModel2D
- class hybrid_learning.concepts.models.concept_models.concept_classification.ConceptClassificationModel2D(concept=None, model=None, layer_id=None, in_channels=None, act_map_size=None, **other_settings)[source]
Bases:
ConceptDetectionModel2DA concept model that classifies whether an image-level concept is recognized in an activation map. This is solved by a localization model with window respectively kernel size the same as the input size.
A forward run with a batch of size
(batch, in_channels, h, w)returns a batch of confidence values of the size(batch, 1). For a usage example compareConceptDetection2DTrainTestHandle.Warning
An error is raised if a tensor with
(height, width)different fromkernel_sizeis provided toforward().Public Data Attributes:
Inherited from : py: class:ConceptDetectionModel2D
conceptThe concept for which this model was configured.
concept_nameThe name of the associated concept if known.
main_model_stumpStump of the main model for which this instance was configured.
main_modelShortcut to access the main model.
layer_idLayer to extract concept from.
kernel_sizeSize of the convolution kernel.
in_channelsNumber of input channels.
apply_sigmoidWhether a sigmoid is applied to the output of the forward function before returning it.
apply_paddingWhether a zero-padding is applied to the input of the forward function.
settingsThe current model settings as dictionary.
Public Methods:
forward(inp)Wrapper around super forward method.
Inherited from : py: class:ConceptDetectionModel2D
reset_parameters()Randomly (re)initialize weight and bias.
to_embedding()Return the plain representation of the ensemble as list of
ConceptEmbedding.forward(inp)Wrapper around super forward method.
Inherited from : py: class:Module
forward(inp)Wrapper around super 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
targetif it exists, otherwise throws an error.get_parameter(target)Returns the parameter given by
targetif it exists, otherwise throws an error.get_buffer(target)Returns the buffer given by
targetif it exists, otherwise throws an error.apply(fn)Applies
fnrecursively 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
floatdatatype.double()Casts all floating point parameters and buffers to
doubledatatype.half()Casts all floating point parameters and buffers to
halfdatatype.bfloat16()Casts all floating point parameters and buffers to
bfloat16datatype.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_dictinto 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()extra_repr()Set the extra representation of the module
Special Methods:
__init__([concept, model, layer_id, ...])Init.
Inherited from : py: class:ConceptDetectionModel2D
__init__([concept, model, layer_id, ...])Init.
Inherited from : py: class:Module
__init__([concept, model, layer_id, ...])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
- __init__(concept=None, model=None, layer_id=None, in_channels=None, act_map_size=None, **other_settings)[source]
Init.
Wrapper around init of a
ConceptDetectionModel2Dwith fixedkernel_sizeof \(1\times1\) and disabled padding. For details on the arguments see the init function of the super classConceptDetectionModel2D.