amatorch.models

Subpackage with the implemented AMA model variants.

class amatorch.models.AMAGauss(stimuli, labels, n_filters=None, filters=None, priors=None, response_noise=0.0, c50=0.0)

Bases: AMAParent

AMAGauss model.

This model assumes that class-conditional responses are Gaussian distributed.

Attributes:

response_statistics

Return the class-conditional response statistics.

Methods

add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Set the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(stimuli)	Compute the class posteriors for the stimuli.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_estimates(stimuli)	Compute latent variable estimates for each stimulus.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_log_likelihoods(stimuli)	Compute the log-likelihood of each class for each stimulus.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_posteriors(stimuli)	Compute the posterior of each class for each stimulus.
get_responses(stimuli)	Compute the responses of the filters to the stimuli after pre-processing.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
log_likelihoods_2_posteriors(log_likelihoods)	Compute the posterior of each class given the log-likelihoods.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
posteriors_2_estimates(posteriors)	Convert posterior probabilities to estimates of the latent variable.
preprocess(stimuli)	Preprocess stimuli by normalizing each channel.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
responses_2_log_likelihoods(responses)	Compute log-likelihood of each class given the filter responses.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module)	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

__call__

get_responses(stimuli)

Compute the responses of the filters to the stimuli after pre-processing.

Parameters:

stimuli (torch.Tensor) – Stimulus tensor of shape (…, n_channels, n_dim).

Returns:

Responses tensor of shape (…, n_filters).

Return type:

torch.Tensor

preprocess(stimuli)

Preprocess stimuli by normalizing each channel.

Each channel of each stimulus is divided by the square root of the sum of squares plus c50.

Parameters:

stimuli (torch.Tensor) – Stimulus tensor of shape (…, n_channels, n_dim).

Returns:

Processed stimuli tensor of shape (…, n_channels, n_dim).

Return type:

torch.Tensor

property response_statistics

Return the class-conditional response statistics.

Returns:

A dictionary containing: - ‘means’: torch.Tensor of shape (n_classes, n_filters). - ‘covariances’: torch.Tensor of shape (n_classes, n_filters, n_filters).

Return type:

dict

responses_2_log_likelihoods(responses)

Compute log-likelihood of each class given the filter responses.

Parameters:

responses (torch.Tensor) – Filter responses tensor of shape (n_stim, n_filters).

Returns:

Log-likelihoods tensor of shape (n_stim, n_classes).

Return type:

torch.Tensor

Modules

ama_gauss
ama_parent