amatorch.models.ama_parent

Classes

AMAParent(priors[, n_dim, n_filters, ...])

Abstract AMA parent class.

class amatorch.models.ama_parent.AMAParent(priors, n_dim=None, n_filters=None, n_channels=1, filters=None, constraint='sphere')

Bases: ABC, Module

Abstract AMA parent class.

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 response to each stimulus.
`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 the stimuli before computing the responses.
`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__

forward(stimuli)

Compute the class posteriors for the stimuli.

Parameters:: stimuli (torch.Tensor) – Stimulus tensor of shape (n_stim, n_channels, n_dim).
Returns:: Posteriors tensor of shape (n_stim, n_classes).
Return type:: torch.Tensor

get_estimates(stimuli)

Compute latent variable estimates for each stimulus.

Parameters:: stimuli (torch.Tensor) – Stimulus tensor of shape (n_stim, n_channels, n_dim).
Returns:: Estimates tensor of shape (n_stim).
Return type:: torch.Tensor

get_log_likelihoods(stimuli)

Compute the log-likelihood of each class for each stimulus.

Parameters:: stimuli (torch.Tensor) – Stimulus tensor of shape (n_stim, n_channels, n_dim).
Returns:: Log-likelihoods tensor of shape (n_stim, n_classes).
Return type:: torch.Tensor

get_posteriors(stimuli)

Compute the posterior of each class for each stimulus.

Parameters:: stimuli (torch.Tensor) – Stimulus tensor of shape (n_stim, n_channels, n_dim).
Returns:: Posteriors tensor of shape (n_stim, n_classes).
Return type:: torch.Tensor

abstract get_responses(stimuli)

Compute the response to each stimulus.

Parameters:: stimuli (torch.Tensor) – Stimulus tensor of shape (n_stim, n_channels, n_dim).
Returns:: Responses tensor of shape (n_stim, n_filters).
Return type:: torch.Tensor

log_likelihoods_2_posteriors(log_likelihoods)

Compute the posterior of each class given the log-likelihoods.

Parameters:: log_likelihoods (torch.Tensor) – Log-likelihoods tensor of shape (n_stim, n_classes).
Returns:: Posteriors tensor of shape (n_stim, n_classes).
Return type:: torch.Tensor

posteriors_2_estimates(posteriors)

Convert posterior probabilities to estimates of the latent variable.

Parameters:: posteriors (torch.Tensor) – Posterior probabilities tensor of shape (n_stim, n_classes).
Returns:: Estimates tensor of shape (n_stim), containing the estimated latent variable for each stimulus.
Return type:: torch.Tensor

abstract preprocess(stimuli)

Preprocess the stimuli before computing the responses.

Parameters:: stimuli (torch.Tensor) – Stimulus tensor of shape (n_stim, n_channels, n_dim).
Returns:: Preprocessed stimuli of shape (n_stim, n_channels, n_dim).
Return type:: torch.Tensor

abstract 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