physioex.models.FoundationEncoder#

class physioex.models.FoundationEncoder(in_chan, checkpoint_path=None, **kwargs)[source]#

Bases: Module

Abstract adapter: frozen encoder that returns embeddings.

Subclasses implement:

  • _build_encoder(**kwargs) -> nn.Module (the pretrained encoder)

  • _get_embedding_dim() -> int

  • _load_pretrained(path) -> None (load checkpoint into self.encoder)

  • _encode(x) -> (B, D) embeddings from (B, C’, T’) input

  • _preprocess(x) -> (B, C’, T’) (optional: resampling, channel mapping)

The wrapper handles:

  • Reshaping (B, L, C, T) -> (B*L, C, T) before encoding

  • Freezing all encoder parameters

  • Reshaping output back to (B, L, D)

Parameters:

  • in_chan (int)

  • checkpoint_path (str | None)

__init__(in_chan, checkpoint_path=None, **kwargs)[source]#

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

Parameters:

  • in_chan (int)

  • checkpoint_path (str | None)

Methods

__init__(in_chan[, checkpoint_path])

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

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.

encode(x)

Alias for forward() - compatibility with embed.py.

eval()

Set the module in evaluation mode.

extra_repr()

Return the extra representation of the module.

float()

Casts all floating point parameters and buffers to float datatype.

forward(x)

(B, L, C, T) -> (B, L, D) embeddings.

get_buffer(target)

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

get_dataset(dataset_name[, root, channels, ...])

Create a dataset with the correct pipeline AND channels for this model.

get_extra_state()

Return any extra state to include in the module's state_dict.

get_parameter(target)

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

get_pipeline()

Return the preprocessing pipeline for this model.

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.

modules([remove_duplicate])

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.

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.

set_extra_state(state)

Set extra state contained in the loaded state_dict.

set_submodule(target, module[, strict])

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.

Attributes

CHANNEL_STRATEGY

MODEL_NAME

PIPELINE_PRESET

T_destination

call_super_init

dump_patches

training

encode(x)[source]#

Alias for forward() - compatibility with embed.py.

Parameters:

x (Tensor)

Return type:

Tensor

forward(x)[source]#

(B, L, C, T) -> (B, L, D) embeddings.

Parameters:

x (Tensor)

Return type:

Tensor

classmethod get_dataset(dataset_name, root=None, channels=None, sequence_length=21, **kwargs)[source]#

Create a dataset with the correct pipeline AND channels for this model.

Automatically selects: - The right resampling pipeline (via PIPELINE_PRESET) - The right EEG channels for this dataset (via _datasets.py registry) - The right constructor kwargs (cohort, visit, subset, …)

The user doesn’t need to know what channels each dataset has or what each model expects — get_dataset() handles both automatically.

The channel registry mirrors EEGBenchmarks’ DATASET_REGISTRY exactly, so the same cache files are reused across both systems.

Parameters:

  • dataset_name (str) – registered name (hmc, sleepedf, mass, wsc, mesa, …). See available_dataset_configs() for full list.

  • root (str) – override data root. If None, uses the default path from the dataset config registry.

  • channels (list) – override channel requests. If None (recommended), uses the dataset-specific channels from the registry.

  • sequence_length (int) – number of epochs per sample (default 21)

  • **kwargs – extra args merged with the dataset config’s extra_kwargs.

Returns:

A BasePhysioDataset instance ready for this model.

Return type:

BasePhysioDataset

Example:

# Everything is automatic — pipeline, channels, root:
dataset = CBraModEncoder.get_dataset("hmc")

# Override root only:
dataset = CBraModEncoder.get_dataset("hmc", root="/my/data/hmc")

# Full manual control:
dataset = CBraModEncoder.get_dataset(
    "hmc", channels=["EEG C4-M1"], root="/my/data/hmc"
)
classmethod get_pipeline()[source]#

Return the preprocessing pipeline for this model.

The pipeline is a resample-only pipeline matching the model’s native sampling rate. Its hash is identical to the one used in EEGBenchmarks, so cached preprocessed data is shared between the two systems.

Subclasses must set PIPELINE_PRESET class attribute.

Return type:

PreprocessingPipeline