gt4sd.frameworks.granular.ml.models.base_model module

Base model for granular.

Summary

Classes:

GranularBaseModel	Base model class.
GranularEncoderDecoderModel	Autoencoder model class.

Reference

class GranularBaseModel(name, data, *args, **kwargs)

Bases: Module

Base model class.

position: int

from_position: List[int]

__init__(name, data, *args, **kwargs)

Construct GranularBaseModel.

Parameters

• name (str) – model name.

• data (Dict[str, str]) – data name mappings.

forward(x, *args, **kwargs)

Forward pass in the model.

Parameters

x (Any) – model input.

Return type

Any

Returns

model output.

abstract _run_step(x, *args, **kwargs)

Run a step in the model.

Parameters

x (Any) – model input.

Return type

Any

Returns

model step output.

abstract step(input_data, target_data, device='cpu', current_epoch=0, *args, **kwargs)

Training step for the model.

Parameters

• input_data (Any) – input for the step.

• target_data (Any) – target for the step.

• device (str) – string representing the device to use. Defaults to “cpu”.

• current_epoch (int) – current epoch. Defaults to 0.

Return type

Tuple[Any, Any, Any]

Returns

a tuple containing the step output, the loss and the logs for the module.

abstract val_step(input_data, target_data, device='cpu', current_epoch=0, *args, **kwargs)

Validation step for the model.

Parameters

• input_data (Any) – input for the step.

• target_data (Any) – target for the step.

• device (str) – string representing the device to use. Defaults to “cpu”.

• current_epoch (int) – current epoch. Defaults to 0.

Return type

Any

Returns

a tuple containing the step output, the loss and the logs for the module.

static add_model_specific_args(parent_parser, name, *args, **kwargs)

Adding to a parser model specific arguments.

Parameters

• parent_parser (ArgumentParser) – patent parser.

• name (str) – model name.

Return type

ArgumentParser

Returns

updated parser.

__annotations__ = {'__call__': 'Callable[..., Any]', '_backward_hooks': 'Dict[int, Callable]', '_buffers': 'Dict[str, Optional[Tensor]]', '_forward_hooks': 'Dict[int, Callable]', '_forward_pre_hooks': 'Dict[int, Callable]', '_is_full_backward_hook': 'Optional[bool]', '_load_state_dict_post_hooks': 'Dict[int, Callable]', '_load_state_dict_pre_hooks': 'Dict[int, Callable]', '_modules': "Dict[str, Optional['Module']]", '_non_persistent_buffers_set': 'Set[str]', '_parameters': 'Dict[str, Optional[Parameter]]', '_state_dict_hooks': 'Dict[int, Callable]', '_version': 'int', 'dump_patches': 'bool', 'forward': 'Callable[..., Any]', 'from_position': typing.List[int], 'position': <class 'int'>, 'training': 'bool'}

__doc__ = 'Base model class.'

__module__ = 'gt4sd.frameworks.granular.ml.models.base_model'

class GranularEncoderDecoderModel(name, data, *args, **kwargs)

Bases: GranularBaseModel

Autoencoder model class.

latent_size: int

abstract decode(z, *args, **kwargs)

Decode a latent space point.

Parameters

z (Any) – latent point.

Return type

Any

Returns

decoded sample.

abstract encode(x, *args, **kwargs)

Encode a sample.

Parameters

x (Any) – input sample.

Return type

Any

Returns

latent encoding.

encode_decode(x, *args, **kwargs)

Encode and decode a sample.

Parameters

x (Any) – input sample.

Return type

Any

Returns

decoded sample.

inference(z, *args, **kwargs)

Run the model in inference mode.

Parameters

z (Any) – sample.

Return type

Any

Returns

generated output.

sample(mu, log_var)

Sample a point from a given mean and average following a normal log-likelihood.

Parameters

• mu (Tensor) – mean tensor.

• log_var (Tensor) – log varian tensor.

Return type

Tuple[Distribution, Distribution, Tensor]

Returns

a tuple containing standard normal, localized normal and the sampled point.

__annotations__ = {'__call__': 'Callable[..., Any]', '_backward_hooks': 'Dict[int, Callable]', '_buffers': 'Dict[str, Optional[Tensor]]', '_forward_hooks': 'Dict[int, Callable]', '_forward_pre_hooks': 'Dict[int, Callable]', '_is_full_backward_hook': 'Optional[bool]', '_load_state_dict_post_hooks': 'Dict[int, Callable]', '_load_state_dict_pre_hooks': 'Dict[int, Callable]', '_modules': "Dict[str, Optional['Module']]", '_non_persistent_buffers_set': 'Set[str]', '_parameters': 'Dict[str, Optional[Parameter]]', '_state_dict_hooks': 'Dict[int, Callable]', '_version': 'int', 'dump_patches': 'bool', 'forward': 'Callable[..., Any]', 'from_position': 'List[int]', 'latent_size': <class 'int'>, 'position': 'int', 'training': 'bool'}

__doc__ = 'Autoencoder model class.'

__module__ = 'gt4sd.frameworks.granular.ml.models.base_model'