MACNNRegressorTorch

class MACNNRegressorTorch(padding: str = 'same', pool_size: int = 3, strides: int = 2, repeats: int = 2, filter_sizes: tuple = (64, 128, 256), kernel_sizes: tuple = (3, 6, 12), reduction: int = 16, activation: str | Callable | None = None, activation_hidden: str | Callable | None = 'ReLU', num_epochs: int = 1500, batch_size: int = 4, optimizer: str | None | Callable = 'RMSprop', optimizer_kwargs: dict | None = None, criterion: str | None | Callable = 'MSELoss', criterion_kwargs: dict | None = None, callbacks: None | str | tuple[str, ...] = 'ReduceLROnPlateau', callback_kwargs: dict | None = None, lr: float = 0.001, verbose: bool = False, init_weights: str | None = None, random_state: int = 0)[source]

Multi-Scale Attention Convolutional Neural Network (MACNN) regressor in PyTorch.

This regressor implements a multi-scale attention mechanism that learns feature representations across different temporal scales.

Parameters:

paddingstr, default=”same”

The type of padding to be provided in MACNN Blocks. Used for pooling layers only. Convolution layers always use “same” padding, so that multi-scale outputs can be concatenated.

pool_sizeint, default=3

A single value representing pooling windows which are applied between two MACNN Blocks.

stridesint, default=2

A single value representing strides to be taken during the pooling operation.

repeatsint, default=2

The number of MACNN Blocks to be stacked.

filter_sizestuple of int, default=(64, 128, 256)

The filter sizes of Conv1D layers within each MACNN Block.

kernel_sizestuple of int, default=(3, 6, 12)

The kernel sizes of Conv1D layers within each MACNN Block.

reductionint, default=16

The factor by which the first dense layer of a MACNN Block will be divided by.

activationstr, Callable, or None, default=None

Activation applied to the output layer.

Permitted values:

None: no activation is applied to the output layer and the network returns raw outputs.
str: name of a class in torch.nn. Case-sensitive names are recommended and must match PyTorch (e.g., "ReLU", "LeakyReLU"). Lowercase aliases for common activations are also accepted (e.g., "relu" is resolved to "ReLU"). The class is instantiated with default constructor arguments. Must be a valid torch.nn activation; see https://pytorch.org/docs/stable/nn.html#non-linear-activations-weighted-sum-nonlinearity
torch.nn.Module: an instance of a torch.nn.Module subclass, for example torch.nn.ReLU(). Arbitrary callables are not supported.

Recommended activations:ReLU, Tanh, Sigmoid, LeakyReLU, ELU, SELU, GELU.

activation_hiddenstr, Callable, or None, default=”ReLU”

Activation applied to the hidden layers.

Permitted values:

None: no activation is applied to the hidden layers.
str: name of a class in torch.nn. Case-sensitive names are recommended and must match PyTorch (e.g., "ReLU", "LeakyReLU"). Lowercase aliases for common activations are also accepted (e.g., "relu" is resolved to "ReLU"). The class is instantiated with default constructor arguments. Must be a valid torch.nn activation; see https://pytorch.org/docs/stable/nn.html#non-linear-activations-weighted-sum-nonlinearity
torch.nn.Module: an instance of a torch.nn.Module subclass, for example torch.nn.ReLU(). Arbitrary callables are not supported.

Recommended activations: ReLU, Tanh, Sigmoid, LeakyReLU, ELU, SELU, GELU.

num_epochsint, default=1500

The number of epochs to train the model.

batch_sizeint, default=4

The size of each mini-batch during training.

optimizercase insensitive str or None or an instance of optimizers

defined in torch.optim, default = “RMSprop” The optimizer to use for training the model.

optimizer_kwargsdict or None, default = None

Additional keyword arguments to pass to the optimizer.

criterioncase insensitive str or None or an instance of a loss function

defined in PyTorch, default = “MSELoss” The loss function to be used in training the neural network.

criterion_kwargsdict or None, default = None

Additional keyword arguments to pass to the loss function.

callbacksNone or str or a tuple of str, default = “ReduceLROnPlateau”

Currently only learning rate schedulers are supported as callbacks.

callback_kwargsdict or None, default = None

The keyword arguments to be passed to the callbacks.

lrfloat, default = 0.001

The learning rate to use for the optimizer.

verbosebool, default = False

Whether to print progress information during training.

init_weightsstr or None, default = None

The method to initialize the weights of the conv layers. Supported values are ‘kaiming_uniform’, ‘kaiming_normal’, ‘xavier_uniform’, ‘xavier_normal’, or None for default PyTorch initialization.

random_stateint, default = 0

Seed to ensure reproducibility.

Attributes:

is_fitted: Whether fit has been called.

References

[1]

Wei Chen et. al, Multi-scale Attention Convolutional

Neural Network for time series classification, Neural Networks, Volume 136, 2021, Pages 126-140, ISSN 0893-6080, https://doi.org/10.1016/j.neunet.2021.01.001.

Examples

>>> from sktime.regression.deep_learning.macnn import MACNNRegressorTorch
>>> from sktime.datasets import load_unit_test
>>> X_train, y_train = load_unit_test(split="train")
>>> X_test, y_test = load_unit_test(split="test")
>>> reg = MACNNRegressorTorch(num_epochs=50, batch_size=2)
>>> reg.fit(X_train, y_train)
MACNNRegressorTorch(...)

Methods

`check_is_fitted`([method_name])	Check if the estimator has been fitted.
`clone`()	Obtain a clone of the object with same hyper-parameters and config.
`clone_tags`(estimator[, tag_names])	Clone tags from another object as dynamic override.
`create_test_instance`([parameter_set])	Construct an instance of the class, using first test parameter set.
`create_test_instances_and_names`([parameter_set])	Create list of all test instances and a list of names for them.
`fit`(X, y)	Fit time series regressor to training data.
`get_class_tag`(tag_name[, tag_value_default])	Get class tag value from class, with tag level inheritance from parents.
`get_class_tags`()	Get class tags from class, with tag level inheritance from parent classes.
`get_config`()	Get config flags for self.
`get_fitted_params`([deep])	Get fitted parameters.
`get_param_defaults`()	Get object's parameter defaults.
`get_param_names`([sort])	Get object's parameter names.
`get_params`([deep])	Get a dict of parameters values for this object.
`get_tag`(tag_name[, tag_value_default, ...])	Get tag value from instance, with tag level inheritance and overrides.
`get_tags`()	Get tags from instance, with tag level inheritance and overrides.
`get_test_params`([parameter_set])	Return testing parameter settings for the estimator.
`is_composite`()	Check if the object is composed of other BaseObjects.
`load_from_path`(serial)	Load object from file location.
`load_from_serial`(serial)	Load object from serialized memory container.
`predict`(X)	Predicts labels for sequences in X.
`reset`()	Reset the object to a clean post-init state.
`save`([path, serialization_format])	Save serialized self to bytes-like object or to (.zip) file.
`score`(X, y[, multioutput])	Scores predicted labels against ground truth labels on X.
`set_config`(**config_dict)	Set config flags to given values.
`set_params`(**params)	Set the parameters of this object.
`set_random_state`([random_state, deep, ...])	Set random_state pseudo-random seed parameters for self.
`set_tags`(**tag_dict)	Set instance level tag overrides to given values.