LSTMFCNClassifierTorch

LSTMFCNClassifierTorch

class LSTMFCNClassifierTorch(kernel_sizes: tuple = (8, 5, 3), filter_sizes: tuple = (128, 256, 128), lstm_size: int = 8, dropout: float = 0.8, attention: bool = False, activation: str | Callable | None = None, activation_hidden: str | Callable | None = 'ReLU', num_epochs: int = 2000, batch_size: int = 128, optimizer: str | None | Callable = 'Adam', optimizer_kwargs: dict | None = None, criterion: str | None | Callable = 'CrossEntropyLoss', criterion_kwargs: dict | None = None, callbacks: None | str | tuple[str, ...] = 'ReduceLROnPlateau', callback_kwargs: dict | None = None, init_weights: str | None = 'kaiming_uniform', metrics: None | str | Callable | tuple[str | Callable, ...] = None, lr: float = 0.001, verbose: bool = False, random_state: int | None = None)[source]

LSTM-FCN classifier for time series classification in PyTorch.

Combines an LSTM arm with a CNN arm. Optionally uses an attention mechanism in the LSTM which the author indicates provides improved performance.

Parameters:

kernel_sizestuple of int, default=(8, 5, 3)

Specifying the length of the 1D convolution windows for each conv layer

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

Size of filter for each conv layer

lstm_sizeint, default=8

Output dimension for LSTM layer (hidden state size)

dropoutfloat, default=0.8

Controls dropout rate of LSTM layer

attentionbool, default=False

If True, uses attention mechanism before LSTM layer

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 (logits). This is typically required when using CrossEntropyLoss, which expects logits as input.

• 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=2000

The number of epochs to train the model.

batch_sizeint, default=128

The size of each mini-batch during training.

optimizercase insensitive str or None or an instance of optimizers

defined in torch.optim, default = “Adam” The optimizer to use for training the model. List of available optimizers: https://pytorch.org/docs/stable/optim.html#algorithms

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 = “CrossEntropyLoss” The loss function to be used in training the neural network. List of available loss functions: https://pytorch.org/docs/stable/nn.html#loss-functions

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. If more than one scheduler is passed, they are applied sequentially in the order they are passed. If None, then no learning rate scheduler is used. Note: Since PyTorch learning rate schedulers need to be initialized with the optimizer object, we only accept the class name (str) of the scheduler here and do not accept an instance of the scheduler. As that can lead to errors and unexpected behavior. List of available learning rate schedulers: https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate

callback_kwargsdict or None, default = None

The keyword arguments to be passed to the callbacks.

init_weights: str or None, default = ‘kaiming_uniform’

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.

metricsNone or str or Callable or tuple of str and/or Callable, default = None

Metrics to compute during training. If None, no metrics are computed beyond the loss. Metrics are computed from torchmetrics library. If a string/Callable is passed, it must be one of the metrics defined in https://lightning.ai/docs/torchmetrics/stable/ Examples: “Accuracy”, “F1Score”, “Precision”, “Recall”

lrfloat, default = 0.001

The learning rate to use for the optimizer.

verbosebool, default = False

Whether to print progress information during training.

random_stateint | None, default = None

Seed to ensure reproducibility.

Attributes:

is_fitted

Whether fit has been called.

References

[1]

Karim et al. Multivariate LSTM-FCNs for Time Series Classification, 2019

https://arxiv.org/pdf/1801.04503.pdf

Examples

>>> from sktime.classification.deep_learning.lstmfcn import LSTMFCNClassifierTorch
>>> 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")
>>> clf = LSTMFCNClassifierTorch(num_epochs=50, batch_size=128)
>>> clf.fit(X_train, y_train)
LSTMFCNClassifierTorch(...)

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 classifier to training data.
fit_predict(X, y[, cv, change_state])	Fit and predict labels for sequences in X.
fit_predict_proba(X, y[, cv, change_state])	Fit and predict labels probabilities for sequences in X.
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.
predict_proba(X)	Predicts labels probabilities 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)	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.