ConvTimeNetClassifier

class ConvTimeNetClassifier(d_model, patch_size, patch_stride, dropout=0, d_ff=128, dw_ks=3, device='cpu', num_epochs=16, batch_size=8, criterion=None, criterion_kwargs=None, optimizer=None, optimizer_kwargs=None, lr=0.001, verbose=False, random_state=None)[source]

ConvTimeNet for time series classification.

ConvTimeNet is a hierarchical pure convolutional model designed. Unlike prevalent methods centered around self-attention mechanisms, ConvTimeNet introduces two key innovations:

A deformable patch layer that adaptively perceives local patterns of temporally dependent basic units in a data-driven manner.
Hierarchical pure convolutional blocks that capture dependency relationships
among the representations of basic units at different scales.

The model employs a large kernel mechanism allowing convolutional blocks to be deeply stacked, achieving a larger receptive field. This architecture effectively models both local patterns and their multi-scale dependencies within a single model, addressing common challenges in time series analysis such as adaptive perception of local patterns and multi-scale dependency capture.

This classifier has been wrapped around implementations from [1], [2] and [3]_.

Parameters:

d_modelint: Hidden dimension size for model processing.
patch_sizeint: Size of patches for sequence splitting.
patch_strideint: Stride length for patch creation.
dropoutfloat, optional (default=0): Dropout rate to apply to layers.
d_ffint, optional (default=128): Dimension of feedforward network.
dw_ksint or list, optional (default=3): Depthwise convolution kernel size(s). Can be a single int or list of ints.
devicestr, optional (default=”cpu”): Device to use for computation (“cpu” or “cuda”).
num_epochsint, optional (default=16): The number of epochs to train the model.
batch_sizeint, optional (default=8): The size of each mini-batch during training.
criterioncallable, optional (default=None): The loss function to use. If None, CrossEntropyLoss will be used.
criterion_kwargsdict, optional (default=None): Additional keyword arguments to pass to the loss function.
optimizerstr, optional (default=None): The optimizer to use. If None, Adam will be used.
optimizer_kwargsdict, optional (default=None): Additional keyword arguments to pass to the optimizer.
lrfloat, optional (default=0.001): The learning rate to use for the optimizer.
verbosebool, optional (default=False): Whether to print progress information during training.
random_stateint, optional (default=None): Seed to ensure reproducibility.

Attributes:

is_fitted: Whether fit has been called.

References

[1]

Cheng, M., Yang, J., Pan, T., Liu, Q., & Li, Z. (2024). ConvTimeNet: A deep hierarchical fully convolutional model for multivariate time series analysis. arXiv preprint arXiv:2403.01493. https://arxiv.org/abs/2403.01493

[2]

https://github.com/Mingyue-Cheng/ConvTimeNet

Examples

>>> from sktime.classification.deep_learning import ConvTimeNetClassifier
>>> import numpy as np
>>> # Create a sample multivariate time series dataset
>>> # 48 samples, 3 variables, length 128
>>> X = np.random.randn(16 * 3, 3, 128).astype("float32")
>>> y = np.array([0, 1, 2] * 16)  # 3 classes
>>> # Create and fit the classifier
>>> clf = ConvTimeNetClassifier(
...     patch_size=4,
...     patch_stride=2,
...     d_model=64,
...     d_ff=128,
...     dw_ks=[5, 7, 9],
...     batch_size=8,
...     device="cpu",
...     random_state=10
... )
>>> clf.fit(X, y)
ConvTimeNetClassifier(...)
>>> # Make predictions
>>> y_pred = clf.predict(X)
>>> y_proba = clf.predict_proba(X)

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.