InceptionTimeClassifier

class InceptionTimeClassifier(n_epochs=1500, batch_size=64, kernel_size=40, n_filters=32, use_residual=True, use_bottleneck=True, bottleneck_size=32, depth=6, callbacks=None, random_state=None, verbose=False, loss='categorical_crossentropy', metrics=None, class_weight=None, activation='softmax', activation_hidden='relu', activation_inception='linear')[source]

InceptionTime Deep Learning Classifier.

Adapted from the implementation from Fawaz et. al https://github.com/hfawaz/InceptionTime/blob/master/classifiers/inception.py

Described in [1]_, InceptionTime is a deep learning model designed for time series classification. It is based on the Inception architecture for images. The model is made up of a series of Inception modules.

InceptionTimeClassifier is a single instance of InceptionTime model described in the original publication [1]_, which uses an ensemble of 5 single instances.

To build an ensemble of models mirroring [1]_, use the BaggingClassifier with n_estimators=5, bootstrap=False, and estimator being an instance of this InceptionTimeClassifier.

Parameters:

activationstring or a tf callable, default=”softmax”: Activation function used in the output layer. List of available activation functions: https://keras.io/api/layers/activations/
activation_hiddenstring or a tf callable, default=”relu”: Activation function used in the hidden layers. List of available activation functions: https://keras.io/api/layers/activations/
activation_inceptionstring or a tf callable, default=”linear”: Activation function used in the Inception modules. List of available activation functions: https://keras.io/api/layers/activations/
n_epochsint, default=1500
batch_sizeint, default=64: the number of samples per gradient update
kernel_sizeint, default=40: specifying the length of the 1D convolution window
n_filtersint, default=32
use_residualboolean, default=True
use_bottleneckboolean, default=True
bottleneck_sizeint, default=32
depthint, default=6
callbackslist of tf.keras.callbacks.Callback objects
random_state: int, optional, default=None: random seed for internal random number generator
verbose: boolean, default=False: whether to print runtime information
loss: str, default=”categorical_crossentropy”
metrics: optional
class_weight: dict, optional, default=None: Dictionary mapping class labels to a weight (float) value to be used during model training. For example, {"A": 1.0, "B": 2.5} will assign a weight of 1.0 to class “A” and 2.5 to class “B”. This is passed directly to Keras’ fit method as the class_weight argument after converting labels to integer encoding. If None, all classes are given equal weight.

Attributes:

is_fitted: Whether fit has been called.

Notes

..[1] Fawaz et. al, InceptionTime: Finding AlexNet for Time Series Classification, Data Mining and Knowledge Discovery, 34, 2020

Examples

Single instance of InceptionTime model: >>> from sktime.classification.deep_learning import InceptionTimeClassifier >>> from sktime.datasets import load_unit_test # doctest: +SKIP >>> X_train, y_train = load_unit_test(split=”train”) # doctest: +SKIP >>> X_test, y_test = load_unit_test(split=”test”) # doctest: +SKIP >>> clf = InceptionTimeClassifier() # doctest: +SKIP >>> clf.fit(X_train, y_train) # doctest: +SKIP InceptionTimeClassifier(…)

To build an ensemble of models mirroring [1]_, use the BaggingClassifier as follows: >>> from sktime.classification.ensemble import BaggingClassifier >>> from sktime.classification.deep_learning import InceptionTimeClassifier >>> from sktime.datasets import load_unit_test # doctest: +SKIP >>> X_train, y_train = load_unit_test(split=”train”) # doctest: +SKIP >>> X_test, y_test = load_unit_test(split=”test”) # doctest: +SKIP >>> clf = BaggingClassifier( … InceptionTimeClassifier(), … n_estimators=5, … bootstrap=False … ) # doctest: +SKIP >>> clf.fit(X_train, y_train) # doctest: +SKIP BaggingClassifier(…)

Methods

`build_model`(input_shape, n_classes, **kwargs)	Construct a compiled, un-trained, keras model that is ready for training.
`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.
`summary`()	Summary function to return the losses/metrics for model fit.