InceptionTimeClassifier

InceptionTime Deep Learning Classifier.

Quickstart

from sktime.classification.deep_learning.inceptiontime import InceptionTimeClassifier

estimator = 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')

Parameters(17)

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.

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(…)