InceptionTimeRegressor

InceptionTime Deep Learning Regressor.

Quickstart

from sktime.regression.deep_learning.inceptiontime import InceptionTimeRegressor

estimator = InceptionTimeRegressor(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='mean_squared_error', metrics=None, activation='linear', activation_hidden='relu', activation_inception='linear')

Parameters(16)

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_stateint, optional, default=None

random seed for internal random number generator

verboseboolean, default=False

whether to print runtime information

lossstr, default=”mean_squared_error”

metricsoptional

activationstring or a tf callable, default=”linear”

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 layers. List of available activation functions: https://keras.io/api/layers/activations/