turicreate.activity_classifier.ActivityClassifier

class turicreate.activity_classifier.ActivityClassifier(model_proxy=None, name=None)

A trained model using C++ implementation that is ready to use for classification or export to CoreML.

This model should not be constructed directly.

Methods

ActivityClassifier.classify(self, dataset[, …]) Return a classification, for each prediction_window examples in the dataset, using the trained activity classification model.
ActivityClassifier.evaluate(self, dataset[, …]) Evaluate the model by making predictions of target values and comparing these to actual values.
ActivityClassifier.export_coreml(self, filename) Export the model in Core ML format.
ActivityClassifier.predict(self, dataset[, …]) Return predictions for dataset, using the trained activity classifier.
ActivityClassifier.predict_topk(self, dataset) Return top-k predictions for the dataset, using the trained model.
ActivityClassifier.save(self, location) Save the model.
ActivityClassifier.summary(self[, output]) Print a summary of the model.