class turicreate.image_similarity.ImageSimilarityModel(state)

An trained model that is ready to use for similarity. This model should not be constructed directly.


ImageSimilarityModel.export_coreml(filename) Save the model in Core ML format.
ImageSimilarityModel.name() Returns the name of the model.
ImageSimilarityModel.query(dataset[, label, …]) For each image, retrieve the nearest neighbors from the model’s stored data.
ImageSimilarityModel.save(location) Save the model.
ImageSimilarityModel.similarity_graph([k, …]) Construct the similarity graph on the reference dataset, which is already stored in the model to find the top k similar images for each image in your input dataset.
ImageSimilarityModel.summary([output]) Print a summary of the model.