001/** 002 * DeepNetts is pure Java Deep Learning Library with support for Backpropagation 003 * based learning and image recognition. 004 * 005 * Copyright (C) 2017 Zoran Sevarac <sevarac@gmail.com> 006 * 007 * This file is part of DeepNetts. 008 * 009 * DeepNetts is free software: you can redistribute it and/or modify 010 * it under the terms of the GNU General Public License as published by 011 * the Free Software Foundation, either version 3 of the License, or 012 * (at your option) any later version. 013 * 014 * but WITHOUT ANY WARRANTY; without even the implied warranty of 015 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 016 * GNU General Public License for more details. 017 * 018 * You should have received a copy of the GNU General Public License 019 * along with this program. If not, see <https://www.gnu.org/licenses/>.package deepnetts.core; 020 */ 021 022package javax.visrec.ml.eval; 023 024/** 025 * All evaluators implement this interface. 026 * Maybe move to visrec.ml.eval 027 * CONSIDER: using more specific model type instead of general model class? Classifier, Regressor? 028 * 029 * @param <T1> Model class 030 * @param <T2> Data set class 031 * 032 * @author Zoran Sevarac 033 * @since 1.0 034 */ 035@FunctionalInterface 036public interface Evaluator<T1, T2> { 037 038 /** 039 * Evaluate model with specified data set. 040 * Return Map with performance metrics and values? 041 * {@code Map<String, PerformanceMeasure>} ili {@code Map<Object, PerformanceMeasure>} 042 * 043 * @param model A model to evaluate 044 * @param testSet Data to use for evaluation 045 * @return performance measures of a model for the specified test set 046 */ // evaluatePerformance testDataSet 047 PerformanceMeasure evaluatePerformance(T1 model, T2 testSet); // kako ce da vrati rezultate testiranja - napraviti neku klasu za to? 048 049}