.append(" subsetMiniBatches ").append(iterAfter - itersBefore) //Note: "end of epoch" effect - may be smaller than subset size .append(" trainMS ").append(end - start).append(" evalMS ").append(endEval - startEval) .append(" accuracy ").append(e.accuracy()).append(" f1 ").append(e.f1()) .append(" AvgAUC ").append(r.calculateAverageAUC()).append(" AvgAUPRC ").append(r.calculateAverageAUCPR()).append("\n");
/** * Top N accuracy of the predictions so far. For top N = 1 (default), equivalent to {@link #accuracy()} * @return Top N accuracy */ public double topNAccuracy() { if (topN <= 1) return accuracy(); if (topNTotalCount == 0) return 0.0; return topNCorrectCount / (double) topNTotalCount; }
@Override public double score(MultiLayerNetwork net, DataSetIterator iterator) { Evaluation e = net.evaluate(iterator); return e.accuracy(); }
@Override public double score(ComputationGraph graph, DataSetIterator iterator) { Evaluation e = graph.evaluate(iterator); return e.accuracy(); }
@Override public double score(ComputationGraph graph, MultiDataSetIterator iterator) { Evaluation e = graph.evaluate(iterator); return e.accuracy(); }
@Override public double calculateScore(MultiLayerNetwork network) { double sum = 0; for (DataSetIterator dataSetIterator : dataSetIterators) { Evaluation eval = network.evaluate(dataSetIterator); sum += eval.accuracy(); } return sum / dataSetIterators.length; }
double acc = accuracy(); double precisionMacro = precision(EvaluationAveraging.Macro); double recallMacro = recall(EvaluationAveraging.Macro);